Dandan Shan

I have the same problem. This happens even using `image = torch.as_tensor(image.astype("float32").transpose(2, 0, 1)).requires_grad_(True)` Want to know how to solve this.

I solved my problem. Mine is caused by the layer_name. In my model, I use the X101_FPN model from detectron2 (https://github.com/facebookresearch/detectron2/blob/master/configs/COCO-Detection/faster_rcnn_X_101_32x8d_FPN_3x.yaml). The original code of this repo uses the last...

Have you solved the issue? Usually, it is related to building the environment. Could you try the steps carefully again? Otherwise, could you share the details about the issue?

Can you take a look and try this fix (https://github.com/jwyang/faster-rcnn.pytorch/issues/503) from [faster-rcnn.pytorch](https://github.com/jwyang/faster-rcnn.pytorch) and see if it works?

Hi, You can try to follow the steps in the demo section (https://github.com/ddshan/hand_object_detector#demo). It provides the command to run demo.py via passing the model checkpoint, image_dir (where the input images...

Hi, We only trained with batch size = 1 due to constraints of our modification on the codebase we followed. Sorry for the inconvenience. Will let you know if we...

Hi, Can you try cuda-10.0 in your home directory and see if it solves the problem since that is what we use. Besides, I highly recommend you to use conda...

Hi @jinfagang We have our data and annotation download instructions on our [website](http://fouheylab.eecs.umich.edu/~dandans/projects/100DOH/download.html). Please check and see if you need any help with the data. I am also happy to...