Files
mrdbourke--pytorch-deep-lea…/extras/exercises/09_pytorch_model_deployment_exercises.ipynb
T
wehub-resource-sync 37c25cd088
make_docs / deploy (push) Waiting to run
chore: import upstream snapshot with attribution
2026-07-13 13:27:58 +08:00

556 lines
134 KiB
Plaintext

{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "view-in-github"
},
"source": [
"<a href=\"https://colab.research.google.com/github/mrdbourke/pytorch-deep-learning/blob/main/extras/exercises/09_pytorch_model_deployment_exercises.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "zNqPNlYylluR"
},
"source": [
"# 09. PyTorch Model Deployment Exercises\n",
"\n",
"Welcome to the 09. PyTorch Model Deployment exercises.\n",
"\n",
"Your objective is to write code to satisify each of the exercises below.\n",
"\n",
"Some starter code has been provided to make sure you have all the resources you need.\n",
"\n",
"> **Note:** There may be more than one solution to each of the exercises.\n",
"\n",
"## Resources\n",
"\n",
"1. These exercises/solutions are based on [section 09. PyTorch Model Deployment](https://www.learnpytorch.io/09_pytorch_model_deployment/) of the Learn PyTorch for Deep Learning course by Zero to Mastery.\n",
"2. See a live [walkthrough of the solutions (errors and all) on YouTube](https://youtu.be/jOX5ZCkWO-0) (but try the exercises yourself first!).\n",
"3. See [all solutions on the course GitHub](https://github.com/mrdbourke/pytorch-deep-learning/tree/main/extras/solutions).\n",
"\n",
"> **Note:** The first section of this notebook is dedicated to getting various helper functions and datasets used for the exercises. The exercises start at the heading \"Exercise 1: ...\"."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "sf8ab9cyHTzU"
},
"source": [
"### Get various imports and helper functions\n",
"\n",
"The code in the following cells prepares imports and data for the exercises below. They are taken from [09. PyTorch Model Deployment](https://www.learnpytorch.io/09_pytorch_model_deployment/). "
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "ChRaHUSJ8DYZ",
"outputId": "6cb38a59-1a4e-4fb3-d531-9606a65a7138"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"torch version: 1.12.1+cu113\n",
"torchvision version: 0.13.1+cu113\n"
]
}
],
"source": [
"# For this notebook to run with updated APIs, we need torch 1.12+ and torchvision 0.13+\n",
"try:\n",
" import torch\n",
" import torchvision\n",
" assert int(torch.__version__.split(\".\")[1]) >= 12 or int(torch.__version__.split(\".\")[0]) > 1, \"torch version should be 1.12+\"\n",
" assert int(torchvision.__version__.split(\".\")[1]) >= 13, \"torchvision version should be 0.13+\"\n",
" print(f\"torch version: {torch.__version__}\")\n",
" print(f\"torchvision version: {torchvision.__version__}\")\n",
"except:\n",
" print(f\"[INFO] torch/torchvision versions not as required, installing nightly versions.\")\n",
" !pip3 install -U torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu113\n",
" import torch\n",
" import torchvision\n",
" print(f\"torch version: {torch.__version__}\")\n",
" print(f\"torchvision version: {torchvision.__version__}\")\n"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"id": "Y5H5P8EjCNGK"
},
"outputs": [],
"source": [
"# Continue with regular imports\n",
"import matplotlib.pyplot as plt\n",
"import torch\n",
"import torchvision\n",
"\n",
"from torch import nn\n",
"from torchvision import transforms\n",
"\n",
"# Try to get torchinfo, install it if it doesn't work\n",
"try:\n",
" from torchinfo import summary\n",
"except:\n",
" print(\"[INFO] Couldn't find torchinfo... installing it.\")\n",
" !pip install -q torchinfo\n",
" from torchinfo import summary\n",
"\n",
"# Try to import the going_modular directory, download it from GitHub if it doesn't work\n",
"try:\n",
" from going_modular.going_modular import data_setup, engine\n",
" from helper_functions import download_data, set_seeds, plot_loss_curves\n",
"except:\n",
" # Get the going_modular scripts\n",
" print(\"[INFO] Couldn't find going_modular or helper_functions scripts... downloading them from GitHub.\")\n",
" !git clone https://github.com/mrdbourke/pytorch-deep-learning\n",
" !mv pytorch-deep-learning/going_modular .\n",
" !mv pytorch-deep-learning/helper_functions.py . # get the helper_functions.py script\n",
" !rm -rf pytorch-deep-learning\n",
" from going_modular.going_modular import data_setup, engine\n",
" from helper_functions import download_data, set_seeds, plot_loss_curves"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 35
},
"id": "bE1AAH_uCjiP",
"outputId": "791af6d4-9e76-492f-bfca-df540cc4fe35"
},
"outputs": [
{
"data": {
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "string"
},
"text/plain": [
