search

tryolabs / luminoth

Deep Learning toolkit for Computer Vision.
https://tryolabs.com
BSD 3-Clause "New" or "Revised" License
2.4k stars 399 forks source link

inconsistent model declaration ? #188

Open ghost opened 6 years ago

ghost commented 6 years ago

I want to bring to attention, the following code snippet -

https://github.com/tryolabs/luminoth/blob/master/luminoth/models/base/base_network.py#L69-L101

In the above snippet

  1. vgg_16 is declared without specifying num_classes meaning it gets built with the default value of 1000. It does not matter as we do not use the fully connected layers.

  2. resnet_v1 is declared with num_classes=None. As specified in the slim documentation, it does not build fully connected layers. This is quite fine.

  3. resnet_v2 is declared with num_classes=self._config.get('num_classes'). Now this is perplexing because num_classes=None was equally fine according to slim documentation.

This inconsistency puts to confusion someone trying to extend luminoth to new networks. Is this an inconsistency, or is it deliberate ?

joaqo commented 6 years ago

Hey @calledbymountains thanks for spotting this. You are quite right, this is an inconsistency on our part. We'll fix it ASAP.

Cheers!