From 78a654084facb3b3244ff5ece26827d284d5fd65 Mon Sep 17 00:00:00 2001 From: Anthony Wang Date: Mon, 16 Aug 2021 21:13:19 -0500 Subject: Initial commit --- .ipynb_checkpoints/intro-checkpoint.ipynb | 43 ++ .../quickstart_tutorial-checkpoint.ipynb | 283 ++++++++ .ipynb_checkpoints/test-checkpoint.ipynb | 6 + model.pth | Bin 0 -> 2680919 bytes quickstart_tutorial.ipynb | 747 +++++++++++++++++++++ test.ipynb | 78 +++ 6 files changed, 1157 insertions(+) create mode 100644 .ipynb_checkpoints/intro-checkpoint.ipynb create mode 100644 .ipynb_checkpoints/quickstart_tutorial-checkpoint.ipynb create mode 100644 .ipynb_checkpoints/test-checkpoint.ipynb create mode 100644 model.pth create mode 100644 quickstart_tutorial.ipynb create mode 100644 test.ipynb diff --git a/.ipynb_checkpoints/intro-checkpoint.ipynb b/.ipynb_checkpoints/intro-checkpoint.ipynb new file mode 100644 index 0000000..95ff70a --- /dev/null +++ b/.ipynb_checkpoints/intro-checkpoint.ipynb @@ -0,0 +1,43 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "%matplotlib inline" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "\n**Learn the Basics** ||\n`Quickstart `_ ||\n`Tensors `_ ||\n`Datasets & DataLoaders `_ ||\n`Transforms `_ ||\n`Build Model `_ ||\n`Autograd `_ ||\n`Optimization `_ ||\n`Save & Load Model `_\n\nLearn the Basics\n===================\n\nAuthors:\n`Suraj Subramanian `_,\n`Seth Juarez `_,\n`Cassie Breviu `_,\n`Dmitry Soshnikov `_,\n`Ari Bornstein `_\n\nMost machine learning workflows involve working with data, creating models, optimizing model\nparameters, and saving the trained models. This tutorial introduces you to a complete ML workflow\nimplemented in PyTorch, with links to learn more about each of these concepts.\n\nWe'll use the FashionMNIST dataset to train a neural network that predicts if an input image belongs\nto one of the following classes: T-shirt/top, Trouser, Pullover, Dress, Coat, Sandal, Shirt, Sneaker,\nBag, or Ankle boot.\n\n`This tutorial assumes a basic familiarity with Python and Deep Learning concepts.`\n\n\nRunning the Tutorial Code\n------------------\nYou can run this tutorial in a couple of ways:\n\n- **In the cloud**: This is the easiest way to get started! Each section has a \"Run in Microsoft Learn\" link at the top, which opens an integrated notebook in Microsoft Learn with the code in a fully-hosted environment.\n- **Locally**: This option requires you to setup PyTorch and TorchVision first on your local machine (`installation instructions `_). Download the notebook or copy the code into your favorite IDE.\n\n\nHow to Use this Guide\n-----------------\nIf you're familiar with other deep learning frameworks, check out the `0. Quickstart `_ first\nto quickly familiarize yourself with PyTorch's API.\n\nIf you're new to deep learning frameworks, head right into the first section of our step-by-step guide: `1. Tensors `_.\n\n\n.. include:: /beginner_source/basics/qs_toc.txt\n\n.. toctree::\n :hidden:\n\n\n" + ] + } + ], + "metadata": { + "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": "3.6.13" + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} \ No newline at end of file diff --git a/.ipynb_checkpoints/quickstart_tutorial-checkpoint.ipynb b/.ipynb_checkpoints/quickstart_tutorial-checkpoint.ipynb new file mode 100644 index 0000000..95d56f7 --- /dev/null +++ b/.ipynb_checkpoints/quickstart_tutorial-checkpoint.ipynb @@ -0,0 +1,283 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "%matplotlib inline" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "\n`Learn the Basics `_ ||\n**Quickstart** ||\n`Tensors `_ ||\n`Datasets & DataLoaders `_ ||\n`Transforms `_ ||\n`Build Model `_ ||\n`Autograd `_ ||\n`Optimization `_ ||\n`Save & Load Model `_\n\nQuickstart\n===================\nThis section runs through the API for common tasks in machine learning. Refer to the links in each section to dive deeper.\n\nWorking with data\n-----------------\nPyTorch has two `primitives to work with data `_:\n``torch.utils.data.DataLoader`` and ``torch.utils.data.Dataset``.\n``Dataset`` stores the samples and their corresponding labels, and ``DataLoader`` wraps an iterable around\nthe ``Dataset``.