{ "cells": [ { "cell_type": "markdown", "id": "686375ac", "metadata": {}, "source": [ "# Day 5 — Superpowers: PyTorch + GPU ⚡\n", "\n", "> **Mission briefing:** Yesterday you hand-built a neural network's engine in pure NumPy — and felt the pain: roughly **130 forward passes** just to nudge the weights *once*. Today the Lab issues you power tools. A library called **PyTorch** computes those nudges automatically and exactly, and a **GPU** runs them at ludicrous speed. Your mission: teach a network to read handwriting — then point it at *your own*.\n", "\n", "**Previously in the Lab:** on Day 4 you built a neural net by hand and earned a deep respect for backpropagation (and no module — just calluses). Today you get the tools the pros actually use.\n", "\n", "**Today you will:**\n", "- Meet **tensors** — NumPy arrays that can live on a GPU and remember their own history\n", "- Let **autograd** compute gradients for you (no more finite-difference nudging)\n", "- Train a real network on **MNIST** and read thousands of strangers' handwritten digits\n", "- Watch a **GPU** demolish a CPU at the one operation that matters: matrix multiply\n", "- Upgrade to a **convolutional** network, then draw your own digit for it to read\n", "\n", "**Today you unlock:** 🔓 **Digit Reader** — draw a digit on screen and the network *you trained* names it.\n", "\n", "
A precise reading

MNIST has 60,000 training and 10,000 test images; the test images do not train the model. Autograd applies the chain rule to recorded tensor operations, subject to floating-point precision. GPU speed depends on matrix size, hardware and transfer overhead; small workloads can be faster on the CPU.

\n" ] }, { "cell_type": "code", "execution_count": null, "id": "6baee145", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:54:59.354926Z", "iopub.status.busy": "2026-08-17T12:54:59.354796Z", "iopub.status.idle": "2026-08-17T12:54:59.463389Z", "shell.execute_reply": "2026-08-17T12:54:59.462312Z" } }, "outputs": [], "source": [ "# ╔═══════════════════════════════════════════════════════════════════╗\n", "# ║ SETUP — run me first! (identical in every Lab notebook) ║\n", "# ╚═══════════════════════════════════════════════════════════════════╝\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/day05 # ← 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\"✅ Setup done | Colab: {IN_COLAB} | Smoke test: {SMOKE}\")\n", "print(f\" data: {DATA_DIR}\")" ] }, { "cell_type": "code", "execution_count": null, "id": "5d0ff20b", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:54:59.465068Z", "iopub.status.busy": "2026-08-17T12:54:59.464878Z", "iopub.status.idle": "2026-08-17T12:55:03.374238Z", "shell.execute_reply": "2026-08-17T12:55:03.373170Z" } }, "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 — running on CPU. Everything still works, just slower.\")" ] }, { "cell_type": "code", "execution_count": null, "id": "05cd5cb3", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:55:03.376044Z", "iopub.status.busy": "2026-08-17T12:55:03.375807Z", "iopub.status.idle": "2026-08-17T12:55:03.379982Z", "shell.execute_reply": "2026-08-17T12:55:03.378884Z" } }, "outputs": [], "source": [ "# ── CONFIG — the Lab's control panel. Tweak me later! ──────────────\n", "EPOCHS = 1 if SMOKE else 3\n", "TRAIN_SUBSET = 2_000 if SMOKE else 60_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": "06cfe173", "metadata": {}, "source": [ "## 1. Tensors — NumPy arrays with two superpowers\n", "\n", "A **tensor** is PyTorch's version of a NumPy array: an n-dimensional grid of numbers. You already know how to work with these from Days 2–4. Tensors add two things a plain NumPy array can't do:\n", "\n", "1. **They can live on a GPU** — thousands of numbers multiplied in parallel.\n", "2. **They remember their own history** — so PyTorch can compute gradients automatically (that's the next section).\n", "\n", "The bridge between the two worlds is one function each way: `torch.from_numpy(array)` and `tensor.numpy()`." ] }, { "cell_type": "code", "execution_count": null, "id": "ca35e1ee", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:55:03.381543Z", "iopub.status.busy": "2026-08-17T12:55:03.381403Z", "iopub.status.idle": "2026-08-17T12:55:03.465985Z", "shell.execute_reply": "2026-08-17T12:55:03.464944Z" } }, "outputs": [], "source": [ "import numpy as np\n", "import torch\n", "\n", "a = np.array([[1., 2.], [3., 4.]])\n", "t = torch.from_numpy(a) # numpy -> torch\n", "back = t.numpy() # torch -> numpy\n", "\n", "print(\"numpy array:\\n\", a)\n", "print(\"torch tensor:\\n\", t)\n", "print(\"shape:\", t.shape, \"| dtype:\", t.dtype)" ] }, { "cell_type": "markdown", "id": "82dc7ccb", "metadata": {}, "source": [ "### 🧪 Exercise 1 — your first tensors\n", "\n", "- `A` is 3×4 and `B` is 4×2. Matrix-multiply them with the `@` operator into `C`.\n", "- Print `C`'s shape and dtype.\n", "- Expected: `C` is **3×2** — the shared inner dimension (4) cancels, exactly like the matmuls you traced by hand on Day 4." ] }, { "cell_type": "code", "execution_count": null, "id": "b254193f", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:55:03.467583Z", "iopub.status.busy": "2026-08-17T12:55:03.467439Z", "iopub.status.idle": "2026-08-17T12:55:03.533283Z", "shell.execute_reply": "2026-08-17T12:55:03.532276Z" } }, "outputs": [], "source": [ "A = torch.rand(3, 4)\n", "B = torch.rand(4, 2)\n", "\n", "# ==================== YOUR CODE HERE ====================\n", "### HINT: '@' is matrix multiply; the inner dims (4) must match and cancel\n", "...\n", "\n", "print(\"C shape:\", C.shape, \"| dtype:\", C.dtype)\n", "assert C.shape == (3, 2), \"C should be 3x2 — check which dimensions cancel\"\n", "print(\"✅ nice — that's a matrix multiply, the heartbeat of every network\")" ] }, { "cell_type": "markdown", "id": "50ec1055", "metadata": {}, "source": [ "## 2. Autograd — yesterday's nudge, automatic and exact\n", "\n", "On Day 4 you found gradients by **nudging**: bump a weight a tiny bit, re-run the network, see how the loss changed. It worked, but it was slow and only approximate.\n", "\n", "PyTorch does it exactly. Mark a tensor with `requires_grad=True` and it silently records every operation you do to it. Call `.backward()` and PyTorch replays those operations in reverse — the **chain rule**, done for you — leaving the gradient in `.grad`.\n", "\n", "
