Implemented SqueezeNet #37
Closed
Conversation
This file contains 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
|
I used DeepDream to see what the activations are picking up but there seems to be no visible/interesting patterns.
|
|
Oh wow, I forgot about deepdream. I'm going to keep this PR open til I apply deep dream to my latest models. We should definitely include deepdream in the standard code just to see what the network is seeing. |
|
I did not change any of your files. Except the |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
The implemented SqueezeNet model is 2MB in size because tensorflow uses 32bit floats. The forward pass is .72 GFLOPs. This would really help people who have a less beefier PC.
I dont remember which car I trained on because I had to keep changing them as the AI kept crashing them.
It seems to like to drive up the mountain in the same place where your model liked to drive up too.
It did ok-ish in a tunnel although I did not give it any training data on tunnels.
All training data was shot in midday. It did not have a noticable drop in performance as the sun started to set.
The training on 45MB dataset (1000 epochs, 64 batch size) took about 15 mins on my 930MX.