tzattack

I have my own MobileNet caffe model, and I encountered with the problem of custom layer of DepthWise Convolution. I saw you change your MobileNet model's dw_conv into group_conv, so...

I want to accelerate the inference process by predicting images in batch, how can I do it? I read your code to know you predict images by crop it several...

Could you please offer your testSet.txt for us to understand your code better?

add support to macOS GPU for inference

3

Use `torch.backends.mps.is_available()` to check whether GPU is available for PyTorch on macOS. Use `to.(xx.device)` to match op device for computing. Use `os.environ['PYTORCH_ENABLE_MPS_FALLBACK'] = '1'` to deal with operator 'aten::grid_sampler_3d' is...