🔢 Math Corner — what backward() actually did (optional)\n", "\n", "`y = x**2` builds a tiny computation graph: `x → square → y`. `y.backward()` walks that graph in reverse, applying the chain rule at each step, and drops the result into `x.grad`. For `y = x²` the derivative is `2x`, so at `x = 2` you get `4`. The magic: the same reverse walk works for a graph with a *million* nodes — which is exactly a neural network.\n", "\n", "
" ] }, { "cell_type": "code", "execution_count": null, "id": "a5138cd9", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:55:03.534892Z", "iopub.status.busy": "2026-08-17T12:55:03.534752Z", "iopub.status.idle": "2026-08-17T12:55:03.539527Z", "shell.execute_reply": "2026-08-17T12:55:03.538569Z" } }, "outputs": [], "source": [ "x = torch.tensor(2.0, requires_grad=True)\n", "y = x ** 2\n", "y.backward() # fill in dy/dx\n", "\n", "print(\"y =\", y.item())\n", "print(\"dy/dx at x=2 =\", x.grad.item(), \" (calculus says 2x = 4 ✓)\")" ] }, { "cell_type": "markdown", "id": "446bd54b", "metadata": {}, "source": [ "### 🧪 Exercise 2 — differentiate by yourself (well, by PyTorch)\n", "\n", "- Build `y = x**3 + 2*x` at `x = 3.0`, then call `y.backward()`.\n", "- Expected: `x.grad` is **29**. (By hand: d/dx(x³ + 2x) = 3x² + 2 = 3·9 + 2 = 29.)" ] }, { "cell_type": "code", "execution_count": null, "id": "06d05bf8", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:55:03.541110Z", "iopub.status.busy": "2026-08-17T12:55:03.540952Z", "iopub.status.idle": "2026-08-17T12:55:03.554318Z", "shell.execute_reply": "2026-08-17T12:55:03.553298Z" } }, "outputs": [], "source": [ "x = torch.tensor(3.0, requires_grad=True)\n", "\n", "# ==================== YOUR CODE HERE ====================\n", "### HINT: write the formula for y, then call y.backward()\n", "...\n", "\n", "print(\"dy/dx at x=3:\", x.grad.item())\n", "assert abs(x.grad.item() - 29.0) < 1e-5, \"d/dx (x^3 + 2x) = 3x^2 + 2 = 29 at x=3\"\n", "print(\"✅ exact gradient, zero calculus homework\")" ] }, { "cell_type": "markdown", "id": "64ac4928", "metadata": {}, "source": [ "### 🎯 Two passes, not 130\n", "\n", "On **Day 4** you estimated each gradient by nudging one weight, running the whole network **forward**, and measuring the change — one forward pass **per weight**. With ~130 weights that was ~130 passes for a *single* training step.\n", "\n", "`loss.backward()` just did that same job for **all** the weights at once, with **one** forward pass and **one** backward pass. That is the entire reason modern AI is possible: autograd records every operation on the way *in*, then replays the chain rule on the way *out*.\n", "\n", "> Under the hood it's all matrix multiplication — the same `@` you just used. Making those multiplications scream on real hardware is a whole field of its own — high-performance computing." ] }, { "cell_type": "markdown", "id": "b4d0b464", "metadata": {}, "source": [ "## 3. The mission: read handwriting (MNIST)\n", "\n", "**MNIST** is the \"hello world\" of computer vision: 60,000 training and 10,000 test handwritten digits (0–9), each a 28×28 grayscale image. 60,000 to train on, 10,000 strangers' digits to test on.\n", "\n", "One rule matters for later: we apply **only** `ToTensor()`, which scales pixels to the range 0–1 and gives us **white digits on a black background**. We do **not** normalize — your Digit Reader Studio module expects exactly this format, so keep it in mind for the unlock." ] }, { "cell_type": "code", "execution_count": null, "id": "24393b73", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:55:03.555777Z", "iopub.status.busy": "2026-08-17T12:55:03.555628Z", "iopub.status.idle": "2026-08-17T12:55:05.878788Z", "shell.execute_reply": "2026-08-17T12:55:05.877756Z" } }, "outputs": [], "source": [ "from torchvision import datasets, transforms\n", "from torch.utils.data import DataLoader, Subset\n", "\n", "tfm = transforms.ToTensor() # pixels -> [0, 1]; no normalization (module contract!)