\n\n\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "import torch\nfrom torch import nn\nfrom torch.utils.data import DataLoader\nfrom torchvision import datasets\nfrom torchvision.transforms import ToTensor, Lambda, Compose\nimport matplotlib.pyplot as plt" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "PyTorch offers domain-specific libraries such as `TorchText `_,\n`TorchVision `_, and `TorchAudio `_,\nall of which include datasets. For this tutorial, we will be using a TorchVision dataset.\n\nThe ``torchvision.datasets`` module contains ``Dataset`` objects for many real-world vision data like\nCIFAR, COCO (`full list here `_). In this tutorial, we\nuse the FashionMNIST dataset. Every TorchVision ``Dataset`` includes two arguments: ``transform`` and\n``target_transform`` to modify the samples and labels respectively.\n\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "# Download training data from open datasets.\ntraining_data = datasets.FashionMNIST(\n root=\"data\",\n train=True,\n download=True,\n transform=ToTensor(),\n)\n\n# Download test data from open datasets.\ntest_data = datasets.FashionMNIST(\n root=\"data\",\n train=False,\n download=True,\n transform=ToTensor(),\n)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "We pass the ``Dataset`` as an argument to ``DataLoader``. This wraps an iterable over our dataset, and supports\nautomatic batching, sampling, shuffling and multiprocess data loading. Here we define a batch size of 64, i.e. each element\nin the dataloader iterable will return a batch of 64 features and labels.\n\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "batch_size = 64\n\n# Create data loaders.\ntrain_dataloader = DataLoader(training_data, batch_size=batch_size)\ntest_dataloader = DataLoader(test_data, batch_size=batch_size)\n\nfor X, y in test_dataloader:\n print(\"Shape of X [N, C, H, W]: \", X.shape)\n print(\"Shape of y: \", y.shape, y.dtype)\n break" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Read more about `loading data in PyTorch `_.\n\n\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "--------------\n\n\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Creating Models\n------------------\nTo define a neural network in PyTorch, we create a class that inherits\nfrom `nn.Module `_. We define the layers of the network\nin the ``__init__`` function and specify how data will pass through the network in the ``forward`` function. To accelerate\noperations in the neural network, we move it to the GPU if available.\n\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "# Get cpu or gpu device for training.\ndevice = \"cuda\" if torch.cuda.is_available() else \"cpu\"\nprint(\"Using {} device\".format(device))\n\n# Define model\nclass NeuralNetwork(nn.Module):\n def __init__(self):\n super(NeuralNetwork, self).__init__()\n self.flatten = nn.Flatten()\n self.linear_relu_stack = nn.Sequential(\n nn.Linear(28*28, 512),\n nn.ReLU(),\n nn.Linear(512, 512),\n nn.ReLU(),\n nn.Linear(512, 10),\n nn.ReLU()\n )\n\n def forward(self, x):\n x = self.flatten(x)\n logits = self.linear_relu_stack(x)\n return logits\n\nmodel = NeuralNetwork().to(device)\nprint(model)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Read more about `building neural networks in PyTorch `_.\n\n\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "--------------\n\n\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Optimizing the Model Parameters\n----------------------------------------\nTo train a model, we need a `loss function `_\nand an `optimizer `_.\n\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "loss_fn = nn.CrossEntropyLoss()\noptimizer = torch.optim.SGD(model.parameters(), lr=1e-3)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "In a single training loop, the model makes predictions on the training dataset (fed to it in batches), and\nbackpropagates the prediction error to adjust the model's parameters.\n\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "def train(dataloader, model, loss_fn, optimizer):\n size = len(dataloader.dataset)\n for batch, (X, y) in enumerate(dataloader):\n X, y = X.to(device), y.to(device)\n\n # Compute prediction error\n pred = model(X)\n loss = loss_fn(pred, y)\n\n # Backpropagation\n optimizer.zero_grad()\n loss.backward()\n optimizer.step()\n\n if batch % 100 == 0:\n loss, current = loss.item(), batch * len(X)\n print(f\"loss: {loss:>7f} [{current:>5d}/{size:>5d}]\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "We also check the model's performance against the test dataset to ensure it is learning.