Manu Mathew
Manu Mathew
Thank you for this good work. Could you please add a licence file? May be the same license file as caffe: https://github.com/BVLC/caffe/blob/master/LICENSE
Is there a plan to support RetinaNet? The accuracy of RetinaNet seems to be higher compared to SSD according to the RetinaNet paper. Thanks,
Do you have any thoughts about integrating FlowNet2 into this repository? FlowNet2 models (including the custom operations such as correlation) have become available for PyTorch 0.3, Python 3.x. https://github.com/vt-vl-lab/pytorch_flownet2 https://github.com/hellock/flownet2-pytorch...
Looking throughh the source code for torch.nn.CrossEntropyLoss(), it seems to be doing log_softmax inside it. The model is also doing a log_softmax at the end. Isn't this a duplicate? Is...
I have an interesting observation. If I add a few Crop layers to the mobilenet model, it becomes quite slow - more than 3x slower. I have a multi GPU...
Hi, I found your flops benchmark quite useful. Is it possible to add a license file to your project, (may be similar to the one you have used in another...
* Building on Ubuntu 18.04 may face some road blocks - but they are solvable. The exact solution may vary slightly depending on the packages in your system. The following...
There is a bug in the reading of Batch Norm weights that cause some models to produce incorrect results. These are example models that produce incorrect results: https://github.com/cvjena/cnn-models/tree/master/ResNet_preact **Solution**: This...
Hi, When using the st_canvas examples in this repository with background images, there seems to be an issue. When the example is loaded, the background image becomes visible, then it...
Hi, This interesting work - I would like to try it. Is it possible for you add a license file - probably something similar to this? https://github.com/pytorch/vision/blob/master/LICENSE