\n", "train_full = datasets.MNIST(DATA_DIR, train=True, download=True, transform=tfm)\n", "test_set = datasets.MNIST(DATA_DIR, train=False, download=True, transform=tfm)\n", "train_set = Subset(train_full, range(TRAIN_SUBSET))\n", "\n", "# num_workers=0: MNIST is tiny, so one process is plenty, and it avoids the\n", "# harmless-but-noisy DataLoader worker-shutdown warnings you can hit 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(f\"train images: {len(train_set):,} test images: {len(test_set):,}\")\n", "\n", "img0, label0 = train_full[0]\n", "print(\"one image:\", tuple(img0.shape), \"| pixel range:\", float(img0.min()), \"to\", float(img0.max()))" ] }, { "cell_type": "code", "execution_count": null, "id": "1a0c2f3b", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:55:05.880774Z", "iopub.status.busy": "2026-08-17T12:55:05.880560Z", "iopub.status.idle": "2026-08-17T12:55:06.538146Z", "shell.execute_reply": "2026-08-17T12:55:06.537064Z" } }, "outputs": [], "source": [ "import matplotlib.pyplot as plt\n", "\n", "fig, axes = plt.subplots(4, 8, figsize=(10, 5))\n", "for ax, idx in zip(axes.ravel(), range(32)):\n", " img, label = train_full[idx]\n", " ax.imshow(img.squeeze(), cmap=\"gray\")\n", " ax.set_title(str(label), fontsize=9)\n", " ax.axis(\"off\")\n", "fig.suptitle(\"MNIST — handwritten digits (white ink on black, values 0–1)\")\n", "plt.tight_layout(); plt.show()" ] }, { "cell_type": "markdown", "id": "0a6643bd", "metadata": {}, "source": [ "## 4. Build the network (a multi-layer perceptron)\n", "\n", "Time to assemble the same kind of network you hand-wired on Day 4 — but in three lines. `nn.Sequential` just stacks layers front to back:\n", "\n", "- `nn.Flatten()` — unroll each 28×28 image into a flat vector of 784 numbers\n", "- `nn.Linear(784, 128)` — the big matmul: `(batch, 784) @ (784, 128)`\n", "- `nn.ReLU()` — the non-linearity that lets it learn curves, not just lines\n", "- `nn.Linear(128, 10)` — ten output scores, one per digit\n", "\n", "### 🧪 Exercise 3 — assemble the MLP\n", "\n", "Build the four-layer `nn.Sequential` above and move it onto `DEVICE`." ] }, { "cell_type": "code", "execution_count": null, "id": "01dfd2a6", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:55:06.539927Z", "iopub.status.busy": "2026-08-17T12:55:06.539695Z", "iopub.status.idle": "2026-08-17T12:55:06.711114Z", "shell.execute_reply": "2026-08-17T12:55:06.709991Z" } }, "outputs": [], "source": [ "import torch.nn as nn\n", "\n", "# ==================== YOUR CODE HERE ====================\n", "...\n", "\n", "print(mlp)" ] }, { "cell_type": "markdown", "id": "b29076b3", "metadata": {}, "source": [ "That `nn.Linear(784, 128)` is exactly the `(batch, 784) @ (784, 128)` matrix multiply you discovered on Day 4 — the network is *made* of matmuls. Let's count how many numbers it's juggling.\n", "\n", "### 🧪 Exercise 4 — count the parameters\n", "\n", "Sum `p.numel()` over `mlp.parameters()`. Expected: **101,770** (that's 784·128 + 128 weights and biases in the first layer, plus 128·10 + 10 in the second)." ] }, { "cell_type": "code", "execution_count": null, "id": "254698de", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:55:06.712936Z", "iopub.status.busy": "2026-08-17T12:55:06.712787Z", "iopub.status.idle": "2026-08-17T12:55:06.716953Z", "shell.execute_reply": "2026-08-17T12:55:06.715950Z" } }, "outputs": [], "source": [ "# ==================== YOUR CODE HERE ====================\n", "### HINT: p.numel() counts the entries in one weight tensor; sum over all params\n", "...\n", "\n", "print(f\"The MLP has {n_params:,} parameters.\")\n", "assert n_params == 101_770, \"Expected 100,480 + 1,290 = 101,770 — check your layer sizes\"\n", "print(\"✅ 101,770 knobs, all tuned by autograd\")" ] }, { "cell_type": "markdown", "id": "f4148dab", "metadata": {}, "source": [ "## 5. The training loop — the pattern that runs all of AI\n", "\n", "Almost every neural network in the world learns with the **same five-step loop**. Burn it into memory:\n", "\n", "1. **`optimizer.zero_grad()`** — forget the last step's gradients\n", "2. **`logits = model(x)`** — forward pass (a stack of matrix multiplies)\n", "3. **`loss = loss_fn(logits, y)`** — how wrong were we?\n", "4. **`loss.backward()`** — autograd fills in every gradient\n", "5. **`optimizer.step()`** — nudge all the weights a little downhill\n", "\n", "That's it. Even GPT-scale models train with this exact skeleton — just bigger.\n", "\n", "### 🧪 Exercise 5 — complete the training loop\n", "\n", "Fill the **five ★ gaps** in `train_model` below — one line each, in order. This is the single most important code you'll write all course.\n", "\n", "- Loss function: `nn.CrossEntropyLoss()` (already wired up).\n", "- Optimizer: `Adam` at `LEARNING_RATE` (already wired up).\n", "- Expected: the printed **loss goes down** each epoch. If it stays flat or explodes, re-check the order of the five steps." ] }, { "cell_type": "code", "execution_count": null, "id": "19f29641", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:55:06.718720Z", "iopub.status.busy": "2026-08-17T12:55:06.718573Z", "iopub.status.idle": "2026-08-17T12:55:06.767043Z", "shell.execute_reply": "2026-08-17T12:55:06.766054Z" } }, "outputs": [], "source": [ "import torch.nn as nn\n", "from tqdm.auto import tqdm\n", "\n", "def train_model(model, epochs):\n", " 'Run the canonical training loop; reused for every model today.'\n", " loss_fn = nn.CrossEntropyLoss()\n", " optimizer = torch.optim.Adam(model.parameters(), lr=LEARNING_RATE)\n", "\n", " for epoch in range(1, epochs + 1):\n", " model.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", "\n", " # ==================== YOUR CODE HERE ====================\n", " ### HINT: ★1 — clear the gradients left over from the previous step\n", " ...\n", "\n", " # ==================== YOUR CODE HERE ====================\n", " ### HINT: ★2 — forward pass: feed the images through the model to get logits\n", " ...\n", "\n", " # ==================== YOUR CODE HERE ====================\n", " ### HINT: ★3 — compare logits to the true labels to get the loss\n", " ...\n", "\n", " # ==================== YOUR CODE HERE ====================\n", " ### HINT: ★4 — backpropagate: fill in a gradient for every weight\n", " ...\n", "\n", " # ==================== YOUR CODE HERE ====================\n", " ### HINT: ★5 — take one step downhill with the optimizer\n", " ...