{ "cells": [ { "cell_type": "markdown", "id": "2b2e7392", "metadata": {}, "source": [ "# Day 6 β€” Machines That See πŸ‘οΈ\n", "\n", "> **Mission briefing:** The Lab's camera team needs a **photo detective**: point it at a picture and it names what's there β€” one of ten everyday objects. But a plain network treats a photo as a flat list of numbers and falls apart. Today you give it real eyes: **convolutions**.\n", "\n", "**Previously in the Lab:** on Day 5 you trained your first real networks with PyTorch and unlocked **Digit Reader**. Those digits were tiny and gray β€” today we go to full color.\n", "\n", "**Today you will:**\n", "- See exactly **why** a flat network struggles with photos\n", "- Build a **convolution** by hand and watch it find edges\n", "- Train a **CNN** on **CIFAR-10** β€” ten object classes, in color\n", "- Read a **confusion matrix** and look through the network's own eyes\n", "- Road-test it on real photos β€” and meet its honest limits\n", "\n", "**Today you unlock:** πŸ”“ **Photo Detective** β€” upload a photo and the CNN *you trained* investigates.\n", "\n", "
A precise reading

Flattening preserves pixel values in a fixed order; it removes the explicit spatial structure from the layer interface. A CNN builds in local connectivity and shared weights. Day 5 trained both an MLP and a CNN. CIFAR-10 contains 50,000 training and 10,000 test images. Report the measured test score and failure cases rather than assuming a universal human baseline.

\n" ] }, { "cell_type": "code", "execution_count": null, "id": "3b1da11d", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:55:54.562600Z", "iopub.status.busy": "2026-08-17T12:55:54.562449Z", "iopub.status.idle": "2026-08-17T12:55:54.673287Z", "shell.execute_reply": "2026-08-17T12:55:54.672261Z" } }, "outputs": [], "source": [ "# ╔═══════════════════════════════════════════════════════════════════╗\n", "# β•‘ SETUP β€” run me first! (identical in every Lab notebook) β•‘\n", "# β•šβ•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•\n", "import os, sys, pathlib\n", "\n", "IN_COLAB = \"google.colab\" in sys.modules\n", "SMOKE = os.environ.get(\"SMOKE_TEST\", \"0\") == \"1\" # tiny fast run for automated tests\n", "\n", "REPO_URL = \"https://github.com/A-Halimi/ai-studio-internship.git\" # instructor: set once\n", "\n", "if IN_COLAB:\n", " if not pathlib.Path(\"/content/ai-studio-internship\").exists():\n", " !git clone -q {REPO_URL} /content/ai-studio-internship\n", " %cd /content/ai-studio-internship/notebooks/day06 # ← ADAPT day folder\n", " %pip -q install gradio==6.19.0 # ← ADAPT per-day installs (see spec; delete line if none)\n", "\n", "HERE = pathlib.Path.cwd()\n", "REPO = HERE.parents[1] # .../notebooks/dayNN -> repo root\n", "DATA_DIR = pathlib.Path(os.environ.get(\"COURSE_DATA_DIR\", REPO / \"data\"))\n", "SAMPLES_DIR = REPO / \"data_samples\" # small datasets shipped with the repo\n", "MODELS_DIR = REPO / \"ai_studio\" / \"models\" # where your Studio modules unlock\n", "for p in (REPO / \"data\", MODELS_DIR):\n", " p.mkdir(parents=True, exist_ok=True)\n", "\n", "import random\n", "import numpy as np\n", "SEED = 42\n", "random.seed(SEED); np.random.seed(SEED)\n", "print(f\"βœ… Setup done | Colab: {IN_COLAB} | Smoke test: {SMOKE}\")\n", "print(f\" data: {DATA_DIR}\")" ] }, { "cell_type": "code", "execution_count": null, "id": "baa7b39b", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:55:54.675155Z", "iopub.status.busy": "2026-08-17T12:55:54.674920Z", "iopub.status.idle": "2026-08-17T12:55:55.944966Z", "shell.execute_reply": "2026-08-17T12:55:55.943898Z" } }, "outputs": [], "source": [ "import torch\n", "torch.manual_seed(SEED)\n", "DEVICE = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n", "if DEVICE.type == \"cuda\":\n", " print(f\"⚑ Running on GPU: {torch.cuda.get_device_name(0)}\")\n", "else:\n", " print(\"🐒 No GPU found β€” running on CPU. Everything still works, just slower.\")" ] }, { "cell_type": "code", "execution_count": null, "id": "a7efbd44", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:55:55.946773Z", "iopub.status.busy": "2026-08-17T12:55:55.946544Z", "iopub.status.idle": "2026-08-17T12:55:55.950501Z", "shell.execute_reply": "2026-08-17T12:55:55.949571Z" } }, "outputs": [], "source": [ "# ── CONFIG β€” the Lab's control panel. Tweak me later! ──────────────\n", "EPOCHS = 1 if SMOKE else 8\n", "TRAIN_SUBSET = 1_000 if SMOKE else 20_000 # how many training images to use\n", "BATCH_SIZE = 128\n", "LEARNING_RATE = 1e-3\n", "print(f\"EPOCHS={EPOCHS} TRAIN_SUBSET={TRAIN_SUBSET:,} BATCH_SIZE={BATCH_SIZE} LR={LEARNING_RATE}\")" ] }, { "cell_type": "markdown", "id": "d4f97285", "metadata": {}, "source": [ "## 1. Why a flat network can't really see\n", "\n", "On Day 5 the very first layer was `nn.Flatten()`: it unrolled each 28Γ—28 image into a list of 784 numbers. That worked for neat, centered digits. For real photos it's a disaster, for three reasons:\n", "\n", "- **It destroys neighborhoods.** Flattening puts pixel (0,0) next to (0,1) but far from (1,0) β€” even though those two are neighbors on the image. The network has to *re-learn* which pixels are adjacent. That's wasteful and hard.\n", "- **It's not shift-invariant.** Move a cat 3 pixels to the right and *every* input number changes. To a flat network, the shifted cat is a brand-new, unrecognizable image.\n", "- **It explodes in size.** A color 32Γ—32 photo is 32Β·32Β·3 = 3,072 numbers. One dense layer to just 512 hidden units needs 3072Β·512 β‰ˆ **1.5 million weights** β€” for a *single* layer, on a *tiny* image.\n", "\n", "Convolutions fix all three at once." ] }, { "cell_type": "markdown", "id": "80d610b2", "metadata": {}, "source": [ "## 2. A convolution is a sliding stencil\n", "\n", "Picture a tiny **magnifying glass**, 3Γ—3 pixels wide. You slide it across the image, and at every position it asks **one fixed question** β€” say, *\"is there a vertical edge right here?\"* β€” and writes down how strongly the answer is \"yes.\"\n", "\n", "That little 3Γ—3 grid of numbers is a **kernel** (or *filter*). Sliding it over the whole image produces a new image β€” a **feature map** β€” that lights up wherever the pattern appears.\n", "\n", "The magic is that **the same kernel is used at every position**. So it finds its pattern anywhere in the image (shift-invariance βœ“), only ever looks at neighbors (respects the 2-D layout βœ“), and costs just 9 numbers instead of millions βœ“.