Phillip Wang

Installation error: [WinError 126] The specified module could not be found

1

Hi, trying to set this up on Windows 10 on Python 3.7.4. This is my stacktrace/process for installing openvr: ``` PS C:\Users\phill> pip install openvr Collecting openvr Using cached https://files.pythonhosted.org/packages/80/40/0d5fa1efaf9e3b85bc95c799022d526108adf4bb29e2623aeb68ed778cb5/openvr-1.5.1701.tar.gz...

fonts arent showing

1

Awesome bar! Could you elaborate on how to get font awesome to work? I've installed it and dropped it into the fontbook, and it seems like it installed correctly (if...

Addresses #5

iter_size in original caffe implementation

1

In the solver.prototxt of the original implementation, `iter_size: 10` specifies that gradient updates only happen every 10 batches. However, the training script here doesnt do such a thing

https://github.com/chenxi116/TF-deeplab/blob/439c872b3d9178d4f28731b25e635c01882193b5/deeplab_model.py#L163 The default end_learning_rate is 0.0001 (https://www.tensorflow.org/api_docs/python/tf/train/polynomial_decay). However, according to https://stackoverflow.com/questions/30033096/what-is-lr-policy-in-caffe/30045244, the default caffe behavior is end_learning_rate=0.