Skip to content

Commit

Permalink
Merge pull request #349 from neuromatch/prepod-day-2
Browse files Browse the repository at this point in the history 
preventing outputs
  • Loading branch information
@SamueleBolotta
SamueleBolotta authored Jun 27, 2024
2 parents 837d97a + dc6b2ec commit 482c904
Show file tree
Hide file tree
Showing 7 changed files with 145 additions and 226 deletions.
77 changes: 39 additions & 38 deletions tutorials/W1D2_ComparingTasks/W1D2_Tutorial1.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -176,6 +176,8 @@
"from pathlib import Path\n",
"import zipfile\n",
"import random\n",
"import contextlib\n",
"import io\n",
"\n",
"# Import third-party libraries\n",
"import numpy as np\n",
Expand Down Expand Up @@ -844,50 +846,49 @@
},
"outputs": [],
"source": [
"# Define a transformation pipeline for the MNIST dataset\n",
"mnist_transform = transforms.Compose([\n",
" transforms.Resize((32, 32)), # Resize the images to 32x32 pixels\n",
" transforms.ToTensor(), # Convert images to PyTorch tensors\n",
" transforms.Normalize(mean=(0.1307,), std=(0.3081,)) # Normalize the images with mean and standard deviation\n",
"])\n",
"with contextlib.redirect_stdout(io.StringIO()):\n",
"\n",
"# Load the MNIST training dataset with transformations applied\n",
"train_val_dataset = torchvision.datasets.MNIST(\n",
" root='./data', # Directory to store/load the data\n",
" train=True, # Specify to load the training set\n",
" transform=mnist_transform, # Apply the transformation pipeline defined earlier\n",
" download=True # Download the dataset if it's not already present\n",
")\n",
" # Define a transformation pipeline for the MNIST dataset\n",
" mnist_transform = transforms.Compose([\n",
" transforms.Resize((32, 32)), # Resize the images to 32x32 pixels\n",
" transforms.ToTensor(), # Convert images to PyTorch tensors\n",
" transforms.Normalize(mean=(0.1307,), std=(0.3081,)) # Normalize the images with mean and standard deviation\n",
" ])\n",
"\n",
"# Load the MNIST test dataset with transformations applied\n",
"test_dataset = torchvision.datasets.MNIST(\n",
" root='./data', # Directory to store/load the data\n",
" train=False, # Specify to load the test set\n",
" transform=mnist_transform, # Apply the transformation pipeline defined earlier\n",
" download=True # Download the dataset if it's not already present\n",
")\n",
" # Load the MNIST training dataset with transformations applied\n",
" train_val_dataset = torchvision.datasets.MNIST(\n",
" root='./data', # Directory to store/load the data\n",
" train=True, # Specify to load the training set\n",
" transform=mnist_transform, # Apply the transformation pipeline defined earlier\n",
" download=True # Download the dataset if it's not already present\n",
" )\n",
"\n",
"# Split the training dataset into training and validation sets\n",
"train_size = int(0.9 * len(train_val_dataset)) # Calculate the size of the training set (90% of the original)\n",
"val_size = len(train_val_dataset) - train_size # Calculate the size of the validation set (remaining 10%)\n",
"train_dataset, val_dataset = torch.utils.data.random_split(\n",
" dataset=train_val_dataset, # Original training dataset to split\n",
" lengths=[train_size, val_size] # Lengths of the resulting splits\n",
")\n",
" # Load the MNIST test dataset with transformations applied\n",
" test_dataset = torchvision.datasets.MNIST(\n",
" root='./data', # Directory to store/load the data\n",
" train=False, # Specify to load the test set\n",
" transform=mnist_transform, # Apply the transformation pipeline defined earlier\n",
" download=True # Download the dataset if it's not already present\n",
" )\n",
"\n",
"# Split the test dataset into two halves: original and transfer sets\n",
"test_size_original = int(0.5 * len(test_dataset)) # Calculate the size of the original test set (50% of the original)\n",
