1303463822
1303463822
in resnet.py, the ResNet101 uses basicblock with depthes = [3, 4, 23, 3] rather than bottleneck. Are there any errors?
when I run "python feature-extration.py --data_dir /home/lab/work/datasets/LFWA+ --save_feature feature.csv --save_label label.csv", it rises AttributeError: 'dict' object has no attribute 'has_key', it is caused by function "add_dtype_name" in mat73_to_pickle.py
Hello, I am trying to train FeatherNetB model, but I meet a problem. This is the error. Input image size: 224, test size: 224 + Number of FLOPs: 83.05M The...
Hello,How can I obtain RGB and depth images with only facial features?
I used your tutorial to train a homography-based LightGlue model. How should I modify the parameters to perform evaluation? Just like evaluating the official model with `python -m gluefactory.eval.megadepth1500 --conf...
Hello, I had a terrible result when training LightGlue based on xfeat, and during training I encountered the problem ]Detected NAN, skipping iteration 1249. Could you share your LightGlue training...