"'cuda'"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n",
"device"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "GmS5yuvxCpLp"
},
"source": [
"### Get data\n",
"\n",
"Want to download the data we've been using in PyTorch Model Deployment: https://www.learnpytorch.io/09_pytorch_model_deployment/#1-getting-data"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "dm772wqgCzN9",
"outputId": "20c3b48d-2c39-4188-ac0f-5e3770d51608"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[INFO] data/pizza_steak_sushi directory exists, skipping download.\n"
]
},
{
"data": {
"text/plain": [
"PosixPath('data/pizza_steak_sushi')"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Download pizza, steak, sushi images from GitHub\n",
"image_path = download_data(source=\"https://github.com/mrdbourke/pytorch-deep-learning/raw/main/data/pizza_steak_sushi_20_percent.zip\",\n",
" destination=\"pizza_steak_sushi\")\n",
"image_path"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"id": "r1ML2c-dCzCi"
},
"outputs": [],
"source": [
"# Setup directory paths to train and test images\n",
"train_dir = image_path / \"train\"\n",
"test_dir = image_path / \"test\""
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "nNBZ_2h_Cy86"
},
"source": [
"### Preprocess data\n",
"\n",
"Turn images into tensors using same code as PyTorch Paper Replicating section 2.1 and 2.2: https://www.learnpytorch.io/08_pytorch_paper_replicating/#21-prepare-transforms-for-images"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "mU0T4gP3DJdF",
"outputId": "a0440ce0-aac5-4f12-b39b-5a0ecad2c959"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Manually created transforms: Compose(\n",
" Resize(size=(224, 224), interpolation=bilinear, max_size=None, antialias=None)\n",
" ToTensor()\n",
")\n"
]
}
],
"source": [
"# Create image size (from Table 3 in the ViT paper) \n",
"IMG_SIZE = 224\n",
"\n",
"# Create transform pipeline manually\n",
"manual_transforms = transforms.Compose([\n",
" transforms.Resize((IMG_SIZE, IMG_SIZE)),\n",
" transforms.ToTensor(),\n",
"]) \n",
"print(f\"Manually created transforms: {manual_transforms}\")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "W4vWgIprDJau",
"outputId": "895ab2e0-62e4-4377-8347-645cc295b013"
},
"outputs": [
{
"data": {
"text/plain": [
"(<torch.utils.data.dataloader.DataLoader at 0x7fb52d4b77d0>,\n",
" <torch.utils.data.dataloader.DataLoader at 0x7fb52d46a450>,\n",
" ['pizza', 'steak', 'sushi'])"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Set the batch size\n",
"BATCH_SIZE = 32 # this is lower than the ViT paper but it's because we're starting small\n",
"\n",
"# Create data loaders\n",
"train_dataloader, test_dataloader, class_names = data_setup.create_dataloaders(\n",
" train_dir=train_dir,\n",
" test_dir=test_dir,\n",
" transform=manual_transforms, # use manually created transforms\n",
" batch_size=BATCH_SIZE\n",
")\n",
"\n",
"train_dataloader, test_dataloader, class_names"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "u7eLIFHyDJRr",
"outputId": "bc8e8d27-2e10-4b78-9304-4d713917b00d"
},
"outputs": [
{
"data": {
"text/plain": [
"(torch.Size([3, 224, 224]), tensor(2))"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Get a batch of images\n",
"image_batch, label_batch = next(iter(train_dataloader))\n",
"\n",
"# Get a single image from the batch\n",
"image, label = image_batch[0], label_batch[0]\n",
"\n",
"# View the batch shapes\n",
"image.shape, label"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 264
},
"id": "2yyNHCmCDbSR",
"outputId": "b1d50d6c-e043-4a21-88da-d0213bf2e018"
},
"outputs": [
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"# Plot image with matplotlib\n",
"plt.imshow(image.permute(1, 2, 0)) # rearrange image dimensions to suit matplotlib [color_channels, height, width] -> [height, width, color_channels]\n",
"plt.title(class_names[label])\n",
"plt.axis(False);"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "nwmoMhW8IqSu"
},
"source": [
"## Exercise 1. Make and time predictions with both feature extractor models on the test dataset using the GPU (`device=\"cuda\"`). \n",
"\n",
"* Compare the model's prediction times on GPU vs CPU - does this close the gap between them? As in, does making predictions on the GPU make the ViT feature extractor prediction times closer to the EffNetB2 feature extractor prediction times?\n",
"* You'll find code to do these steps in [section 5. Making predictions with our trained models and timing them](https://www.learnpytorch.io/09_pytorch_model_deployment/#5-making-predictions-with-our-trained-models-and-timing-them) and [section 6. Comparing model results, prediction times and size](https://www.learnpytorch.io/09_pytorch_model_deployment/#6-comparing-model-results-prediction-times-and-size)."