"test_size_transfer = len(test_dataset) - test_size_original # Calculate the size of the transfer test set (remaining 50%)\n",
"test_dataset_original, test_dataset_transfer = torch.utils.data.random_split(\n",
" dataset=test_dataset, # Original test dataset to split\n",
" lengths=[test_size_original, test_size_transfer] # Lengths of the resulting splits\n",
")\n",
" # Split the training dataset into training and validation sets\n",
" train_size = int(0.9 * len(train_val_dataset)) # Calculate the size of the training set (90% of the original)\n",
" val_size = len(train_val_dataset) - train_size # Calculate the size of the validation set (remaining 10%)\n",
" train_dataset, val_dataset = torch.utils.data.random_split(\n",
" dataset=train_val_dataset, # Original training dataset to split\n",
" lengths=[train_size, val_size] # Lengths of the resulting splits\n",
" )\n",
"\n",
"# Display the training dataset object\n",
"train_dataset\n",
" # Split the test dataset into two halves: original and transfer sets\n",
" test_size_original = int(0.5 * len(test_dataset)) # Calculate the size of the original test set (50% of the original)\n",
" test_size_transfer = len(test_dataset) - test_size_original # Calculate the size of the transfer test set (remaining 50%)\n",
" test_dataset_original, test_dataset_transfer = torch.utils.data.random_split(\n",
" dataset=test_dataset, # Original test dataset to split\n",
" lengths=[test_size_original, test_size_transfer] # Lengths of the resulting splits\n",
" )\n",
"\n",
"# Print the sizes of the training, validation, original test, and transfer test datasets\n",
"len(train_dataset), len(val_dataset), len(test_dataset_original), len(test_dataset_transfer)"
" # Display the training dataset object\n",
" train_dataset"
]
},
{
Expand Down
44 changes: 8 additions & 36 deletions tutorials/W1D2_ComparingTasks/W1D2_Tutorial2.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -84,8 +84,7 @@
"cell_type": "markdown",
"id": "273ae64d-bc44-4e0e-b077-487da8391334",
"metadata": {
"execution": {},
"jp-MarkdownHeadingCollapsed": true
"execution": {}
},
"source": [
"---\n",
Expand Down Expand Up @@ -153,6 +152,8 @@
"\n",
"import logging\n",
"import gc\n",
"import contextlib\n",
"import io\n",
"\n",
"# PyTorch and related libraries\n",
"import torch\n",
Expand Down Expand Up @@ -181,8 +182,7 @@
"cell_type": "markdown",
"id": "910f242f",
"metadata": {
"execution": {},
"jp-MarkdownHeadingCollapsed": true
"execution": {}
},
"source": [
"## Figure settings\n"
Expand Down Expand Up @@ -211,40 +211,11 @@
"plt.style.use(\"https://raw.githubusercontent.com/NeuromatchAcademy/course-content/main/nma.mplstyle\")"
]
},
{
"cell_type": "markdown",
"id": "01471a7f",
"metadata": {
"execution": {},
"jp-MarkdownHeadingCollapsed": true
},
"source": [
"## Plotting functions\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "598cc45f-c4b7-406c-a80b-6adfae387583",
"metadata": {
"cellView": "form",
"execution": {},
"tags": [
"hide-input"
]
},
"outputs": [],
"source": [
"# @title Plotting functions\n",
"# @markdown"
]
},
{
"cell_type": "markdown",
"id": "808d728a",
"metadata": {
"execution": {},
"jp-MarkdownHeadingCollapsed": true
"execution": {}
},
"source": [
"## Helper functions"
Expand Down Expand Up @@ -526,8 +497,9 @@
" torchvision.transforms.Normalize((0.1307,), (0.3081,)) # Normalize the images with mean and standard deviation\n",
"])\n",
"\n",
"# Load the MNIST test dataset with the defined transformations\n",
"test_dset = torchvision.datasets.MNIST(\"./\", train=False, transform=mnist_transforms, download=True)\n",
"with contextlib.redirect_stdout(io.StringIO()):\n",
" # Load the MNIST test dataset with the defined transformations\n",
" test_dset = torchvision.datasets.MNIST(\"./\", train=False, transform=mnist_transforms, download=True)\n",
"\n",
