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.

Sign up for GitHub

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

Jump to bottom

Only using 3/4 resnet50 stages by choice? #11

Open

cgebbe opened this issue Feb 26, 2021 · 0 comments

cgebbe commented Feb 26, 2021

According to https://github.com/lattice-ai/DeepLabV3-Plus/blob/master/deeplabv3plus/model/backbones.py#L7 you use as your backbone features for resnet50

    'feature_1': 'conv4_block6_2_relu',

```
    'feature_2': 'conv2_block3_2_relu'
```

This would mean that you are using only three out of the four resnet stages, see naming scheme of https://github.com/tensorflow/tensorflow/blob/v2.4.1/tensorflow/python/keras/applications/resnet.py#L468

Is this intended? If so, why?

The text was updated successfully, but these errors were encountered:

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment