DenseNet and FC-DenseNet #2308
Closed
DenseNet and FC-DenseNet #2308
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Only implemented very simple tests for now. Tests run OK.
|
/cc @ikhlestov |
|
why closed? |
|
Can one of the admins verify this patch? |
ikhlestov
reviewed
Feb 28, 2018
| # We perform a first convolution. | ||
| # If DenseNet BC, first convolution has 2*growth_rate output channels | ||
| if bottleneck and compression < 1.0: | ||
| n_filters_first_conv = 2 * growth_rate |
There was a problem hiding this comment.
I think this behavior should be somehow be mentioned in the densenet method documentation.
| ##################### | ||
| pool_name = 'pool%d' % (n_dense + 1) | ||
| if dense_prediction: | ||
| net = slim.pool(net, [7, 7], pooling_type='AVG', scope=pool_name) |
There was a problem hiding this comment.
What if we have not 224x224 input? From my point of view we should use dynamic average pooling based on input shape.
| from __future__ import division | ||
| from __future__ import print_function | ||
|
|
||
| import numpy as np |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
7 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
I implemented slim models for DenseNet and FC-DenseNet, based on the original lasagne/theano code made available by the authors of FC-DenseNets. Hope it will be useful.
DenseNets for Semantic Segmentation - code