\n\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "def test(dataloader, model, loss_fn):\n size = len(dataloader.dataset)\n num_batches = len(dataloader)\n model.eval()\n test_loss, correct = 0, 0\n with torch.no_grad():\n for X, y in dataloader:\n X, y = X.to(device), y.to(device)\n pred = model(X)\n test_loss += loss_fn(pred, y).item()\n correct += (pred.argmax(1) == y).type(torch.float).sum().item()\n test_loss /= num_batches\n correct /= size\n print(f\"Test Error: \\n Accuracy: {(100*correct):>0.1f}%, Avg loss: {test_loss:>8f} \\n\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "The training process is conducted over several iterations (*epochs*). During each epoch, the model learns\nparameters to make better predictions. We print the model's accuracy and loss at each epoch; we'd like to see the\naccuracy increase and the loss decrease with every epoch.\n\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "epochs = 5\nfor t in range(epochs):\n print(f\"Epoch {t+1}\\n-------------------------------\")\n train(train_dataloader, model, loss_fn, optimizer)\n test(test_dataloader, model, loss_fn)\nprint(\"Done!\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Read more about `Training your model `_.\n\n\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "--------------\n\n\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Saving Models\n-------------\nA common way to save a model is to serialize the internal state dictionary (containing the model parameters).\n\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "torch.save(model.state_dict(), \"model.pth\")\nprint(\"Saved PyTorch Model State to model.pth\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Loading Models\n----------------------------\n\nThe process for loading a model includes re-creating the model structure and loading\nthe state dictionary into it.\n\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "model = NeuralNetwork()\nmodel.load_state_dict(torch.load(\"model.pth\"))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "This model can now be used to make predictions.\n\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "classes = [\n \"T-shirt/top\",\n \"Trouser\",\n \"Pullover\",\n \"Dress\",\n \"Coat\",\n \"Sandal\",\n \"Shirt\",\n \"Sneaker\",\n \"Bag\",\n \"Ankle boot\",\n]\n\nmodel.eval()\nx, y = test_data[0][0], test_data[0][1]\nwith torch.no_grad():\n pred = model(x)\n predicted, actual = classes[pred[0].argmax(0)], classes[y]\n print(f'Predicted: \"{predicted}\", Actual: \"{actual}\"')" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Read more about `Saving & Loading your model `_.\n\n\n" + ] + } + ], + "metadata": { + "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": "3.6.13" + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} \ No newline at end of file diff --git a/.ipynb_checkpoints/test-checkpoint.ipynb b/.ipynb_checkpoints/test-checkpoint.ipynb new file mode 100644 index 0000000..363fcab --- /dev/null +++ b/.ipynb_checkpoints/test-checkpoint.ipynb @@ -0,0 +1,6 @@ +{ + "cells": [], + "metadata": {}, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/model.pth b/model.pth new file mode 100644 index 0000000..3cad339 Binary files /dev/null and b/model.pth differ diff --git a/quickstart_tutorial.ipynb b/quickstart_tutorial.ipynb new file mode 100644 index 0000000..3ea080e --- /dev/null +++ b/quickstart_tutorial.ipynb @@ -0,0 +1,747 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false, + "jupyter": { + "outputs_hidden": false + } + }, + "outputs": [], + "source": [ + "%matplotlib inline" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "\n", + "`Learn the Basics `_ ||\n", + "**Quickstart** ||\n", + "`Tensors `_ ||\n", + "`Datasets & DataLoaders `_ ||\n", + "`Transforms `_ ||\n", + "`Build Model `_ ||\n", + "`Autograd `_ ||\n", + "`Optimization `_ ||\n", + "`Save & Load Model `_\n", + "\n", + "Quickstart\n", + "===================\n", + "This section runs through the API for common tasks in machine learning. Refer to the links in each section to dive deeper.