\n", "\n", " running += loss.item() * images.size(0)\n", " print(f\"epoch {epoch}: train loss {running / len(train_loader.dataset):.3f}\")\n", " return model" ] }, { "cell_type": "code", "execution_count": null, "id": "434984ca", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:55:06.769076Z", "iopub.status.busy": "2026-08-17T12:55:06.768931Z", "iopub.status.idle": "2026-08-17T12:55:22.301301Z", "shell.execute_reply": "2026-08-17T12:55:22.300231Z" } }, "outputs": [], "source": [ "train_model(mlp, EPOCHS)\n", "print(\"✅ MLP trained.\")" ] }, { "cell_type": "markdown", "id": "60ca5e9a", "metadata": {}, "source": [ "## 6. Grade it on strangers' handwriting\n", "\n", "Training loss is nice, but the real question is: how well does it read digits it has **never seen**? We loop over the 10,000-image test set and count how many it gets right — all inside `torch.no_grad()`, because we're only *reading* the network now, not training it (no gradients needed, so it runs faster and uses less memory).\n", "\n", "### 🧪 Exercise 6 — write `evaluate`\n", "\n", "Fill in the no-grad loop that counts correct predictions. The class the network picks is the index of the largest logit: `logits.argmax(dim=1)`." ] }, { "cell_type": "code", "execution_count": null, "id": "c32e4d76", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:55:22.303014Z", "iopub.status.busy": "2026-08-17T12:55:22.302869Z", "iopub.status.idle": "2026-08-17T12:55:23.043508Z", "shell.execute_reply": "2026-08-17T12:55:23.042311Z" } }, "outputs": [], "source": [ "def evaluate(model, loader):\n", " 'Return accuracy (fraction correct) over a data loader.'\n", " model.eval()\n", " correct = total = 0\n", " # ==================== YOUR CODE HERE ====================\n", " ### HINT: wrap the loop in `with torch.no_grad():` and compare argmax to labels\n", " ...\n", " return correct / total\n", "\n", "mlp_acc = evaluate(mlp, test_loader)\n", "print(f\"MLP test accuracy: {mlp_acc:.4f}\")\n", "if not SMOKE:\n", " assert mlp_acc >= 0.95, \"Expected >= 0.95 on the full run — check your training loop\"\n", " print(f\"🎉 Your network just read {round(mlp_acc * 10000):,} of 10,000 strangers' digits!\")" ] }, { "cell_type": "markdown", "id": "b2ffc7c1", "metadata": {}, "source": [ "## 7. Why a GPU? Let's measure it ⚡\n", "\n", "Everything above is matrix multiplication. A **GPU** does thousands of multiplies at once, which is why it obliterates a CPU on big matrices. Let's prove it: time `A @ B` for growing matrix sizes on the CPU, and (if you have one) on the GPU.\n", "\n", "One catch: a GPU runs **asynchronously**. When you write `A @ B`, the CPU fires off the work and moves on *before* the GPU is done. So to time it honestly you must call `torch.cuda.synchronize()` — \"wait until the GPU actually finishes\" — before stopping the clock.\n", "\n", "### 🧪 Exercise 7 — time the matmul\n", "\n", "Fill in the two timed blocks (CPU and GPU). The warm-up call and the `synchronize()` calls are given — you write the timing with `time.perf_counter()`." ] }, { "cell_type": "code", "execution_count": null, "id": "c0cfdc65", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:55:23.045204Z", "iopub.status.busy": "2026-08-17T12:55:23.045058Z", "iopub.status.idle": "2026-08-17T12:55:23.545159Z", "shell.execute_reply": "2026-08-17T12:55:23.544036Z" } }, "outputs": [], "source": [ "import time\n", "\n", "sizes = [256, 512, 1024] if SMOKE else [512, 1024, 2048, 4096]\n", "cpu_times, gpu_times = [], []\n", "\n", "for n in sizes:\n", " A = torch.randn(n, n)\n", " B = torch.randn(n, n)\n", "\n", " # --- CPU timing ---\n", " # ==================== YOUR CODE HERE ====================\n", " ### HINT: read time.perf_counter() before and after C = A @ B, store the difference\n", " ...\n", "\n", " # --- GPU timing (only if we actually have a CUDA device) ---\n", " if DEVICE.type == \"cuda\":\n", " Ag, Bg = A.to(DEVICE), B.to(DEVICE)\n", " _ = Ag @ Bg # warm-up: the very first CUDA call is slow\n", " torch.cuda.synchronize() # wait for the warm-up to finish\n", " # ==================== YOUR CODE HERE ====================\n", " ### HINT: same idea, but call torch.cuda.synchronize() before stopping the clock\n", " ...\n", "\n", " line = f\"n={n:5d} CPU {cpu_times[-1] * 1e3:8.1f} ms\"\n", " if DEVICE.type == \"cuda\":\n", " line += f\" GPU {gpu_times[-1] * 1e3:8.3f} ms\"\n", " print(line)" ] }, { "cell_type": "code", "execution_count": null, "id": "babe0f49", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:55:23.546710Z", "iopub.status.busy": "2026-08-17T12:55:23.546553Z", "iopub.status.idle": "2026-08-17T12:55:23.644933Z", "shell.execute_reply": "2026-08-17T12:55:23.643692Z" } }, "outputs": [], "source": [ "import matplotlib.pyplot as plt\n", "import numpy as np\n", "\n", "x = np.arange(len(sizes))\n", "plt.figure(figsize=(8, 5))\n", "plt.bar(x - 0.2, np.array(cpu_times) * 1e3, width=0.4, label=\"CPU\")\n", "if DEVICE.type == \"cuda\":\n", " plt.bar(x + 0.2, np.array(gpu_times) * 1e3, width=0.4, label=\"GPU\")\n", "plt.yscale(\"log\")\n", "plt.xticks(x, [str(n) for n in sizes])\n", "plt.xlabel(\"matrix size n (an n × n matrix)\")\n", "plt.ylabel(\"time per matmul (ms, log scale)\")\n", "plt.title(\"Matrix multiply: CPU vs GPU\")\n", "plt.legend(); plt.tight_layout(); plt.show()\n", "\n", "if DEVICE.type == \"cuda\":\n", " for n, ct, gt in zip(sizes, cpu_times, gpu_times):\n", " print(f\"n={n:5d}: GPU is {ct / gt:6.1f}× faster\")\n", "else:\n", " print(\"🐢 CPU only — no GPU to compare against right now.\")\n", " print(\" On the Lab's GPU, the GPU bars would sit far below the CPU bars.