\n", "\n", "Let's build one by hand and point it at a real photo." ] }, { "cell_type": "code", "execution_count": null, "id": "b20818ec", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:55:55.952012Z", "iopub.status.busy": "2026-08-17T12:55:55.951875Z", "iopub.status.idle": "2026-08-17T12:55:59.266772Z", "shell.execute_reply": "2026-08-17T12:55:59.265823Z" } }, "outputs": [], "source": [ "import numpy as np\n", "import torch\n", "import torch.nn.functional as F\n", "import matplotlib.pyplot as plt\n", "from sklearn.datasets import load_sample_image\n", "\n", "photo = load_sample_image(\"china.jpg\") # a real photo, no download needed\n", "gray = photo.mean(axis=2) # collapse color -> grayscale\n", "img = torch.tensor(gray, dtype=torch.float32).reshape(1, 1, *gray.shape)\n", "\n", "# A horizontal-edge detector: rows of -1 / 0 / +1\n", "h_kernel = torch.tensor([[-1., -1., -1.],\n", " [ 0., 0., 0.],\n", " [ 1., 1., 1.]]).reshape(1, 1, 3, 3)\n", "h_edges = F.conv2d(img, h_kernel)\n", "\n", "fig, axes = plt.subplots(1, 2, figsize=(10, 4))\n", "axes[0].imshow(gray, cmap=\"gray\"); axes[0].set_title(\"original\"); axes[0].axis(\"off\")\n", "axes[1].imshow(h_edges[0, 0], cmap=\"gray\"); axes[1].set_title(\"horizontal edges\"); axes[1].axis(\"off\")\n", "plt.tight_layout(); plt.show()" ] }, { "cell_type": "markdown", "id": "dc645e53", "metadata": {}, "source": [ "### πŸ§ͺ Exercise 1 β€” the vertical-edge kernel\n", "\n", "The horizontal detector had *rows* of βˆ’1 / 0 / +1. To find **vertical** edges, you need *columns* of βˆ’1 / 0 / +1 instead β€” the same idea, turned 90Β°.\n", "\n", "- Build `v_kernel` and apply it with `F.conv2d`.\n", "- Expected: the output lights up on **vertical** boundaries (the sides of pillars and doorframes) instead of horizontal ones." ] }, { "cell_type": "code", "execution_count": null, "id": "77b49792", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:55:59.269221Z", "iopub.status.busy": "2026-08-17T12:55:59.268995Z", "iopub.status.idle": "2026-08-17T12:55:59.316291Z", "shell.execute_reply": "2026-08-17T12:55:59.315229Z" } }, "outputs": [], "source": [ "# ==================== YOUR CODE HERE ====================\n", "### HINT: transpose the pattern β€” make columns of -1, 0, +1 instead of rows\n", "...\n", "v_edges = F.conv2d(img, v_kernel)\n", "\n", "fig, axes = plt.subplots(1, 3, figsize=(10, 4))\n", "axes[0].imshow(gray, cmap=\"gray\"); axes[0].set_title(\"original\"); axes[0].axis(\"off\")\n", "axes[1].imshow(h_edges[0, 0], cmap=\"gray\"); axes[1].set_title(\"horizontal edges\"); axes[1].axis(\"off\")\n", "axes[2].imshow(v_edges[0, 0], cmap=\"gray\"); axes[2].set_title(\"vertical edges\"); axes[2].axis(\"off\")\n", "plt.tight_layout(); plt.show()" ] }, { "cell_type": "markdown", "id": "6e43273b", "metadata": {}, "source": [ "### πŸ§ͺ Exercise 2 β€” a blur kernel\n", "\n", "Not every kernel finds edges. A kernel of equal positive weights that sum to 1 **averages** each neighborhood β€” a blur.\n", "\n", "- Build a 3Γ—3 kernel where every entry is `1/9`, then apply it.\n", "- Expected: a softer, smeared version of the photo." ] }, { "cell_type": "code", "execution_count": null, "id": "cfcaf6e8", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:55:59.318144Z", "iopub.status.busy": "2026-08-17T12:55:59.318002Z", "iopub.status.idle": "2026-08-17T12:55:59.360142Z", "shell.execute_reply": "2026-08-17T12:55:59.358931Z" } }, "outputs": [], "source": [ "# ==================== YOUR CODE HERE ====================\n", "### HINT: torch.ones(1, 1, 3, 3) / 9 makes nine equal weights that sum to 1\n", "...\n", "blurred = F.conv2d(img, blur_kernel)\n", "\n", "fig, axes = plt.subplots(1, 2, figsize=(10, 4))\n", "axes[0].imshow(gray, cmap=\"gray\"); axes[0].set_title(\"original\"); axes[0].axis(\"off\")\n", "axes[1].imshow(blurred[0, 0], cmap=\"gray\"); axes[1].set_title(\"blurred (3Γ—3 average)\"); axes[1].axis(\"off\")\n", "plt.tight_layout(); plt.show()" ] }, { "cell_type": "markdown", "id": "0334d471", "metadata": {}, "source": [ "## 3. Stacking convolutions = seeing bigger things\n", "\n", "One kernel finds one pattern. A convolution **layer** learns *many* kernels at once (our detective learns 32 in its first layer). Stack layers and something beautiful happens:\n", "\n", "- **Layer 1** learns edges and color blobs β€” like the ones you just built by hand.\n", "- **Layer 2** combines those edges into **corners, curves, and textures**.\n", "- **Layer 3** combines those into **object parts** β€” an ear, a wheel, an eye.\n", "\n", "And you never hand-design these kernels. The network *learns* them by gradient descent: `loss.backward()` discovers which 3Γ—3 patterns matter.\n", "\n", "> **HPC echo:** a convolution is secretly a big matrix multiply. Libraries unroll each image patch into a column (a trick called `im2col`) and hit the whole thing with one giant `@`. It's the same operation you've been staring at since Day 4 β€” which is exactly why GPUs love convolutions, and why HPC engineers obsess over making `@` fast." ] }, { "cell_type": "markdown", "id": "32e18740", "metadata": {}, "source": [ "## 4. Meet CIFAR-10 β€” the world in 32Γ—32 color\n", "\n", "**CIFAR-10** is 60,000 tiny color photos, each 32Γ—32 pixels, across 10 classes: airplane, automobile, bird, cat, deer, dog, frog, horse, ship, truck. It's the classic proving ground for \"can your network actually see?\"\n", "\n", "This time we **do** normalize the pixels to roughly βˆ’1…+1. Centering the numbers keeps training stable β€” and it's the exact recipe your Studio module expects, so remember it for the unlock: `Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))`, i.e. `(x βˆ’ 0.5) / 0.5`." ] }, { "cell_type": "code", "execution_count": null, "id": "3615a1c4", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:55:59.361876Z", "iopub.status.busy": "2026-08-17T12:55:59.361731Z", "iopub.status.idle": "2026-08-17T12:56:02.251619Z", "shell.execute_reply": "2026-08-17T12:56:02.250371Z" } }, "outputs": [], "source": [ "from torchvision import datasets, transforms\n", "from torch.utils.data import DataLoader, Subset\n", "\n", "tfm = transforms.Compose([\n", " transforms.ToTensor(), # -> [0, 1]\n", " transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)), # -> ~[-1, 1] (module contract!)\n", "])\n", "\n", "# The official CIFAR-10 server (cs.toronto.edu) is often slow β€” use a fast md5-verified mirror.\n", "# (In the Docker container the dataset is already baked in, so nothing downloads at all.)\n", "datasets.CIFAR10.url = \"https://data.brainchip.com/dataset-mirror/cifar10/cifar-10-python.tar.gz\"\n", "\n", "train_full = datasets.CIFAR10(DATA_DIR, train=True, download=True, transform=tfm)\n", "test_set = datasets.CIFAR10(DATA_DIR, train=False, download=True, transform=tfm)\n", "classes = train_full.classes\n", "train_set = Subset(train_full, range(TRAIN_SUBSET))\n", "\n", "# num_workers=0: CIFAR-10 is small and already local, so one process is plenty,\n", "# and it avoids the harmless-but-noisy DataLoader worker-shutdown warnings in Jupyter.