"# Calculate the height and width of the MNIST images (28x28)\n",
"height = int(784**0.5)\n",
Expand Down
81 changes: 41 additions & 40 deletions tutorials/W1D2_ComparingTasks/instructor/W1D2_Tutorial1.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -176,6 +176,8 @@
"from pathlib import Path\n",
"import zipfile\n",
"import random\n",
"import contextlib\n",
"import io\n",
"\n",
"# Import third-party libraries\n",
"import numpy as np\n",
Expand Down Expand Up @@ -844,50 +846,49 @@
},
"outputs": [],
"source": [
"# Define a transformation pipeline for the MNIST dataset\n",
"mnist_transform = transforms.Compose([\n",
" transforms.Resize((32, 32)), # Resize the images to 32x32 pixels\n",
" transforms.ToTensor(), # Convert images to PyTorch tensors\n",
" transforms.Normalize(mean=(0.1307,), std=(0.3081,)) # Normalize the images with mean and standard deviation\n",
"])\n",
"\n",
"# Load the MNIST training dataset with transformations applied\n",
"train_val_dataset = torchvision.datasets.MNIST(\n",
" root='./data', # Directory to store/load the data\n",
" train=True, # Specify to load the training set\n",
" transform=mnist_transform, # Apply the transformation pipeline defined earlier\n",
" download=True # Download the dataset if it's not already present\n",
")\n",
"\n",
"# Load the MNIST test dataset with transformations applied\n",
"test_dataset = torchvision.datasets.MNIST(\n",
" root='./data', # Directory to store/load the data\n",
" train=False, # Specify to load the test set\n",
" transform=mnist_transform, # Apply the transformation pipeline defined earlier\n",
" download=True # Download the dataset if it's not already present\n",
")\n",
"with contextlib.redirect_stdout(io.StringIO()):\n",
"\n",
" # Define a transformation pipeline for the MNIST dataset\n",
" mnist_transform = transforms.Compose([\n",
" transforms.Resize((32, 32)), # Resize the images to 32x32 pixels\n",
" transforms.ToTensor(), # Convert images to PyTorch tensors\n",
" transforms.Normalize(mean=(0.1307,), std=(0.3081,)) # Normalize the images with mean and standard deviation\n",
" ])\n",
"\n",
" # Load the MNIST training dataset with transformations applied\n",
" train_val_dataset = torchvision.datasets.MNIST(\n",
" root='./data', # Directory to store/load the data\n",
" train=True, # Specify to load the training set\n",
" transform=mnist_transform, # Apply the transformation pipeline defined earlier\n",
" download=True # Download the dataset if it's not already present\n",
" )\n",
"\n",
"# Split the training dataset into training and validation sets\n",
"train_size = int(0.9 * len(train_val_dataset)) # Calculate the size of the training set (90% of the original)\n",
"val_size = len(train_val_dataset) - train_size # Calculate the size of the validation set (remaining 10%)\n",
"train_dataset, val_dataset = torch.utils.data.random_split(\n",
" dataset=train_val_dataset, # Original training dataset to split\n",
" lengths=[train_size, val_size] # Lengths of the resulting splits\n",
")\n",
" # Load the MNIST test dataset with transformations applied\n",
" test_dataset = torchvision.datasets.MNIST(\n",
" root='./data', # Directory to store/load the data\n",
" train=False, # Specify to load the test set\n",
" transform=mnist_transform, # Apply the transformation pipeline defined earlier\n",
" download=True # Download the dataset if it's not already present\n",
" )\n",
"\n",
"# Split the test dataset into two halves: original and transfer sets\n",
"test_size_original = int(0.5 * len(test_dataset)) # Calculate the size of the original test set (50% of the original)\n",
"test_size_transfer = len(test_dataset) - test_size_original # Calculate the size of the transfer test set (remaining 50%)\n",
"test_dataset_original, test_dataset_transfer = torch.utils.data.random_split(\n",
" dataset=test_dataset, # Original test dataset to split\n",
