GPH
Thank you very much for your adacof.py algorithm. When I use it in my work, the forward computing is fine, however, when calling `loss.backward()`, I met the following errors: ```python...
In the code, the optimizer is Adam. I trained it for a long time but the loss is around 8 and MAP is around 0.06. This is frustrateing. It is...
Dear uoip: First of all, thanks for your work very much. You write a python wrapper for KCFcpp. I want to make use of it. But I have a question...
is there something wrong or How to process the output of FT
When i running command : `python yolo_main.py -m prototxt/yolo_tiny_deploy.prototxt -w weights/yolo_tiny.caffemodel -i images/cat.jpg` I met error below: `F0220 18:45:25.861762 19763 net.cpp:767] Check failed: target_blobs.size() == source_layer.blobs_size() (1 vs. 2) Incompatible...
Fix the download_models function to download models in the correct directories and names.
Sir， can you include the MOVIE metric? The related paper is "Motion Tuned Spatio-Temporal Quality Assessment of Natural Videos". And I found a related repo [here](https://github.com/LongguangWang/Video-Quality-Assessment). Thanks!
Please support multi-gpu training and tensorboard, it would be great!
Hi, I found most models are trained in "eps" mode. And I wonder if there are models trained in "x0" mode or not. This helps me a lot, thanks!