\")" ] }, { "cell_type": "markdown", "id": "67d974b3", "metadata": {}, "source": [ "### The numbers behind the numbers\n", "\n", "Multiplying two n×n matrices costs about **2·n³** floating-point operations. Divide that by the time you measured and you get **FLOP/s** — operations per second. A workstation CPU manages a few billion (**GFLOP/s**); a modern GPU does **tens of trillions** (**TFLOP/s**). Same math, wildly different speed — because the GPU does thousands of multiplies in parallel.\n", "\n", "> Squeezing these numbers out of the hardware is a profession of its own — high-performance computing. Today you *use* the speed; one day you could *build* it." ] }, { "cell_type": "markdown", "id": "cc0ea026", "metadata": {}, "source": [ "## 8. A sharper tool: the convolutional network 🔬\n", "\n", "The MLP flattens each image into 784 numbers on the very first line — throwing away the fact that nearby pixels belong together. A **convolutional** network keeps the 2-D shape and slides small pattern-detectors across it. (Day 6 goes deep on *why* this works — today, just feel the accuracy jump.)\n", "\n", "Here's a small CNN. Don't worry about every line yet; notice it ends in the same two `Linear` layers, just fed by smarter features." ] }, { "cell_type": "code", "execution_count": null, "id": "b51b3506", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:55:23.646618Z", "iopub.status.busy": "2026-08-17T12:55:23.646469Z", "iopub.status.idle": "2026-08-17T12:55:23.653404Z", "shell.execute_reply": "2026-08-17T12:55:23.652466Z" } }, "outputs": [], "source": [ "import torch.nn as nn\n", "\n", "class SmallCNN(nn.Module):\n", " def __init__(self):\n", " super().__init__()\n", " self.features = nn.Sequential(\n", " nn.Conv2d(1, 16, 3, padding=1), nn.ReLU(), nn.MaxPool2d(2), # 28 -> 14\n", " nn.Conv2d(16, 32, 3, padding=1), nn.ReLU(), nn.MaxPool2d(2), # 14 -> 7\n", " )\n", " self.classifier = nn.Sequential(\n", " nn.Flatten(),\n", " nn.Linear(32 * 7 * 7, 128), nn.ReLU(),\n", " nn.Linear(128, 10),\n", " )\n", "\n", " def forward(self, x):\n", " return self.classifier(self.features(x))\n", "\n", "print(SmallCNN())" ] }, { "cell_type": "markdown", "id": "7bfe1325", "metadata": {}, "source": [ "### 🧪 Exercise 8 — train the CNN by reusing your loop\n", "\n", "You already wrote `train_model`. That's the point of a reusable function: the CNN trains with the **exact same call**. Instantiate `SmallCNN`, move it to `DEVICE`, and train it." ] }, { "cell_type": "code", "execution_count": null, "id": "708515f7", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:55:23.654970Z", "iopub.status.busy": "2026-08-17T12:55:23.654839Z", "iopub.status.idle": "2026-08-17T12:55:45.090046Z", "shell.execute_reply": "2026-08-17T12:55:45.088860Z" } }, "outputs": [], "source": [ "cnn = SmallCNN().to(DEVICE)\n", "\n", "# ==================== YOUR CODE HERE ====================\n", "### HINT: no new loop needed — call the train_model you already wrote\n", "...\n", "\n", "cnn_acc = evaluate(cnn, test_loader)\n", "print(f\"CNN test accuracy: {cnn_acc:.4f}\")" ] }, { "cell_type": "code", "execution_count": null, "id": "7debe7e4", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:55:45.091719Z", "iopub.status.busy": "2026-08-17T12:55:45.091566Z", "iopub.status.idle": "2026-08-17T12:55:45.095682Z", "shell.execute_reply": "2026-08-17T12:55:45.094435Z" } }, "outputs": [], "source": [ "print(f\"MLP accuracy: {mlp_acc:.4f}\")\n", "print(f\"CNN accuracy: {cnn_acc:.4f}\")\n", "print(f\"The CNN got {(cnn_acc - mlp_acc) * 100:+.2f} percentage points by respecting the image's shape.\")" ] }, { "cell_type": "markdown", "id": "4e3d0623", "metadata": {}, "source": [ "## 9. Autopsy: where does it slip?\n", "\n", "No network is perfect. Let's look at the digits the CNN got **wrong** — true label on the left of the arrow, its guess on the right." ] }, { "cell_type": "code", "execution_count": null, "id": "ee423a4d", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:55:45.097229Z", "iopub.status.busy": "2026-08-17T12:55:45.097083Z", "iopub.status.idle": "2026-08-17T12:55:45.466651Z", "shell.execute_reply": "2026-08-17T12:55:45.465503Z" } }, "outputs": [], "source": [ "import matplotlib.pyplot as plt\n", "\n", "cnn.eval()\n", "wrong = []\n", "with torch.no_grad():\n", " for images, labels in test_loader:\n", " preds = cnn(images.to(DEVICE)).argmax(1).cpu()\n", " for img, t_, p_ in zip(images, labels, preds):\n", " if int(t_) != int(p_):\n", " wrong.append((img, int(t_), int(p_)))\n", " if len(wrong) >= 16:\n", " break\n", "\n", "fig, axes = plt.subplots(2, 8, figsize=(10, 3))\n", "for ax, (img, t_, p_) in zip(axes.ravel(), wrong[:16]):\n", " ax.imshow(img.squeeze(), cmap=\"gray\")\n", " ax.set_title(f\"{t_} → {p_}\", fontsize=9, color=\"crimson\")\n", " ax.axis(\"off\")\n", "fig.suptitle(\"Where the network slips: true → predicted\")\n", "plt.tight_layout(); plt.show()" ] }, { "cell_type": "markdown", "id": "16e58050", "metadata": {}, "source": [ "Be honest with yourself as you look: how many of those would *you* get right, out of context? A lot of them are genuinely mangled — a 4 that's really a 9, a 7 with a slash that looks like a 1. The network isn't dumb; the handwriting is hard." ] }, { "cell_type": "markdown", "id": "9500a891", "metadata": {}, "source": [ "## 10. Read *your* handwriting ✍️\n", "\n", "Now the fun part. The helper below turns whatever you scribble on the pad into the exact format your network trained on — a 28×28 white-on-black image, centered — then asks the CNN what it sees.