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"id": "pmDd_YZ7VSrL"
},
"outputs": [],
"source": [
"# TODO: your code"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "MBWnDZao9w_5"
},
"source": [
"## Exercise 2. The ViT feature extractor seems to have more learning capacity (due to more parameters) than EffNetB2, how does it go on the larger 20% split of the entire Food101 dataset?\n",
"\n",
"* Train a ViT feature extractor on the 20% Food101 dataset for 5 epochs, just like we did with EffNetB2 in section [10. Creating FoodVision Big](https://www.learnpytorch.io/09_pytorch_model_deployment/#10-creating-foodvision-big)."
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"id": "NFXVZNCzVYgV"
},
"outputs": [],
"source": [
"# TODO: your code"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "aTKbje-e9118"
},
"source": [
"## Exercise 3. Make predictions across the 20% Food101 test dataset with the ViT feature extractor from exercise 2 and find the \"most wrong\" predictions\n",
"* The predictions will be the ones with the highest prediction probability but with the wrong predicted label.\n",
"* Write a sentence or two about why you think the model got these predictions wrong."
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"id": "R7iKYRAUVkA7"
},
"outputs": [],
"source": [
"# TODO: your code"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "LH-vHr3m9_oH"
},
"source": [
"## Exercise 4. Evaluate the ViT feature extractor across the whole Food101 test dataset rather than just the 20% version, how does it perform?\n",
"* Does it beat the original Food101 paper's best result of 56.4% accuracy?"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"id": "dWxceTz3VmeB"
},
"outputs": [],
"source": [
"# TODO: your code"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "ZLcCgRhS-OhV"
},
"source": [
"## Exercise 5. Head to [Paperswithcode.com](https://paperswithcode.com/) and find the current best performing model on the Food101 dataset.\n",
"* What model architecture does it use?"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"id": "7HwonCSsVtnr"
},
"outputs": [],
"source": [
"# TODO: your answer to the above"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "ujfO-mmmHfUZ"
},
"source": [
"## Exercise 6. Write down 1-3 potential failure points of our deployed FoodVision models and what some potential solutions might be.\n",
"* For example, what happens if someone was to upload a photo that wasn't of food to our FoodVision Mini model?"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"id": "fEmSj0f3HevI"
},
"outputs": [],
"source": [
"# TODO: your answer to the above"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "NkHIwxA2Hj7j"
},
"source": [
"## Exercise 7. Pick any dataset from [`torchvision.datasets`](https://pytorch.org/vision/stable/datasets.html) and train a feature extractor model on it using a model from [`torchvision.models`](https://pytorch.org/vision/stable/models.html) (you could use one of the model's we've already created, e.g. EffNetB2 or ViT) for 5 epochs and then deploy your model as a Gradio app to Hugging Face Spaces. \n",
"* You may want to pick smaller dataset/make a smaller split of it so training doesn't take too long.\n",
"* I'd love to see your deployed models! So be sure to share them in Discord or on the [course GitHub Discussions page](https://github.com/mrdbourke/pytorch-deep-learning/discussions)."
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {
"id": "0URR1A8_HobF"
},
"outputs": [],
"source": [
"# TODO: your code"
]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"authorship_tag": "ABX9TyOpTNnoV+StMaGmx7snqUcn",
"collapsed_sections": [],
"include_colab_link": true,
"name": "09_pytorch_model_deployment_exercises.ipynb",
"provenance": [],
"toc_visible": true
},
"gpuClass": "standard",
"kernelspec": {
"display_name": "Python 3.8.13",
"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": "3.8.13"
},
"vscode": {
"interpreter": {
"hash": "3fbe1355223f7b2ffc113ba3ade6a2b520cadace5d5ec3e828c83ce02eb221bf"
}
}
},
"nbformat": 4,
"nbformat_minor": 4
}