Skip to content

Conversation

cnuahs
Copy link

@cnuahs cnuahs commented Mar 23, 2019

Step 7 in the instructions for the LeNet challenge suggests that
the third convolution operation (conv_3) should contain 125 filters
while the comment in the code block indicates it should have 120
filters. Adding 125 filters will work, producing comparable
results/model performance. However, the subsequent visualisation
of the activation or feature maps for layer3 will fail when the
subplot index exceeds 120.

This change simply corrects the challenge instructions to be
consistent with the code comments and subsequent visualisation
to avoid confusion.

Step 7 in the instructions for the LeNet challenge suggests that
the third convolution operation (conv_3) should contain 125 filters
while the comment in the code block indicates it should have 120
filters. Adding 125 filters will work, producing comparable
results/model performance. However, the subsequent visualisation
of the activation or feature maps for layer3 will fail when the
subplot index exceeds 120.

This change simply corrects the challenge instructions to be
consistent with the code comments and subsequent visualisation
to avoid confusion.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant