Skip to content

Add LeNet Implementation in PyTorch #7070

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 14 commits into from
Apr 7, 2023
Merged
Show file tree
Hide file tree
Changes from 10 commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
73 changes: 73 additions & 0 deletions computer_vision/lenet_pytorch.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,73 @@
"""
LeNet Network

Paper: http://vision.stanford.edu/cs598_spring07/papers/Lecun98.pdf
"""

import numpy
import torch
import torch.nn as nn


class LeNet(nn.Module):
def __init__(self) -> None:
super().__init__()

self.tanh = nn.Tanh()
self.avgpool = nn.AvgPool2d(kernel_size=2, stride=2)

self.conv1 = nn.Conv2d(
in_channels=1,
out_channels=6,
kernel_size=(5, 5),
stride=(1, 1),
padding=(0, 0),
)
self.conv2 = nn.Conv2d(
in_channels=6,
out_channels=16,
kernel_size=(5, 5),
stride=(1, 1),
padding=(0, 0),
)
self.conv3 = nn.Conv2d(
in_channels=16,
out_channels=120,
kernel_size=(5, 5),
stride=(1, 1),
padding=(0, 0),
)

self.linear1 = nn.Linear(120, 84)
self.linear2 = nn.Linear(84, 10)

def forward(self, image_array: numpy.ndarray) -> numpy.ndarray:
image_array = self.tanh(self.conv1(image_array))
image_array = self.avgpool(image_array)
image_array = self.tanh(self.conv2(image_array))
image_array = self.avgpool(image_array)
image_array = self.tanh(self.conv3(image_array))

image_array = image_array.reshape(image_array.shape[0], -1)
image_array = self.tanh(self.linear1(image_array))
image_array = self.linear2(image_array)
return image_array


def test_model() -> bool:
"""
Test the model on a random input of size [64, 1, 32, 32]

>>> test_model()
True

"""
random_image = torch.randn(64, 1, 32, 32)
model = LeNet()
output = model(random_image)

return output.shape == torch.zeros([64, 10]).shape


if __name__ == "__main__":
print(f"Model Passed: {test_model()}")
1 change: 1 addition & 0 deletions requirements.txt
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@ statsmodels
sympy
tensorflow
texttable
torch
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Do I need to do anything about this?

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The only thing we can do is wait until torch is compatible with the current version of Python.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Okay, after it is compatible this PR will be automatically merged?

tweepy
xgboost
yulewalker