Chris Tegho

For how long did you train it for? Also reducing the batch size that much for 512x512 images will unlikely produce good results, even if you increase the gradient accumulations,...

any reason you used `depthwise_conv2d` instead of `con2d`?

This is my TF implementation, though not for tf 2.0 ``` def blur_pool(inp, pad_type='reflect', filter=3, stride=2, pad_off=0): def pad(inp, pad_sizes, pad_type): return tf.pad(inp, paddings=pad_sizes, mode=pad_type) pad_sizes = [int(1.*(filter-1)/2), int(np.ceil(1.*(filter-1)/2)), int(1.*(filter-1)/2),...

Hi Michael, Thanks for sharing your trained base model. This is very helpful! On Mon, Dec 2, 2019 at 9:05 AM Michael wrote: > You could try my trained base...

I had the same issue, so I switched to PyTorch 0.3.1 but now I get ``` import torch.utils.checkpoint as cp ImportError: No module named checkpoint ``` @DL-Alva Were you able...

This ended up working, although not sure what I did to resolve the issue. I did install torchvision==0.4.2, and installed torch 0.4.0 then reinstalled torch 0.3.1.

I am running into the same problem. The following function call: ``` var vid = new cv.VideoCapture('test.avi') ``` is giving this error `Error: Video file could not be opened (opencv...