\n", "\n", "**Tip:** draw **big and centered**, filling most of the box. The network learned from centered digits, so a tiny scribble in the corner confuses it." ] }, { "cell_type": "code", "execution_count": null, "id": "f1a1ffc7", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:55:45.468520Z", "iopub.status.busy": "2026-08-17T12:55:45.468380Z", "iopub.status.idle": "2026-08-17T12:55:45.475595Z", "shell.execute_reply": "2026-08-17T12:55:45.474566Z" } }, "outputs": [], "source": [ "import numpy as np\n", "from PIL import Image\n", "\n", "def sketch_to_tensor(sketch):\n", " 'Sketchpad value -> MNIST-style (1,1,28,28) tensor + a preview, or (None, None).'\n", " img = sketch.get(\"composite\") if isinstance(sketch, dict) else sketch\n", " if img is None:\n", " return None, None\n", " arr = np.asarray(img).astype(np.float32)\n", "\n", " if arr.ndim == 3 and arr.shape[2] == 4: # RGBA -> flatten onto white\n", " rgb, alpha = arr[..., :3], arr[..., 3:4] / 255.0\n", " arr = rgb * alpha + 255.0 * (1.0 - alpha)\n", " if arr.ndim == 3:\n", " arr = arr.mean(axis=2) # to grayscale\n", "\n", " ink = 255.0 - arr if np.median(arr) > 127 else arr # want white ink on black\n", " if ink.max() < 10: # empty canvas\n", " return None, None\n", " ink = ink / ink.max() * 255.0\n", "\n", " ys, xs = np.where(ink > 30) # crop tight to the strokes\n", " crop = ink[ys.min():ys.max() + 1, xs.min():xs.max() + 1]\n", " side = max(crop.shape)\n", " sq = np.zeros((side, side), np.float32) # pad to a square\n", " oy, ox = (side - crop.shape[0]) // 2, (side - crop.shape[1]) // 2\n", " sq[oy:oy + crop.shape[0], ox:ox + crop.shape[1]] = crop\n", "\n", " small = Image.fromarray(sq.astype(np.uint8)).resize((20, 20), Image.LANCZOS)\n", " canvas = np.zeros((28, 28), np.float32)\n", " canvas[4:24, 4:24] = np.asarray(small, dtype=np.float32) # center in 28x28\n", "\n", " x = torch.from_numpy(canvas / 255.0).reshape(1, 1, 28, 28)\n", " preview = np.kron(canvas.astype(np.uint8), np.ones((6, 6), np.uint8)) # zoom for display\n", " return x, preview" ] }, { "cell_type": "code", "execution_count": null, "id": "16dbd62a", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:55:45.477111Z", "iopub.status.busy": "2026-08-17T12:55:45.476977Z", "iopub.status.idle": "2026-08-17T12:55:48.032939Z", "shell.execute_reply": "2026-08-17T12:55:48.031500Z" } }, "outputs": [], "source": [ "import gradio as gr\n", "\n", "cnn.eval()\n", "\n", "def read_digit(sketch):\n", " x, preview = sketch_to_tensor(sketch)\n", " if x is None:\n", " return {}, None\n", " dev = next(cnn.parameters()).device # follow the model onto whatever device it is on\n", " with torch.no_grad():\n", " probs = torch.softmax(cnn(x.to(dev))[0], dim=0)\n", " return {str(i): float(p) for i, p in enumerate(probs)}, preview\n", "\n", "with gr.Blocks() as demo:\n", " gr.Markdown(\"## ✍️ Draw a digit (0–9) — big and centered!\")\n", " with gr.Row():\n", " pad = gr.Sketchpad(label=\"Draw here\", canvas_size=(280, 280))\n", " with gr.Column():\n", " out = gr.Label(num_top_classes=3, label=\"I think it's a ...\")\n", " seen = gr.Image(label=\"What the network sees (28×28)\", height=180)\n", " pad.change(read_digit, pad, [out, seen])\n", "\n", "if not SMOKE:\n", " demo.launch(share=IN_COLAB)" ] }, { "cell_type": "markdown", "id": "d4feff02", "metadata": {}, "source": [ "## 🔓 Unlock your Studio module\n", "\n", "Time to ship. We export the trained CNN as a **TorchScript** file — a self-contained, frozen copy the AI Studio can load without your training code. The input contract must match exactly what your Studio module expects: a `(1, 1, 28, 28)` tensor with values 0–1, white-on-black." ] }, { "cell_type": "code", "execution_count": null, "id": "f0631c43", "metadata": { "execution": { "iopub.execute_input": "2026-08-17T12:55:48.036041Z", "iopub.status.busy": "2026-08-17T12:55:48.035808Z", "iopub.status.idle": "2026-08-17T12:55:48.345847Z", "shell.execute_reply": "2026-08-17T12:55:48.344586Z" } }, "outputs": [], "source": [ "# Export the trained CNN so the Studio's Digit Reader tab can load it.\n", "REQUIRED_FILES = [\"digit_reader.pt\"]\n", "\n", "cnn.eval()\n", "example = torch.zeros(1, 1, 28, 28) # input contract: (1,1,28,28), values 0–1\n", "scripted = torch.jit.trace(cnn.cpu(), example) # trace on CPU; the Studio runs on CPU\n", "scripted.save(str(MODELS_DIR / \"digit_reader.pt\"))\n", "cnn.to(DEVICE) # put the live model back on its device\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(\"🔓 UNLOCKED: Digit Reader! Run the Studio to see it live:\")\n", "print(\" python ai_studio/app.py (from the repo root)\")" ] }, { "cell_type": "markdown", "id": "95d20a82", "metadata": {}, "source": [ "## 🏁 Checkpoint\n", "\n", "Look what you built today:\n", "\n", "- ✅ Traded hand-rolled gradients for **autograd** — two passes instead of 130\n", "- ✅ Trained an **MLP** to ~97% on MNIST, then a **CNN** to even higher\n", "- ✅ Measured a **GPU** demolishing a CPU at matrix multiply\n", "- ✅ Drew your own digit and watched *your* network read it\n", "- 🔓 Unlocked **Digit Reader** in your AI Studio\n", "\n", "You fed this network tiny 28×28 gray digits and it learned to read. But the world isn't gray, and it isn't 28×28.\n", "\n", "**Tomorrow — Day 6, \"Machines That See\":** real color photos, ten kinds of objects, and convolutions used in earnest. Your network is about to grow eyes. 👁️" ] }, { "cell_type": "markdown", "id": "19ea38b9", "metadata": {}, "source": [ "---\n", "\n", "
\n", " \n", " \"Dr.\n", " \n", "
\n", "\n", "
The Lab · AI Studio — Intro to AI · © 2026 Dr. Abdelghafour HALIMI · ahalimi.com · All rights reserved.
