tensorflow 1.1 and tensorflow/models workarounds

warmspringwinds / tf-image-segmentation

Image Segmentation framework based on Tensorflow and TF-Slim library

MIT License

549 stars 188 forks source link

tensorflow 1.1 and tensorflow/models workarounds #20

Closed ahundt closed 7 years ago

ahundt commented 7 years ago

If you're running resnet with the latest tensorflow and tensorflow/models you will need the following: https://github.com/tensorflow/models/pull/1447

I plan to update this with additional info for running on tensorflow 1.1

BrianOn99 commented 7 years ago

With this commit, should we specify spatial_squeeze=False in tf_image_segmentation/models/resnet_v1_101_8s.py?

ahundt commented 7 years ago

They've merged the fix. Yes spatial_squeeze=False because that would reduce the number of output dimensions and we are making predictions with the same dimensions as the input.