\n", "train_loader = DataLoader(train_set, batch_size=BATCH_SIZE, shuffle=True, num_workers=0)\n", "test_loader = DataLoader(test_set, batch_size=256, shuffle=False, num_workers=0)\n", "print(\"classes:\", classes)\n", "print(f\"train images: {len(train_set):,} test images: {len(test_set):,}\")" ] }, { "cell_type": "code", "execution_count": null, "id": "1efb1f2b", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:56:02.253472Z", "iopub.status.busy": "2026-08-17T12:56:02.253196Z", "iopub.status.idle": "2026-08-17T12:56:02.571935Z", "shell.execute_reply": "2026-08-17T12:56:02.570754Z" } }, "outputs": [], "source": [ "import matplotlib.pyplot as plt\n", "\n", "fig, axes = plt.subplots(4, 8, figsize=(10, 6))\n", "for ax, idx in zip(axes.ravel(), range(32)):\n", " img_t, label = train_full[idx]\n", " ax.imshow((img_t * 0.5 + 0.5).permute(1, 2, 0)) # un-normalize: img*0.5+0.5 -> [0,1]\n", " ax.set_title(classes[label], fontsize=8)\n", " ax.axis(\"off\")\n", "fig.suptitle(\"CIFAR-10 β€” 32Γ—32 color photos\")\n", "plt.tight_layout(); plt.show()" ] }, { "cell_type": "markdown", "id": "40313e93", "metadata": {}, "source": [ "## 5. Build the detective\n", "\n", "Here's the blueprint: two **convolution blocks** to see, then two dense layers to decide.\n", "\n", "```\n", "Conv2d(3 β†’ 32, 3Γ—3, pad 1) β†’ ReLU β†’ MaxPool(2) # 32Γ—32 β†’ 16Γ—16\n", "Conv2d(32 β†’ 64, 3Γ—3, pad 1) β†’ ReLU β†’ MaxPool(2) # 16Γ—16 β†’ 8Γ—8\n", "Flatten β†’ Linear(64Β·8Β·8 β†’ 256) β†’ ReLU β†’ Dropout(0.3) β†’ Linear(256 β†’ 10)\n", "```\n", "\n", "`padding=1` keeps each conv the same width; `MaxPool2d(2)` halves it and keeps only the strongest response in each 2Γ—2 patch. `Dropout` randomly silences 30% of neurons during training so the network can't over-rely on any single one β€” cheap insurance against memorizing.\n", "\n", "### πŸ§ͺ Exercise 3 β€” assemble the CNN\n", "\n", "Translate the blueprint into an `nn.Sequential`. Match the numbers exactly β€” the unlock at the end traces this shape." ] }, { "cell_type": "code", "execution_count": null, "id": "15038a9e", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:56:02.573688Z", "iopub.status.busy": "2026-08-17T12:56:02.573446Z", "iopub.status.idle": "2026-08-17T12:56:02.984674Z", "shell.execute_reply": "2026-08-17T12:56:02.983496Z" } }, "outputs": [], "source": [ "import torch.nn as nn\n", "\n", "# ==================== YOUR CODE HERE ====================\n", "...\n", "\n", "print(detective)\n", "\n", "# shape check: a fake batch of 4 images should come out (4, 10)\n", "_probe = detective(torch.zeros(4, 3, 32, 32, device=DEVICE))\n", "assert _probe.shape == (4, 10), \"The network should output 10 scores per image\"\n", "print(\"βœ… shape check passed:\", tuple(_probe.shape))" ] }, { "cell_type": "markdown", "id": "280abecd", "metadata": {}, "source": [ "### πŸ§ͺ Exercise 4 β€” count the cost\n", "\n", "Add up the detective's parameters and compare to that 1.5-million-weight *single* MLP layer from Section 1." ] }, { "cell_type": "code", "execution_count": null, "id": "a0b03728", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:56:02.986309Z", "iopub.status.busy": "2026-08-17T12:56:02.986152Z", "iopub.status.idle": "2026-08-17T12:56:02.990556Z", "shell.execute_reply": "2026-08-17T12:56:02.989543Z" } }, "outputs": [], "source": [ "# ==================== YOUR CODE HERE ====================\n", "### HINT: sum(p.numel() for p in detective.parameters())\n", "...\n", "\n", "mlp_one_layer = 32 * 32 * 3 * 512 + 512\n", "print(f\"The whole detective: {n_params:,} parameters\")\n", "print(f\"One dense 3072β†’512 layer alone: {mlp_one_layer:,} parameters\")\n", "print(f\"Entire CNN smaller than that one layer? {n_params < mlp_one_layer}\")" ] }, { "cell_type": "markdown", "id": "e6038d4e", "metadata": {}, "source": [ "## 6. Train the detective\n", "\n", "Same five-step loop as Day 5 β€” you know this pattern cold now. We print the **test accuracy after every epoch** so you can watch it climb. On the Lab's GPU the full run takes a few minutes; grab water and watch the number go up." ] }, { "cell_type": "code", "execution_count": null, "id": "a39356b5", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:56:02.992121Z", "iopub.status.busy": "2026-08-17T12:56:02.991976Z", "iopub.status.idle": "2026-08-17T12:56:43.781391Z", "shell.execute_reply": "2026-08-17T12:56:43.779805Z" } }, "outputs": [], "source": [ "import torch.nn as nn\n", "from tqdm.auto import tqdm\n", "\n", "def evaluate(model, loader):\n", " model.eval()\n", " correct = total = 0\n", " with torch.no_grad():\n", " for images, labels in loader:\n", " preds = model(images.to(DEVICE)).argmax(1).cpu()\n", " correct += (preds == labels).sum().item()\n", " total += labels.size(0)\n", " return correct / total\n", "\n", "loss_fn = nn.CrossEntropyLoss()\n", "optimizer = torch.optim.Adam(detective.parameters(), lr=LEARNING_RATE)\n", "\n", "for epoch in range(1, EPOCHS + 1):\n", " detective.train()\n", " running = 0.0\n", " for images, labels in tqdm(train_loader, desc=f\"epoch {epoch}/{EPOCHS}\"):\n", " images, labels = images.to(DEVICE), labels.to(DEVICE)\n", " optimizer.zero_grad()\n", " loss = loss_fn(detective(images), labels)\n", " loss.backward()\n", " optimizer.step()\n", " running += loss.item() * images.size(0)\n", " train_loss = running / len(train_loader.dataset)\n", " test_acc = evaluate(detective, test_loader)\n", " print(f\"epoch {epoch}: train loss {train_loss:.3f} | test accuracy {test_acc:.3f}\")\n", "\n", "if not SMOKE:\n", " assert test_acc > 0.60, \"Expected > 60% after the full run β€” give it all 8 epochs on GPU\"" ] }, { "cell_type": "markdown", "id": "f7cc3d56", "metadata": {}, "source": [ "### How good is 70%, really?\n", "\n", "If that number feels low, hold on. Random guessing across 10 classes is **10%** β€” your detective is already **7Γ— better than chance**, learned from just 20,000 tiny images. Humans score about **94%** on CIFAR-10, and they've had years of practice.\n", "\n", "The gap is real, though, and tomorrow you'll close most of it with one trick. For now, look at *where* it goes wrong β€” that's where the story is." ] }, { "cell_type": "markdown", "id": "bc120d59", "metadata": {}, "source": [ "## 7. Where does it get confused?\n", "\n", "A **confusion matrix** counts, for every true class, what the network actually *guessed*. The diagonal is correct answers; bright spots off the diagonal are mix-ups.\n", "\n", "### πŸ§ͺ Exercise 5 β€” build the confusion matrix\n", "\n", "Loop over the test set and tally `cm[true, predicted] += 1` for each image." ] }, { "cell_type": "code", "execution_count": null, "id": "71a85085", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:56:43.783401Z", "iopub.status.busy": "2026-08-17T12:56:43.783238Z", "iopub.status.idle": "2026-08-17T12:56:45.377958Z", "shell.execute_reply": "2026-08-17T12:56:45.376748Z" } }, "outputs": [], "source": [ "import numpy as np\n", "import seaborn as sns\n", "import matplotlib.pyplot as plt\n", "\n", "detective.eval()\n", "cm = np.zeros((10, 10), dtype=int)\n", "with torch.no_grad():\n", " for images, labels in test_loader:\n", " preds = detective(images.to(DEVICE)).argmax(1).cpu().numpy()\n", " # ==================== YOUR CODE HERE ====================\n", " ### HINT: for each (true, pred) pair, do cm[true, pred] += 1\n", " ...\n", "\n", "plt.figure(figsize=(8, 6))\n", "sns.heatmap(cm, annot=True, fmt=\"d\", cmap=\"Blues\",\n", " xticklabels=classes, yticklabels=classes)\n", "plt.xlabel(\"predicted class\"); plt.ylabel(\"true class\")\n", "plt.title(\"Confusion matrix β€” where the detective gets confused\")\n", "plt.tight_layout(); plt.show()" ] }, { "cell_type": "markdown", "id": "829c3ae5", "metadata": {}, "source": [ "Look at the brightest off-diagonal cells. Almost always it's **cat ↔ dog** and **deer ↔ horse** β€” four-legged, furry, similar silhouettes once you shrink them to 32Γ—32. Your network isn't making *random* mistakes; it's making the same ones a squinting human would. That's a sign it learned something real about shape and texture." ] }, { "cell_type": "markdown", "id": "2d4b816d", "metadata": {}, "source": [ "## 8. See through the detective's eyes\n", "\n", "Two ways to peek inside. First, the **32 filters** its first layer learned β€” tiny 3Γ—3 color patterns, the machine-designed cousins of your hand-built edge kernels. Second, the **feature maps**: what those filters light up on for a real image." ] }, { "cell_type": "code", "execution_count": null, "id": "ad9829bb", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:56:45.379904Z", "iopub.status.busy": "2026-08-17T12:56:45.379755Z", "iopub.status.idle": "2026-08-17T12:56:45.766987Z", "shell.execute_reply": "2026-08-17T12:56:45.765900Z" } }, "outputs": [], "source": [ "import matplotlib.pyplot as plt\n", "\n", "# The 32 first-layer filters, shown as little color squares\n", "w = detective[0].weight.detach().cpu() # shape (32, 3, 3, 3)\n", "w = (w - w.min()) / (w.max() - w.min()) # scale to [0,1] for display\n", "\n", "fig, axes = plt.subplots(4, 8, figsize=(9, 5))\n", "for ax, i in zip(axes.ravel(), range(32)):\n", " ax.imshow(w[i].permute(1, 2, 0)) # (3,3,3) C,H,W -> H,W,C\n", " ax.axis(\"off\")\n", "fig.suptitle(\"Layer 1 β€” the 32 tiny 3Γ—3 filters the detective learned\")\n", "plt.tight_layout(); plt.show()" ] }, { "cell_type": "code", "execution_count": null, "id": "0c8ae583", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:56:45.768585Z", "iopub.status.busy": "2026-08-17T12:56:45.768441Z", "iopub.status.idle": "2026-08-17T12:56:45.940036Z", "shell.execute_reply": "2026-08-17T12:56:45.938935Z" } }, "outputs": [], "source": [ "# Feature maps: run one test image through just the first conv layer\n", "detective.eval()\n", "img_t, label = test_set[0]\n", "with torch.no_grad():\n", " fmaps = detective[0](img_t.unsqueeze(0).to(DEVICE))[0].cpu() # (32, 32, 32)\n", "\n", "fig, axes = plt.subplots(4, 8, figsize=(9, 5))\n", "for ax, i in zip(axes.ravel(), range(32)):\n", " ax.imshow(fmaps[i], cmap=\"viridis\")\n", " ax.axis(\"off\")\n", "fig.suptitle(f\"Feature maps of conv-1 for a '{classes[label]}' image\")\n", "plt.tight_layout(); plt.show()" ] }, { "cell_type": "markdown", "id": "3de4a32c", "metadata": {}, "source": [ "### πŸ§ͺ Exercise 6 β€” look at a different class\n", "\n", "Pick a class name (try `\"ship\"`, `\"frog\"`, or `\"airplane\"`), find the first test image of that class, and show conv-1's feature maps for it. Notice how a *different* set of the 32 maps lights up than for the previous image β€” same filters, different features triggered." ] }, { "cell_type": "code", "execution_count": null, "id": "3e7966bb", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:56:45.942129Z", "iopub.status.busy": "2026-08-17T12:56:45.941983Z", "iopub.status.idle": "2026-08-17T12:56:46.110014Z", "shell.execute_reply": "2026-08-17T12:56:46.108898Z" } }, "outputs": [], "source": [ "target_class = \"ship\"\n", "\n", "# ==================== YOUR CODE HERE ====================\n", "### HINT: scan test_set for the first image whose label name matches target_class\n", "...\n", "\n", "fig, axes = plt.subplots(4, 8, figsize=(9, 5))\n", "for ax, i in zip(axes.ravel(), range(32)):\n", " ax.imshow(fmaps[i], cmap=\"viridis\")\n", " ax.axis(\"off\")\n", "fig.suptitle(f\"Feature maps of conv-1 for a '{classes[label]}' image\")\n", "plt.tight_layout(); plt.show()" ] }, { "cell_type": "markdown", "id": "4341ccd5", "metadata": {}, "source": [ "## 9. Why train on a GPU?\n", "\n", "Convolutions are even hungrier than the plain matrix multiplies you timed on Day 5 β€” so a GPU pulls even further ahead. Let's time a few real training steps of the detective on each device.\n", "\n", "### πŸ§ͺ Exercise 7 β€” time a training step, GPU vs CPU\n", "\n", "Fill in the timed loop. The warm-up pass and `torch.cuda.synchronize()` are given β€” remember, a GPU runs *asynchronously*, so you must wait for it to finish before stopping the clock." ] }, { "cell_type": "code", "execution_count": null, "id": "f76689d1", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:56:46.112055Z", "iopub.status.busy": "2026-08-17T12:56:46.111917Z", "iopub.status.idle": "2026-08-17T12:56:48.074251Z", "shell.execute_reply": "2026-08-17T12:56:48.073088Z" } }, "outputs": [], "source": [ "import time\n", "import copy\n", "import torch.nn as nn\n", "\n", "loss_fn = nn.CrossEntropyLoss()\n", "images, labels = next(iter(train_loader))\n", "N_STEPS = 3 if SMOKE else 20\n", "\n", "def time_training_steps(model, imgs, lbls, n_steps):\n", " opt = torch.optim.Adam(model.parameters(), lr=LEARNING_RATE)\n", " model.train()\n", " # warm-up (first pass builds kernels / caches)\n", " loss_fn(model(imgs), lbls).backward()\n", " if imgs.is_cuda:\n", " torch.cuda.synchronize()\n", " # ==================== YOUR CODE HERE ====================\n", " ### HINT: time n_steps of (zero_grad, forward+loss, backward, step); synchronize if on GPU\n", " ...