" lengths=[test_size_original, test_size_transfer] # Lengths of the resulting splits\n",
")\n",
" # Split the training dataset into training and validation sets\n",
" train_size = int(0.9 * len(train_val_dataset)) # Calculate the size of the training set (90% of the original)\n",
" val_size = len(train_val_dataset) - train_size # Calculate the size of the validation set (remaining 10%)\n",
" train_dataset, val_dataset = torch.utils.data.random_split(\n",
" dataset=train_val_dataset, # Original training dataset to split\n",
" lengths=[train_size, val_size] # Lengths of the resulting splits\n",
" )\n",
"\n",
"# Display the training dataset object\n",
"train_dataset\n",
" # Split the test dataset into two halves: original and transfer sets\n",
" test_size_original = int(0.5 * len(test_dataset)) # Calculate the size of the original test set (50% of the original)\n",
" test_size_transfer = len(test_dataset) - test_size_original # Calculate the size of the transfer test set (remaining 50%)\n",
" test_dataset_original, test_dataset_transfer = torch.utils.data.random_split(\n",
" dataset=test_dataset, # Original test dataset to split\n",
" lengths=[test_size_original, test_size_transfer] # Lengths of the resulting splits\n",
" )\n",
"\n",
"# Print the sizes of the training, validation, original test, and transfer test datasets\n",
"len(train_dataset), len(val_dataset), len(test_dataset_original), len(test_dataset_transfer)"
" # Display the training dataset object\n",
" train_dataset"
]
},
{
Expand Down
44 changes: 8 additions & 36 deletions tutorials/W1D2_ComparingTasks/instructor/W1D2_Tutorial2.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -84,8 +84,7 @@
"cell_type": "markdown",
"id": "273ae64d-bc44-4e0e-b077-487da8391334",
"metadata": {
"execution": {},
"jp-MarkdownHeadingCollapsed": true
"execution": {}
},
"source": [
"---\n",
Expand Down Expand Up @@ -153,6 +152,8 @@
"\n",
"import logging\n",
"import gc\n",
"import contextlib\n",
"import io\n",
"\n",
"# PyTorch and related libraries\n",
"import torch\n",
Expand Down Expand Up @@ -181,8 +182,7 @@
"cell_type": "markdown",
"id": "910f242f",
"metadata": {
"execution": {},
"jp-MarkdownHeadingCollapsed": true
"execution": {}
},
"source": [
"## Figure settings\n"
Expand Down Expand Up @@ -211,40 +211,11 @@
"plt.style.use(\"https://raw.githubusercontent.com/NeuromatchAcademy/course-content/main/nma.mplstyle\")"
]
},
{
"cell_type": "markdown",
"id": "01471a7f",
"metadata": {
"execution": {},
"jp-MarkdownHeadingCollapsed": true
},
"source": [
"## Plotting functions\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "598cc45f-c4b7-406c-a80b-6adfae387583",
"metadata": {
"cellView": "form",
"execution": {},
"tags": [
"hide-input"
]
},
"outputs": [],
"source": [
"# @title Plotting functions\n",
"# @markdown"
]
},
{
"cell_type": "markdown",
"id": "808d728a",
"metadata": {
"execution": {},
"jp-MarkdownHeadingCollapsed": true
"execution": {}
},
"source": [
"## Helper functions"
Expand Down Expand Up @@ -526,8 +497,9 @@
" torchvision.transforms.Normalize((0.1307,), (0.3081,)) # Normalize the images with mean and standard deviation\n",
"])\n",
"\n",
"# Load the MNIST test dataset with the defined transformations\n",
"test_dset = torchvision.datasets.MNIST(\"./\", train=False, transform=mnist_transforms, download=True)\n",
"with contextlib.redirect_stdout(io.StringIO()):\n",
" # Load the MNIST test dataset with the defined transformations\n",
" test_dset = torchvision.datasets.MNIST(\"./\", train=False, transform=mnist_transforms, download=True)\n",
"\n",
"# Calculate the height and width of the MNIST images (28x28)\n",
"height = int(784**0.5)\n",
Expand Down
Binary file modified tutorials/W1D2_ComparingTasks/static/W1D2_Tutorial2_Solution_39154423_0.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading

0 comments on commit 482c904

Please sign in to comment.