" ] } ], "metadata": { "authors": [ { "name": "Dr. Abdelghafour HALIMI" } ], "copyright": "© 2026 Dr. Abdelghafour HALIMI · ahalimi.com · 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": { "001d0581b87346788b82597bb1e6c2e2": { "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 } }, "017ad9fc538a40cdb09f5f1b92892f2d": { "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_b2f7deec288b410b8206862d44d93800", "IPY_MODEL_61990dc58c3849fe9e8ec3ab5f7b1fbf", "IPY_MODEL_8c445f848db64da797e340039a06f131" ], "layout": "IPY_MODEL_994ba061a9f04b2cb4a5affe86127bd7", "tabbable": null, "tooltip": null } }, "098fc4a610014204b7df79e4eca25208": { "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 } }, "0beb75d922304e01b215485807d1edc8": { "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_5f8c7e7b864e4e199d4e1d95a0243d5c", "max": 469, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_93c6b44faf3a47d2af9518c5585abfa1", "tabbable": null, "tooltip": null, "value": 469 } }, "0e8c56edeed045b081813f87326ee229": { "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 } }, "13dce749aa89400385a9a9a5c5c7cce5": { "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 } }, "1556dc47a86e412ca91eb59fc8046aaa": { "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_894c3d0dd19d412ba38db287f98aaebe", "placeholder": "​", "style": "IPY_MODEL_8755b25e813e48fe9f32718e01937e12", "tabbable": null, "tooltip": null, "value": " 469/469 [00:05<00:00, 88.95it/s]" } }, "17c4fde2d79b4705b19ddb765b3edba0": { "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 } }, "1af5f92c9fe044358944cf9896cb1ea3": { "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 } }, "1bcf9f159acd4ca58d96f7cd865b8b0b": { "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_cafc079581c043f0bf63b281a60aeb28", "IPY_MODEL_40feaa95d40740e2863b9651603bd3bc", "IPY_MODEL_ddf04f419ceb4466b5f71da5715827f3" ], "layout": "IPY_MODEL_8b0f2240008544bf9df75a3c701dbf01", "tabbable": null, "tooltip": null } }, "1c5c834b6c4e4e0f9188fae3814f7b2f": { "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 } }, "296b795a77c9484d96242b16b75ce5fe": { "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 } }, "32c88b55137144178cdc9d8faf4d7cee": { "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_c0f07becfefb47739853b34a87f0f17c", "placeholder": "​", "style": "IPY_MODEL_fc6f0367973e42bfb75f43519d749f56", "tabbable": null, "tooltip": null, "value": "epoch 1/3: 100%" } }, "34d9f3afdd96400393bbd6e284707173": { "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 } }, "3fab8a150b3f40c0967a6854f886ae78": { "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_dbc7aa5b74094b1a958d8a5114e28624", "IPY_MODEL_b9aa13ce67de4bdcb776fe0381408b4b", "IPY_MODEL_1556dc47a86e412ca91eb59fc8046aaa" ], "layout": "IPY_MODEL_0e8c56edeed045b081813f87326ee229", "tabbable": null, "tooltip": null } }, "3fdd18f71b2d4bc89be7e3997c8f4783": { "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 } }, "40feaa95d40740e2863b9651603bd3bc": { "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_13dce749aa89400385a9a9a5c5c7cce5", "max": 469, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_9b882a71b7c041c08811d02ac38c980b", "tabbable": null, "tooltip": null, "value": 469 } }, "426831d80cdb4527965670a63f9ec052": { "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 } }, "45e45b8080e44f4388259032ede68c3a": { "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": "" } }, "49245545961a42c281de03636182bcf7": { "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_1c5c834b6c4e4e0f9188fae3814f7b2f", "max": 469, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_d721b4a23c8e4b9eb6ad793ac92c90ea", "tabbable": null, "tooltip": null, "value": 469 } }, "531c0aa72bd046f0818f7be118b51a84": { "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": "" } }, "5603a9e164cd4466baa0a2d0deca2780": { "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 } }, "5f8c7e7b864e4e199d4e1d95a0243d5c": { "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 } }, "618521eb655a4e6ba114b695f3eb9fe0": { "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_e59d644a6fc34c3db40c296c1ad76066", "placeholder": "​", "style": "IPY_MODEL_426831d80cdb4527965670a63f9ec052", "tabbable": null, "tooltip": null, "value": " 469/469 [00:05<00:00, 92.43it/s]" } }, "61990dc58c3849fe9e8ec3ab5f7b1fbf": { "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_d3dee055362641328229178aa20fa9c6", "max": 469, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_bf54b39ae7214faea9e7b447687150ab", "tabbable": null, "tooltip": null, "value": 469 } }, "63642ef08a1b4fe9ba14b8f040ee16f4": { "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_32c88b55137144178cdc9d8faf4d7cee", "IPY_MODEL_0beb75d922304e01b215485807d1edc8", "IPY_MODEL_b7407b797cc94544991ea2ffd2892aa0" ], "layout": "IPY_MODEL_1af5f92c9fe044358944cf9896cb1ea3", "tabbable": null, "tooltip": null } }, "666c4d3c585442038fe9f7f58fe7a139": { "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 } }, "748b4f229f3347e0bbf33998d7b54021": { "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_296b795a77c9484d96242b16b75ce5fe", "max": 469, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_45e45b8080e44f4388259032ede68c3a", "tabbable": null, "tooltip": null, "value": 469 } }, "8039ae418cb342a08d9bd4f859501d51": { "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 } }, "84bbd8e125ab438a852130e56efd6359": { "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 } }, "85ca5fb4b75f42a48c16f8486b9da78f": { "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_d9363ee23afb41fe815e655dc4aacc54", "IPY_MODEL_49245545961a42c281de03636182bcf7", "IPY_MODEL_ea7a02563a464e42b87caf2fc708bf84" ], "layout": "IPY_MODEL_a7059528ec034e0ba0aa4c2f27e99226", "tabbable": null, "tooltip": null } }, "8755b25e813e48fe9f32718e01937e12": { "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 } }, "894c3d0dd19d412ba38db287f98aaebe": { "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 } }, "8a5639aaa8304a7fbff3f9da4c110293": { "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 } }, "8b0f2240008544bf9df75a3c701dbf01": { "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 } }, "8c445f848db64da797e340039a06f131": { "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_098fc4a610014204b7df79e4eca25208", "placeholder": "​", "style": "IPY_MODEL_91a2bf75b43945898cb7b4cc70d34c1e", "tabbable": null, "tooltip": null, "value": " 469/469 [00:08<00:00, 75.95it/s]" } }, "91a2bf75b43945898cb7b4cc70d34c1e": { "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 } }, "93c6b44faf3a47d2af9518c5585abfa1": { "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": "" } }, "989cdf29f1224f5396b13f7daeab6ead": { "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 } }, "994ba061a9f04b2cb4a5affe86127bd7": { "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 } }, "9a22e76d395b4e7ebb17e5128383a5a6": { "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 } }, "9b882a71b7c041c08811d02ac38c980b": { "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": "" } }, "a563f37016d94905b15650866504fa04": { "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 } }, "a7059528ec034e0ba0aa4c2f27e99226": { "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 } }, "a9b1e4ba7b164fad87bb86d22a744db5": { "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_ea26c4f1f4734a929f992318210bb977", "IPY_MODEL_748b4f229f3347e0bbf33998d7b54021", "IPY_MODEL_618521eb655a4e6ba114b695f3eb9fe0" ], "layout": "IPY_MODEL_a563f37016d94905b15650866504fa04", "tabbable": null, "tooltip": null } }, "b2f7deec288b410b8206862d44d93800": { "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_9a22e76d395b4e7ebb17e5128383a5a6", "placeholder": "​", "style": "IPY_MODEL_5603a9e164cd4466baa0a2d0deca2780", "tabbable": null, "tooltip": null, "value": "epoch 1/3: 100%" } }, "b7407b797cc94544991ea2ffd2892aa0": { "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_fe051d91f72f425989e1a00bee0198b3", "placeholder": "​", "style": "IPY_MODEL_8a5639aaa8304a7fbff3f9da4c110293", "tabbable": null, "tooltip": null, "value": " 469/469 [00:05<00:00, 102.15it/s]" } }, "b9aa13ce67de4bdcb776fe0381408b4b": { "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_84bbd8e125ab438a852130e56efd6359", "max": 469, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_531c0aa72bd046f0818f7be118b51a84", "tabbable": null, "tooltip": null, "value": 469 } }, "be0492ad8c1047d9ac171f7dfb1a6e66": { "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 } }, "be535684745e42979fdc662c10f7c841": { "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 } }, "bf54b39ae7214faea9e7b447687150ab": { "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": "" } }, "c0f07becfefb47739853b34a87f0f17c": { "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 } }, "cafc079581c043f0bf63b281a60aeb28": { "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_be535684745e42979fdc662c10f7c841", "placeholder": "​", "style": "IPY_MODEL_dd187a0c13ec40b9b07af0ecea6f7c9d", "tabbable": null, "tooltip": null, "value": "epoch 3/3: 100%" } }, "d3dee055362641328229178aa20fa9c6": { "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 } }, "d721b4a23c8e4b9eb6ad793ac92c90ea": { "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": "" } }, "d9363ee23afb41fe815e655dc4aacc54": { "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_8039ae418cb342a08d9bd4f859501d51", "placeholder": "​", "style": "IPY_MODEL_3fdd18f71b2d4bc89be7e3997c8f4783", "tabbable": null, "tooltip": null, "value": "epoch 2/3: 100%" } }, "dbc7aa5b74094b1a958d8a5114e28624": { "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_17c4fde2d79b4705b19ddb765b3edba0", "placeholder": "​", "style": "IPY_MODEL_be0492ad8c1047d9ac171f7dfb1a6e66", "tabbable": null, "tooltip": null, "value": "epoch 3/3: 100%" } }, "dd187a0c13ec40b9b07af0ecea6f7c9d": { "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 } }, "ddf04f419ceb4466b5f71da5715827f3": { "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_001d0581b87346788b82597bb1e6c2e2", "placeholder": "​", "style": "IPY_MODEL_eaed33e06a004d79942fbb671350c174", "tabbable": null, "tooltip": null, "value": " 469/469 [00:05<00:00, 91.40it/s]" } }, "e279207276a64e3fa64db22a9ca1fb36": { "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 } }, "e59d644a6fc34c3db40c296c1ad76066": { "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 } }, "ea26c4f1f4734a929f992318210bb977": { "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_e279207276a64e3fa64db22a9ca1fb36", "placeholder": "​", "style": "IPY_MODEL_989cdf29f1224f5396b13f7daeab6ead", "tabbable": null, "tooltip": null, "value": "epoch 2/3: 100%" } }, "ea7a02563a464e42b87caf2fc708bf84": { "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_34d9f3afdd96400393bbd6e284707173", "placeholder": "​", "style": "IPY_MODEL_666c4d3c585442038fe9f7f58fe7a139", "tabbable": null, "tooltip": null, "value": " 469/469 [00:06<00:00, 78.12it/s]" } }, "eaed33e06a004d79942fbb671350c174": { "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 } }, "fc6f0367973e42bfb75f43519d749f56": { "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 } }, "fe051d91f72f425989e1a00bee0198b3": { "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 }