\n", "\n", "cpu_model = copy.deepcopy(detective).cpu()\n", "cpu_t = time_training_steps(cpu_model, images.cpu(), labels.cpu(), N_STEPS)\n", "print(f\"CPU: {cpu_t * 1e3:8.1f} ms per training step\")\n", "\n", "if DEVICE.type == \"cuda\":\n", " gpu_model = copy.deepcopy(detective).to(DEVICE)\n", " gpu_t = time_training_steps(gpu_model, images.to(DEVICE), labels.to(DEVICE), N_STEPS)\n", " print(f\"GPU: {gpu_t * 1e3:8.1f} ms per training step\")\n", " print(f\"β†’ the GPU is {cpu_t / gpu_t:.1f}Γ— faster at training this CNN\")\n", "else:\n", " print(\"🐒 CPU only β€” on the Lab's GPU this step would be many times faster.\")" ] }, { "cell_type": "markdown", "id": "0943138f", "metadata": {}, "source": [ "## 10. Road test on real photos\n", "\n", "Your detective only ever saw 32Γ—32 CIFAR images. What happens on a full-size photo from the wild? The helper below center-crops any image, shrinks it to the detective's tiny 32Γ—32 world, normalizes it exactly like training, and shows you both what *you* see and what *it* sees." ] }, { "cell_type": "code", "execution_count": null, "id": "9f91a276", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:56:48.075964Z", "iopub.status.busy": "2026-08-17T12:56:48.075815Z", "iopub.status.idle": "2026-08-17T12:56:48.294902Z", "shell.execute_reply": "2026-08-17T12:56:48.293782Z" } }, "outputs": [], "source": [ "import numpy as np\n", "from PIL import Image\n", "import matplotlib.pyplot as plt\n", "from sklearn.datasets import load_sample_image\n", "\n", "def road_test(pil_img, title):\n", " im = pil_img.convert(\"RGB\")\n", " side = min(im.size) # square center-crop\n", " left, top = (im.width - side) // 2, (im.height - side) // 2\n", " im32 = im.crop((left, top, left + side, top + side)).resize((32, 32), Image.LANCZOS)\n", "\n", " x = torch.from_numpy(np.asarray(im32, np.float32) / 255.0).permute(2, 0, 1).unsqueeze(0)\n", " x = (x - 0.5) / 0.5 # the exact training normalization\n", " detective.eval()\n", " dev = next(detective.parameters()).device # follow the model onto whatever device it is on\n", " with torch.no_grad():\n", " probs = torch.softmax(detective(x.to(dev))[0], dim=0)\n", " top = int(probs.argmax())\n", "\n", " fig, axes = plt.subplots(1, 2, figsize=(6, 3))\n", " axes[0].imshow(im); axes[0].set_title(title); axes[0].axis(\"off\")\n", " axes[1].imshow(im32); axes[1].axis(\"off\")\n", " axes[1].set_title(f\"detective sees 32Γ—32\\nβ†’ {classes[top]} ({float(probs[top]):.0%})\")\n", " plt.tight_layout(); plt.show()\n", "\n", "road_test(Image.fromarray(load_sample_image(\"flower.jpg\")), \"flower.jpg\")\n", "road_test(Image.fromarray(load_sample_image(\"china.jpg\")), \"china.jpg\")\n", "road_test(Image.open(SAMPLES_DIR / \"rps_starter\" / \"rock\" / \"rock_01.jpg\"), \"your rock ✊\")\n", "road_test(Image.open(SAMPLES_DIR / \"rps_starter\" / \"scissors\" / \"scissors_01.jpg\"), \"your scissors ✌️\")" ] }, { "cell_type": "markdown", "id": "27bb80d5", "metadata": {}, "source": [ "### The honest limits\n", "\n", "On the flower and the landscape, the detective does its best to squeeze them into its 10 boxes. But your **hand** photos? It has no \"hand\" class β€” it was never taught one β€” so it is *forced* to shout \"cat!\" or \"bird!\" with total confidence.\n", "\n", "That's not a bug; it's the deal you made when you trained on only 10 classes and 20,000 tiny images. **Tomorrow you'll fix exactly this**, by borrowing a network that has already seen over a million photos of a thousand kinds of things." ] }, { "cell_type": "markdown", "id": "d413827f", "metadata": {}, "source": [ "## 11. The Photo Detective mini-app\n", "\n", "Same preprocessing, wrapped in a little upload-and-investigate interface β€” a preview of the Studio tab you're about to unlock." ] }, { "cell_type": "code", "execution_count": null, "id": "fd1a8979", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:56:48.296832Z", "iopub.status.busy": "2026-08-17T12:56:48.296654Z", "iopub.status.idle": "2026-08-17T12:56:50.198003Z", "shell.execute_reply": "2026-08-17T12:56:50.196573Z" } }, "outputs": [], "source": [ "import gradio as gr\n", "\n", "detective.eval()\n", "\n", "def investigate(img):\n", " if img is None:\n", " return {}, None\n", " im = Image.fromarray(img).convert(\"RGB\")\n", " side = min(im.size)\n", " left, top = (im.width - side) // 2, (im.height - side) // 2\n", " im32 = im.crop((left, top, left + side, top + side)).resize((32, 32), Image.LANCZOS)\n", " x = torch.from_numpy(np.asarray(im32, np.float32) / 255.0).permute(2, 0, 1).unsqueeze(0)\n", " x = (x - 0.5) / 0.5\n", " dev = next(detective.parameters()).device # follow the model onto whatever device it is on\n", " with torch.no_grad():\n", " probs = torch.softmax(detective(x.to(dev))[0], dim=0)\n", " preview = np.kron(np.asarray(im32), np.ones((8, 8, 1), np.uint8))\n", " return {c: float(p) for c, p in zip(classes, probs)}, preview\n", "\n", "with gr.Blocks() as demo:\n", " gr.Markdown(\"## πŸ•΅οΈ Photo Detective β€” upload a photo of one of the 10 classes\")\n", " with gr.Row():\n", " inp = gr.Image(type=\"numpy\", label=\"Evidence (your photo)\")\n", " with gr.Column():\n", " out = gr.Label(num_top_classes=5, label=\"Verdict\")\n", " seen = gr.Image(label=\"What the detective sees (32Γ—32)\", height=200)\n", " inp.change(investigate, inp, [out, seen])\n", "\n", "if not SMOKE:\n", " demo.launch(share=IN_COLAB)" ] }, { "cell_type": "markdown", "id": "919d11ff", "metadata": {}, "source": [ "## πŸ”“ Unlock your Studio module\n", "\n", "Ship it. We export the trained CNN as **TorchScript**, plus a small JSON file listing the 10 class names so the Studio knows what each output means. The input contract: a `(1, 3, 32, 32)` tensor, normalized with `(x βˆ’ 0.5) / 0.5` β€” exactly what your `road_test` helper produced." ] }, { "cell_type": "code", "execution_count": null, "id": "1aa53ebb", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:56:50.199982Z", "iopub.status.busy": "2026-08-17T12:56:50.199805Z", "iopub.status.idle": "2026-08-17T12:56:50.522333Z", "shell.execute_reply": "2026-08-17T12:56:50.521140Z" } }, "outputs": [], "source": [ "import json\n", "\n", "REQUIRED_FILES = [\"photo_detective.pt\", \"photo_detective_classes.json\"]\n", "\n", "detective.eval()\n", "example = torch.zeros(1, 3, 32, 32) # input contract: (1,3,32,32), normalized\n", "scripted = torch.jit.trace(detective.cpu(), example) # trace on CPU; the Studio runs on CPU\n", "scripted.save(str(MODELS_DIR / \"photo_detective.pt\"))\n", "detective.to(DEVICE) # put the live model back on its device\n", "\n", "(MODELS_DIR / \"photo_detective_classes.json\").write_text(\n", " json.dumps(list(classes)), encoding=\"utf-8\")\n", "\n", "missing = [f for f in REQUIRED_FILES if not (MODELS_DIR / f).exists()]\n", "assert not missing, f\"Something didn't save: {missing}\"\n", "print(\"πŸ”“ UNLOCKED: Photo Detective! Run the Studio to see it live:\")\n", "print(\" python ai_studio/app.py (from the repo root)\")" ] }, { "cell_type": "markdown", "id": "0a0e78d3", "metadata": {}, "source": [ "## 🏁 Checkpoint\n", "\n", "Today you gave a network eyes:\n", "\n", "- βœ… Saw why flattening a photo throws away everything that matters\n", "- βœ… Built edge and blur **convolutions** by hand with `F.conv2d`\n", "- βœ… Trained a **CNN** on CIFAR-10 to roughly **7Γ— better than guessing**\n", "- βœ… Read a **confusion matrix** and visualized the filters it learned\n", "- πŸ”“ Unlocked **Photo Detective** in your AI Studio\n", "\n", "Your detective learned from just 20,000 tiny images. That's why it tops out around 70% β€” and why a photo of your hand comes back as \"cat.\"\n", "\n", "**Tomorrow β€” Day 7, \"Standing on Giants\":** 36 photos could never train a great network from scratch. So you won't. You'll **borrow 1.2 million photos' worth of experience** from a network trained on ImageNet and fine-tune it on rock-paper-scissors in minutes. It's the shortcut the pros actually use. πŸͺ¨πŸ“„βœ‚οΈ" ] }, { "cell_type": "markdown", "id": "2bd7f163", "metadata": {}, "source": [ "---\n", "\n", "
\n", " \n", " \"Dr.\n", " \n", "
\n", "\n", "
The Lab Β· AI Studio β€” Intro to AI Β· Β© 2026 Dr. Abdelghafour HALIMI Β· ahalimi.com Β· All rights reserved.
" ] } ], "metadata": { "authors": [ { "name": "Dr. Abdelghafour HALIMI" } ], "copyright": "Β© 2026 Dr. Abdelghafour HALIMI Β· ahalimi.com Β· All rights reserved", "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.12.3" }, "widgets": { "application/vnd.jupyter.widget-state+json": { "state": { "023f8b35c5c040c987a9e53c86521ed6": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "0445f1095e194c8f941403cde49f1d35": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "05dc80d035304c09bbc5920e7405619f": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "0ab115ead4824baa96ad1e077fe6fdb6": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "0b4dad765e8a4d89a3df9bc1932c1a63": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "HTMLView", "description": "", "description_allow_html": false, "layout": "IPY_MODEL_023f8b35c5c040c987a9e53c86521ed6", "placeholder": "​", "style": "IPY_MODEL_2417308cd0744de5ac830f0f8e2cb49c", "tabbable": null, "tooltip": null, "value": " 157/157 [00:03<00:00, 42.08it/s]" } }, "0e3365441a2b4f5da7d27ba7c7d74c0d": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "HTMLView", "description": "", "description_allow_html": false, "layout": "IPY_MODEL_6e0850cdb2ba4a2c9d9deac8b411286d", "placeholder": "​", "style": "IPY_MODEL_287c04e29f3048df9a4b5bfe8728f4f3", "tabbable": null, "tooltip": null, "value": "epoch 5/8: 100%" } }, "0e81156c06094d75a1ae2850d01d5515": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "StyleView", "background": null, "description_width": "", "font_size": null, "text_color": null } }, "0ee34cb6be3c452c91bdf403564fdd6a": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "0f21d990c6f84700a55980c71b15670e": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "11ff4df95a50411a992d94a39d8edf78": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "12bc3d99874c4310848b28a2dc0e1a1c": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "187ab011f4834a0185a919e6fb72c0ce": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "19878079fd5345839d876ea93d939618": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "StyleView", "background": null, "description_width": "", "font_size": null, "text_color": null } }, "1db3d83ac54f4f8383b1c08ce55a1848": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "1ed1ee077cff4378849051eb32956e8b": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_63516cf828ea4b3fbb442ee3bfbb75a2", "IPY_MODEL_f7911f3960ad48ce85ce15db2dc57020", "IPY_MODEL_59d7aa8e85854a73a7e979d3ae3175a7" ], "layout": "IPY_MODEL_0ee34cb6be3c452c91bdf403564fdd6a", "tabbable": null, "tooltip": null } }, "23371de63f7e4a54b0edafb8bcb4957c": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "2417308cd0744de5ac830f0f8e2cb49c": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "StyleView", "background": null, "description_width": "", "font_size": null, "text_color": null } }, "284531189488420a8d4fc23409287606": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "287c04e29f3048df9a4b5bfe8728f4f3": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "StyleView", "background": null, "description_width": "", "font_size": null, "text_color": null } }, "2b1a55db867440d1a368a5609688dfad": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "2db48289f992487597968e5f7291b2e1": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_allow_html": false, "layout": "IPY_MODEL_feca8e79f5bd474c91a3f0cae817ad1b", "max": 157, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_44d915e25bcb4df0a8897a7d944040eb", "tabbable": null, "tooltip": null, "value": 157 } }, "31d78e770d7349c29890e552459fc39d": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_a86c9e9bcbbe45f1aa8572bff4a6f135", "IPY_MODEL_f30fad5eff5c41f490b771cf47b3a88b", "IPY_MODEL_5db4e5ec773a464e975e5dce94149699" ], "layout": "IPY_MODEL_38818fc5064c4296a72bde71242b6572", "tabbable": null, "tooltip": null } }, "329a17fd17744d8db1c5fbae4320d938": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "HTMLView", "description": "", "description_allow_html": false, "layout": "IPY_MODEL_0f21d990c6f84700a55980c71b15670e", "placeholder": "​", "style": "IPY_MODEL_40a95d7299d84ca98187f3f7d4720a21", "tabbable": null, "tooltip": null, "value": "epoch 7/8: 100%" } }, "381ac43a9dee412b8721e79162d6262a": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "StyleView", "background": null, "description_width": "", "font_size": null, "text_color": null } }, "38818fc5064c4296a72bde71242b6572": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "39a775bc82624e2b9eb26c060073602e": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "StyleView", "background": null, "description_width": "", "font_size": null, "text_color": null } }, "3e1e9d6f07f242948493e98a3908334c": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "StyleView", "background": null, "description_width": "", "font_size": null, "text_color": null } }, "40a95d7299d84ca98187f3f7d4720a21": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "StyleView", "background": null, "description_width": "", "font_size": null, "text_color": null } }, "42162c666fb5411d9de3ae492f0bd915": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_0e3365441a2b4f5da7d27ba7c7d74c0d", "IPY_MODEL_d17fe87bfd32493abf9ce3a90a746de4", "IPY_MODEL_8fc434efb7b8441497266f83ac180bb8" ], "layout": "IPY_MODEL_6db3a05e157a44e1be35b84a83c02eaf", "tabbable": null, "tooltip": null } }, "435e20b70d2e46ad83f4237bb0a09167": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "44d915e25bcb4df0a8897a7d944040eb": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "47e262efd3b745c3b9e58848b9ebddda": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_allow_html": false, "layout": "IPY_MODEL_a3e8b3988c87455cb4654369280a0bd4", "max": 157, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_fba8ee2432e74bf0bf79f84bc58e02d4", "tabbable": null, "tooltip": null, "value": 157 } }, "4c1c4ddf02c2482684c8d24b2474d1b4": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "StyleView", "background": null, "description_width": "", "font_size": null, "text_color": null } }, "4c2b1f915fd24256860219b5b51960e3": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_95ab58dff1a7436ca685be932133b46c", "IPY_MODEL_5fdfb6518a1345f987cc2ab286864fdc", "IPY_MODEL_c3f805f1fac743fcaac86caf4d495ad1" ], "layout": "IPY_MODEL_187ab011f4834a0185a919e6fb72c0ce", "tabbable": null, "tooltip": null } }, "4c5a8cf76bbe46918ad781a21471dad8": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "51da0dd9b4d04ede9a3bd914a913cc93": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "HTMLView", "description": "", "description_allow_html": false, "layout": "IPY_MODEL_23371de63f7e4a54b0edafb8bcb4957c", "placeholder": "​", "style": "IPY_MODEL_3e1e9d6f07f242948493e98a3908334c", "tabbable": null, "tooltip": null, "value": " 157/157 [00:03<00:00, 44.03it/s]" } }, "5256a4a1507e48aa9b7f3135edd5341a": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "StyleView", "background": null, "description_width": "", "font_size": null, "text_color": null } }, "546f4624d3f14ba1a691be2be80f9fa5": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_a03ddc1a781948998703610bf990488c", "IPY_MODEL_8e5ce8efce07487d8c7cf4129b8d6b62", "IPY_MODEL_51da0dd9b4d04ede9a3bd914a913cc93" ], "layout": "IPY_MODEL_05dc80d035304c09bbc5920e7405619f", "tabbable": null, "tooltip": null } }, "5688e127bc5048349e4c0e508c3498e4": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "59d7aa8e85854a73a7e979d3ae3175a7": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "HTMLView", "description": "", "description_allow_html": false, "layout": "IPY_MODEL_ac67e5d8a1ae4f959d91d65337eb691d", "placeholder": "​", "style": "IPY_MODEL_fe97b9c9e0b54a75a4247fa21706f6c1", "tabbable": null, "tooltip": null, "value": " 157/157 [00:05<00:00, 42.89it/s]" } }, "5db4e5ec773a464e975e5dce94149699": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "HTMLView", "description": "", "description_allow_html": false, "layout": "IPY_MODEL_f3cf80b6c7fd483bab668c9732acacde", "placeholder": "​", "style": "IPY_MODEL_5256a4a1507e48aa9b7f3135edd5341a", "tabbable": null, "tooltip": null, "value": " 157/157 [00:03<00:00, 43.69it/s]" } }, "5fdfb6518a1345f987cc2ab286864fdc": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_allow_html": false, "layout": "IPY_MODEL_1db3d83ac54f4f8383b1c08ce55a1848", "max": 157, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_682dea562c1b4e7b83373e69daab5de9", "tabbable": null, "tooltip": null, "value": 157 } }, "63516cf828ea4b3fbb442ee3bfbb75a2": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "HTMLView", "description": "", "description_allow_html": false, "layout": "IPY_MODEL_c256c7a108c544ba8a12f5c349185a62", "placeholder": "​", "style": "IPY_MODEL_cd906d32e1154a09a85dc64e6fd028fd", "tabbable": null, "tooltip": null, "value": "epoch 6/8: 100%" } }, "682dea562c1b4e7b83373e69daab5de9": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "682ef37b005f4eac859fa6cb5039d5f5": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "6db3a05e157a44e1be35b84a83c02eaf": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "6e0850cdb2ba4a2c9d9deac8b411286d": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "74e9a8df1dcf497cbc3881479fa78025": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "7d7f003d16044462998ad0162ef3b139": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "80e5df71ca73465dab76942c3a57ec21": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "846883cf7ee54aa48c4159dd97dd0fd4": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "84e9070825aa4d178e1aefd34c693919": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "8ac38f77e67647e780619de8c62cb24e": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "8e5ce8efce07487d8c7cf4129b8d6b62": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_allow_html": false, "layout": "IPY_MODEL_435e20b70d2e46ad83f4237bb0a09167", "max": 157, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_eb5e75830cb24be3b53916c52f0a2d25", "tabbable": null, "tooltip": null, "value": 157 } }, "8fc434efb7b8441497266f83ac180bb8": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "HTMLView", "description": "", "description_allow_html": false, "layout": "IPY_MODEL_5688e127bc5048349e4c0e508c3498e4", "placeholder": "​", "style": "IPY_MODEL_d82f3effad7f4962909a596a85563a58", "tabbable": null, "tooltip": null, "value": " 157/157 [00:03<00:00, 43.67it/s]" } }, "9160df6b4c6c4d049571cfe7cab6c0be": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "StyleView", "background": null, "description_width": "", "font_size": null, "text_color": null } }, "95ab58dff1a7436ca685be932133b46c": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "HTMLView", "description": "", "description_allow_html": false, "layout": "IPY_MODEL_a09d1e7524744328a3e565b5ed653e3d", "placeholder": "​", "style": "IPY_MODEL_0e81156c06094d75a1ae2850d01d5515", "tabbable": null, "tooltip": null, "value": "epoch 2/8: 100%" } }, "9e4d02eba18e45a9bfa34cc9d415812b": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "HTMLView", "description": "", "description_allow_html": false, "layout": "IPY_MODEL_fb741573331a44bc866e77821aa1c6d2", "placeholder": "​", "style": "IPY_MODEL_d485f20e28a949e19a4eb66a5260996b", "tabbable": null, "tooltip": null, "value": "epoch 8/8: 100%" } }, "a03ddc1a781948998703610bf990488c": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "HTMLView", "description": "", "description_allow_html": false, "layout": "IPY_MODEL_7d7f003d16044462998ad0162ef3b139", "placeholder": "​", "style": "IPY_MODEL_19878079fd5345839d876ea93d939618", "tabbable": null, "tooltip": null, "value": "epoch 4/8: 