depthwise

FWIW, it'd be great to run a typical deep learning experiment queue on something like this. Upload code+configs to S3. Lambda picks up, stuffs it into a container, training runs...

The model is ShuffleNet V2, the dataset is Imagenet 1K. This isn't necessarily a bug, just wanted to bring this to author's attention. Feel free to close.

Metrics don't always improve, and columns show the _last_ value, not the _best_ one (AKA the only one the researcher actually cares about). The request is to display (and be...

Could someone suggest how to deal with data deps provided by `WORKSPACE`? Basically, I'd like to embed a deep learning model and then read it with TFLite from inside. TFLite...

Answering my own question after digging through the code some more: ```python pkgutil.get_data("__main__", "tflite_models/detect_float.tflite") ``` gets the data

The paper says this doesn't really benefit much from pretraining, FWIW