\n", + "\n", + "Working with data\n", + "-----------------\n", + "PyTorch has two `primitives to work with data `_:\n", + "``torch.utils.data.DataLoader`` and ``torch.utils.data.Dataset``.\n", + "``Dataset`` stores the samples and their corresponding labels, and ``DataLoader`` wraps an iterable around\n", + "the ``Dataset``.\n", + "\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": { + "collapsed": false, + "jupyter": { + "outputs_hidden": false + } + }, + "outputs": [], + "source": [ + "import torch\n", + "from torch import nn\n", + "from torch.utils.data import DataLoader\n", + "from torchvision import datasets\n", + "from torchvision.transforms import ToTensor, Lambda, Compose\n", + "import matplotlib.pyplot as plt" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "PyTorch offers domain-specific libraries such as `TorchText `_,\n", + "`TorchVision `_, and `TorchAudio `_,\n", + "all of which include datasets. For this tutorial, we will be using a TorchVision dataset.\n", + "\n", + "The ``torchvision.datasets`` module contains ``Dataset`` objects for many real-world vision data like\n", + "CIFAR, COCO (`full list here `_). In this tutorial, we\n", + "use the FashionMNIST dataset. Every TorchVision ``Dataset`` includes two arguments: ``transform`` and\n", + "``target_transform`` to modify the samples and labels respectively.\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": { + "collapsed": false, + "jupyter": { + "outputs_hidden": false + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz\n", + "Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz to data/FashionMNIST/raw/train-images-idx3-ubyte.gz\n" + ] + }, + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "47918efb82854fc7a269ce73230391b0", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + " 0%| | 0/26421880 [00:00`_.\n", + "\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "--------------\n", + "\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Creating Models\n", + "------------------\n", + "To define a neural network in PyTorch, we create a class that inherits\n", + "from `nn.Module `_. We define the layers of the network\n", + "in the ``__init__`` function and specify how data will pass through the network in the ``forward`` function. To accelerate\n", + "operations in the neural network, we move it to the GPU if available.\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": { + "collapsed": false, + "jupyter": { + "outputs_hidden": false + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Using cpu device\n", + "NeuralNetwork(\n", + " (flatten): Flatten(start_dim=1, end_dim=-1)\n", + " (linear_relu_stack): Sequential(\n", + " (0): Linear(in_features=784, out_features=512, bias=True)\n", + " (1): ReLU()\n", + " (2): Linear(in_features=512, out_features=512, bias=True)\n", + " (3): ReLU()\n", + " (4): Linear(in_features=512, out_features=10, bias=True)\n", + " (5): ReLU()\n", + " )\n", + ")\n" + ] + } + ], + "source": [ + "# Get cpu or gpu device for training.\n", + "device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n", + "print(\"Using {} device\".format(device))\n", + "\n", + "# Define model\n", + "class NeuralNetwork(nn.Module):\n", + " def __init__(self):\n", + " super(NeuralNetwork, self).__init__()\n", + " self.flatten = nn.Flatten()\n", + " self.linear_relu_stack = nn.Sequential(\n", + " nn.Linear(28*28, 512),\n", + " nn.ReLU(),\n", + " nn.Linear(512, 512),\n", + " nn.ReLU(),\n", + " nn.Linear(512, 10),\n", + " nn.ReLU()\n", + " )\n", + "\n", + " def forward(self, x):\n", + " x = self.flatten(x)\n", + " logits = self.linear_relu_stack(x)\n", + " return logits\n", + "\n", + "model = NeuralNetwork().to(device)\n", + "print(model)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Read more about `building neural networks in PyTorch `_.\n", + "\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "--------------\n", + "\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Optimizing the Model Parameters\n", + "----------------------------------------\n", + "To train a model, we need a `loss function `_\n", + "and an `optimizer `_.\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": { + "collapsed": false, + "jupyter": { + "outputs_hidden": false + } + }, + "outputs": [], + "source": [ + "loss_fn = nn.CrossEntropyLoss()\n", + "optimizer = torch.optim.SGD(model.parameters(), lr=1e-3)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "In a single training loop, the model makes predictions on the training dataset (fed to it in batches), and\n", + "backpropagates the prediction error to adjust the model's parameters.\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": { + "collapsed": false, + "jupyter": { + "outputs_hidden": false + } + }, + "outputs": [], + "source": [ + "def train(dataloader, model, loss_fn, optimizer):\n", + " size = len(dataloader.dataset)\n", + " for batch, (X, y) in enumerate(dataloader):\n", + " X, y = X.to(device), y.to(device)\n", + "\n", + " # Compute prediction error\n", + " pred = model(X)\n", + " loss = loss_fn(pred, y)\n", + "\n", + " # Backpropagation\n", + " optimizer.zero_grad()\n", + " loss.backward()\n", + " optimizer.step()\n", + "\n", + " if batch % 100 == 0:\n", + " loss, current = loss.item(), batch * len(X)\n", + " print(f\"loss: {loss:>7f} [{current:>5d}/{size:>5d}]\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "We also check the model's performance against the test dataset to ensure it is learning.\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": { + "collapsed": false, + "jupyter": { + "outputs_hidden": false + } + }, + "outputs": [], + "source": [ + "def test(dataloader, model, loss_fn):\n", + " size = len(dataloader.dataset)\n", + " num_batches = len(dataloader)\n", + " model.eval()\n", + " test_loss, correct = 0, 0\n", + " with torch.no_grad():\n", + " for X, y in dataloader:\n", + " X, y = X.to(device), y.to(device)\n", + " pred = model(X)\n", + " test_loss += loss_fn(pred, y).item()\n", + " correct += (pred.argmax(1) == y).type(torch.float).sum().item()\n", + " test_loss /= num_batches\n", + " correct /= size\n", + " print(f\"Test Error: \\n Accuracy: {(100*correct):>0.1f}%, Avg loss: {test_loss:>8f} \\n\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "The training process is conducted over several iterations (*epochs*). During each epoch, the model learns\n", + "parameters to make better predictions. We print the model's accuracy and loss at each epoch; we'd like to see the\n", + "accuracy increase and the loss decrease with every epoch.\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": { + "collapsed": false, + "jupyter": { + "outputs_hidden": false + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch 1\n", + "-------------------------------\n", + "loss: 1.758146 [ 0/60000]\n", + "loss: 1.820034 [ 6400/60000]\n", + "loss: 1.846449 [12800/60000]\n", + "loss: 1.975245 [19200/60000]\n", + "loss: 1.612495 [25600/60000]\n", + "loss: 1.748993 [32000/60000]\n", + "loss: 1.628008 [38400/60000]\n", + "loss: 1.655061 [44800/60000]\n", + "loss: 1.770255 [51200/60000]\n", + "loss: 1.654287 [57600/60000]\n", + "Test Error: \n", + " Accuracy: 37.7%, Avg loss: 1.749445 \n", + "\n", + "Epoch 2\n", + "-------------------------------\n", + "loss: 1.670408 [ 0/60000]\n", + "loss: 1.743051 [ 6400/60000]\n", + "loss: 1.773547 [12800/60000]\n", + "loss: 1.924395 [19200/60000]\n", + "loss: 1.529726 [25600/60000]\n", + "loss: 1.692361 [32000/60000]\n", + "loss: 1.559834 [38400/60000]\n", + "loss: 1.593531 [44800/60000]\n", + "loss: 1.712157 [51200/60000]\n", + "loss: 1.605115 [57600/60000]\n", + "Test Error: \n", + " Accuracy: 38.1%, Avg loss: 1.694516 \n", + "\n", + "Epoch 3\n", + "-------------------------------\n", + "loss: 1.607648 [ 0/60000]\n", + "loss: 1.684907 [ 6400/60000]\n", + "loss: 1.716139 [12800/60000]\n", + "loss: 1.888849 [19200/60000]\n", + "loss: 1.474264 [25600/60000]\n", + "loss: 1.652733 [32000/60000]\n", + "loss: 1.514825 [38400/60000]\n", + "loss: 1.549373 [44800/60000]\n", + "loss: 1.670293 [51200/60000]\n", + "loss: 1.571395 [57600/60000]\n", + "Test Error: \n", + " Accuracy: 39.0%, Avg loss: 1.653676 \n", + "\n", + "Epoch 4\n", + "-------------------------------\n", + "loss: 1.561757 [ 0/60000]\n", + "loss: 1.640771 [ 6400/60000]\n", + "loss: 1.669458 [12800/60000]\n", + "loss: 1.862879 [19200/60000]\n", + "loss: 1.435348 [25600/60000]\n", + "loss: 1.623189 [32000/60000]\n", + "loss: 1.482370 [38400/60000]\n", + "loss: 1.515045 [44800/60000]\n", + "loss: 1.638349 [51200/60000]\n", + "loss: 1.545919 [57600/60000]\n", + "Test Error: \n", + " Accuracy: 39.9%, Avg loss: 1.621615 \n", + "\n", + "Epoch 5\n", + "-------------------------------\n", + "loss: 1.525517 [ 0/60000]\n", + "loss: 1.604991 [ 6400/60000]\n", + "loss: 1.630397 [12800/60000]\n", + "loss: 1.841878 [19200/60000]\n", + "loss: 1.406707 [25600/60000]\n", + "loss: 1.599460 [32000/60000]\n", + "loss: 1.456716 [38400/60000]\n", + "loss: 1.485950 [44800/60000]\n", + "loss: 1.612476 [51200/60000]\n", + "loss: 1.525381 [57600/60000]\n", + "Test Error: \n", + " Accuracy: 40.7%, Avg loss: 1.595456 \n", + "\n", + "Done!