Mohit Jain

I created a custom model using Google Vision API and the expected input size for that model was 512x512 as opposed to the 300x300 in MobileSSDNet (default with TFLite example)....

@notimesea Does the `cudnn.convert()` method work if we convert a GPU-based model to a CPU-based model using a machine which has GPU support and then load this converted model on...

@sunshineatnoon @paulinder I am trying to run Fast-RCNN with a customised region-proposal algorithm. It looks like @sunshineatnoon has deleted the fast-rcnn fork. I want to know what is the format...

Ah, turns out there was a stray entry in my train.txt file causing the Assertion error. My .mat format was indeed correct - for anyone else who might stumble on...

Still looking for this answer. Any updates @acpn @ssakhavi @nascimentocrafael ? It's quite weird that there's a lot of post discussing the 'changes' they made to the original script to...

For me the problem was solved by removing the cached .pkl files from ./data/cache/_train_gt.pkl

Strangely, the script runs fine if I pass one of the training snapshots instead of the final model hdf5 (eg. mlp_num_hidden_units_1024_num_hidden_layers_3_epoch_99.hdf5). @avisingh599 : Can you throw some light on this?

Instead of having to annotate and train on that data, can we simply load a configuration/parameter file (model) instead and test new data against it? A prebuilt NER engine, that's...