Chintak Sheth

Yes, still the same error. Tried with `'schedule': { 0: 0.0005, 150: 0.00005, 201: 'stop', }` as well.

Also while running the previous `convert.py` commands there were quite a few files for which "box could not be found" or "box too small" were outputted. In such cases, what...

``` /home/ubuntu/dataset/kaggle_diabetic/solution/src/lasagne-master/lasagne/init.py:86: UserWarning: The uniform initializer no longer uses Glorot et al.'s approach to determine the bounds, but defaults to the range (-0.01, 0.01) instead. Please use the new GlorotUniform...

Ok. Output for `pip list`: ``` click (3.3) decorator (4.0.6) funcsigs (0.4) ghalton (0.6) joblib (0.9.3) Lasagne (0.1.dev0, /home/ubuntu/dataset/kaggle_diabetic/solution/src/lasagne-master) matplotlib (1.4.3) mock (1.3.0) networkx (1.10) nolearn (0.6a0.dev0, /home/ubuntu/dataset/kaggle_diabetic/solution/src/nolearn-master) nose (1.3.7)...

Any other changes I can try?

AWS G2 instance which has GRID K520 GPU with CUDA 7.0 and cuDNN v3.0. Nope, the problem still persists.

Yep, I had tried that in the beginning. It's "nan" for the first batch itself.

Yes, I did a fresh install, preprocessed the images again and then ran the train_nn.py for all the given config files - I get "non finite loss" in the very...

Nope. After a few days I'll try and test it on another system.