\n" + ] + } + ], + "source": [ + "epochs = 5\n", + "for t in range(epochs):\n", + " print(f\"Epoch {t+1}\\n-------------------------------\")\n", + " train(train_dataloader, model, loss_fn, optimizer)\n", + " test(test_dataloader, model, loss_fn)\n", + "print(\"Done!\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Read more about `Training your model `_.\n", + "\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "--------------\n", + "\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Saving Models\n", + "-------------\n", + "A common way to save a model is to serialize the internal state dictionary (containing the model parameters).\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": { + "collapsed": false, + "jupyter": { + "outputs_hidden": false + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Saved PyTorch Model State to model.pth\n" + ] + } + ], + "source": [ + "torch.save(model.state_dict(), \"model.pth\")\n", + "print(\"Saved PyTorch Model State to model.pth\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Loading Models\n", + "----------------------------\n", + "\n", + "The process for loading a model includes re-creating the model structure and loading\n", + "the state dictionary into it.\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": { + "collapsed": false, + "jupyter": { + "outputs_hidden": false + } + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "model = NeuralNetwork()\n", + "model.load_state_dict(torch.load(\"model.pth\"))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "This model can now be used to make predictions.\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": { + "collapsed": false, + "jupyter": { + "outputs_hidden": false + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Predicted: \"Ankle boot\", Actual: \"Ankle boot\"\n" + ] + } + ], + "source": [ + "classes = [\n", + " \"T-shirt/top\",\n", + " \"Trouser\",\n", + " \"Pullover\",\n", + " \"Dress\",\n", + " \"Coat\",\n", + " \"Sandal\",\n", + " \"Shirt\",\n", + " \"Sneaker\",\n", + " \"Bag\",\n", + " \"Ankle boot\",\n", + "]\n", + "\n", + "model.eval()\n", + "x, y = test_data[0][0], test_data[0][1]\n", + "with torch.no_grad():\n", + " pred = model(x)\n", + " predicted, actual = classes[pred[0].argmax(0)], classes[y]\n", + " print(f'Predicted: \"{predicted}\", Actual: \"{actual}\"')" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Read more about `Saving & Loading your model `_.\n", + "\n", + "\n" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "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": "3.9.6" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +} diff --git a/test.ipynb b/test.ipynb new file mode 100644 index 0000000..3312e79 --- /dev/null +++ b/test.ipynb @@ -0,0 +1,78 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "id": "5a2a1e37-f4db-4963-a0ac-7b39353f826f", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "tensor([[0.2226, 0.2227, 0.1347],\n", + " [0.7975, 0.3823, 0.9395],\n", + " [0.1675, 0.9185, 0.4175],\n", + " [0.0476, 0.1244, 0.6878],\n", + " [0.5177, 0.7245, 0.2723]])\n" + ] + } + ], + "source": [ + "import torch\n", + "x = torch.rand(5, 3)\n", + "print(x)" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "id": "53469c52-9438-4d62-aa2a-e93fb3fef23b", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "False" + ] + }, + "execution_count": 2, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "torch.cuda.is_available()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "f13c7010-acb0-4870-aa6f-1294701cfc7e", + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "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": "3.9.6" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} -- cgit v1.2.3-70-g09d2