Daniel Saez

Wrong modelview when using pip version

6

I am using eos 3D model to generate 2D depth maps. Initially, I used the python bindings compiled from source and everything worked fine. However, when using the version from...

Create local terminal when connected to remote

3

When I am using vscode remote I like to open a terminal in my local machine. Sometimes I need to open more than one since I want to ssh to...

Bad accuracy on MNIST dataset

5

Commit 2a4fe4be1ad7f2a6900408641d128e73469edbd8 made the accuracy on the MNIST dataset decrease from 6-7 degrees to 26-27 degrees. The version before that commit can be used as a workaround for now: https://github.com/d4nst/RotNet/tree/1d934ba4e810806d264cbbbb94d165515887988a

Add option to save standalone model

2

Added an additional option `--standalone-output-path` to `convert.py` to produce standalone models using TensorFlow's `freeze_graph` tool. It addresses #23. There is probably a cleaner way to do this, but I didn't...

Padding issue in GoogleNet

2

There is an issue when converting GoogleNet. Although the predicted labels seems to always be the same, the outputs when using Caffe and TensorFlow are different (in some cases the...