100%" } }, "a09d1e7524744328a3e565b5ed653e3d": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "a3e8b3988c87455cb4654369280a0bd4": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "a7a895908568472eb3fc7d7d4a013eab": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_cbe37e34221c47b699971baa60b8b290", "IPY_MODEL_47e262efd3b745c3b9e58848b9ebddda", "IPY_MODEL_c454180939bd49d5bd5a59111c02c131" ], "layout": "IPY_MODEL_12bc3d99874c4310848b28a2dc0e1a1c", "tabbable": null, "tooltip": null } }, "a86c9e9bcbbe45f1aa8572bff4a6f135": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "HTMLView", "description": "", "description_allow_html": false, "layout": "IPY_MODEL_4c5a8cf76bbe46918ad781a21471dad8", "placeholder": "​", "style": "IPY_MODEL_4c1c4ddf02c2482684c8d24b2474d1b4", "tabbable": null, "tooltip": null, "value": "epoch 3/8: 100%" } }, "ac67e5d8a1ae4f959d91d65337eb691d": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "bd2d6620aee747909351b622a29e4805": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_9e4d02eba18e45a9bfa34cc9d415812b", "IPY_MODEL_de878d5ebc924aab86f9c13ff7b8cbff", "IPY_MODEL_0b4dad765e8a4d89a3df9bc1932c1a63" ], "layout": "IPY_MODEL_11ff4df95a50411a992d94a39d8edf78", "tabbable": null, "tooltip": null } }, "bfddec0a77b54da097012e11692af7f7": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "c0492f40233b41bcad62a6d0d751723b": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "StyleView", "background": null, "description_width": "", "font_size": null, "text_color": null } }, "c256c7a108c544ba8a12f5c349185a62": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "c2ff9b1d81c3400d9ac0424d0d19b2f2": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "c3f805f1fac743fcaac86caf4d495ad1": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "HTMLView", "description": "", "description_allow_html": false, "layout": "IPY_MODEL_8ac38f77e67647e780619de8c62cb24e", "placeholder": "​", "style": "IPY_MODEL_9160df6b4c6c4d049571cfe7cab6c0be", "tabbable": null, "tooltip": null, "value": " 157/157 [00:03<00:00, 49.80it/s]" } }, "c454180939bd49d5bd5a59111c02c131": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "HTMLView", "description": "", "description_allow_html": false, "layout": "IPY_MODEL_284531189488420a8d4fc23409287606", "placeholder": "​", "style": "IPY_MODEL_381ac43a9dee412b8721e79162d6262a", "tabbable": null, "tooltip": null, "value": " 157/157 [00:03<00:00, 52.66it/s]" } }, "c8ee25f90adf4beb95e36ee267f9b31a": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "HTMLView", "description": "", "description_allow_html": false, "layout": "IPY_MODEL_80e5df71ca73465dab76942c3a57ec21", "placeholder": "​", "style": "IPY_MODEL_c0492f40233b41bcad62a6d0d751723b", "tabbable": null, "tooltip": null, "value": " 157/157 [00:03<00:00, 41.70it/s]" } }, "cbe37e34221c47b699971baa60b8b290": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "HTMLView", "description": "", "description_allow_html": false, "layout": "IPY_MODEL_d67410fcff6445c388363cd52771caf4", "placeholder": "​", "style": "IPY_MODEL_39a775bc82624e2b9eb26c060073602e", "tabbable": null, "tooltip": null, "value": "epoch 1/8: 100%" } }, "cd906d32e1154a09a85dc64e6fd028fd": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "StyleView", "background": null, "description_width": "", "font_size": null, "text_color": null } }, "d17fe87bfd32493abf9ce3a90a746de4": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_allow_html": false, "layout": "IPY_MODEL_682ef37b005f4eac859fa6cb5039d5f5", "max": 157, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_84e9070825aa4d178e1aefd34c693919", "tabbable": null, "tooltip": null, "value": 157 } }, "d485f20e28a949e19a4eb66a5260996b": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "StyleView", "background": null, "description_width": "", "font_size": null, "text_color": null } }, "d67410fcff6445c388363cd52771caf4": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "d82f3effad7f4962909a596a85563a58": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "StyleView", "background": null, "description_width": "", "font_size": null, "text_color": null } }, "de878d5ebc924aab86f9c13ff7b8cbff": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_allow_html": false, "layout": "IPY_MODEL_846883cf7ee54aa48c4159dd97dd0fd4", "max": 157, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_74e9a8df1dcf497cbc3881479fa78025", "tabbable": null, "tooltip": null, "value": 157 } }, "eb5e75830cb24be3b53916c52f0a2d25": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "f30fad5eff5c41f490b771cf47b3a88b": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_allow_html": false, "layout": "IPY_MODEL_0445f1095e194c8f941403cde49f1d35", "max": 157, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_0ab115ead4824baa96ad1e077fe6fdb6", "tabbable": null, "tooltip": null, "value": 157 } }, "f3cf80b6c7fd483bab668c9732acacde": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "f7911f3960ad48ce85ce15db2dc57020": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_allow_html": false, "layout": "IPY_MODEL_c2ff9b1d81c3400d9ac0424d0d19b2f2", "max": 157, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_2b1a55db867440d1a368a5609688dfad", "tabbable": null, "tooltip": null, "value": 157 } }, "f8979d4dd39448b9adb35d5c52e51254": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "2.0.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_329a17fd17744d8db1c5fbae4320d938", "IPY_MODEL_2db48289f992487597968e5f7291b2e1", "IPY_MODEL_c8ee25f90adf4beb95e36ee267f9b31a" ], "layout": "IPY_MODEL_bfddec0a77b54da097012e11692af7f7", "tabbable": null, "tooltip": null } }, "fb741573331a44bc866e77821aa1c6d2": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "fba8ee2432e74bf0bf79f84bc58e02d4": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "fe97b9c9e0b54a75a4247fa21706f6c1": { "model_module": "@jupyter-widgets/controls", "model_module_version": "2.0.0", "model_name": "HTMLStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "2.0.0", "_model_name": "HTMLStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "StyleView", "background": null, "description_width": "", "font_size": null, "text_color": null } }, "feca8e79f5bd474c91a3f0cae817ad1b": { "model_module": "@jupyter-widgets/base", "model_module_version": "2.0.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "2.0.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "2.0.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border_bottom": null, "border_left": null, "border_right": null, "border_top": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } } }, "version_major": 2, "version_minor": 0 } } }, "nbformat": 4, "nbformat_minor": 5 }