Dipankar Nandi
Dipankar Nandi
Actually, I have a JSON file (person_keypoints_scenario) that includes keys like file name, image shape, ID, bbox, and also key points. From this file, I omitted the file name and...
> Hi, author, what's the difference between this repo with the torchvision DCN op. https://pytorch.org/vision/stable/_modules/torchvision/ops/deform_conv.html The previous versions of DCNv2 in dcn_v2_cuda.cu use THCUDA which causes errors during setup.py. This...
You can install the latest version of every library and work around accordingly.
This error occurs when the code is unable to locate your image file. I encountered this when using my own dataset. The best way to sort this out is to...
Could you clarify how did you successfully build the DCNv2? I am encountering an error of ‘THFloatBlas_gemv’ was not declared in this scope; did you mean ‘THFloatBlas_swap’? It would be...
these are heatmaps and set of coordinate values
In DCVn2, you will find an "ext" file! Change the name of that file to _ext.so This should resolve the issue for you. It worked for me!
Did you install the DCNv2 as mentioned in the install.md??
I recently solved this and evaluated only the 13 key points leaving behind the eyes and the ears as per my application. Just open the cocoeval.py under pycocotools, then head...
@Andreahernandezt It would be great if you can share the procedure for training on your custom dataset. Apart from editing the configuration files, what other are important factors? If you...