Qi Cai

Thanks!

@yuvaltassa I am aslo interested in dynamically adding new objects into the scenes while simulating. For example, at each step, place a new box into the scenes while keeping the...

@yuvaltassa Thanks, I will have a try!

Yes, it's vgg reduced 300. If the current version is broken, can I get the results with the repo before commit https://github.com/zhreshold/mxnet-ssd/commit/6f517aa1818c0ac37c1ddb8ed1858b6d9e49551a ? This commit seems change a lot of...

@xioryu Thank you very much. I originally thought of getting different size of images in different batches for batch size ==1 like that in Faster R-CNN to resize images with...

Thanks! Setting offscreen_only = True does not work for me. My environment is: 4 V100 GPUs and CUDA_VISIBLE_DEVICES not set.  When the script is: ``` python import sapien print(sapien.__version__)...

@CrazySssst hi, have you figured out why the offsets should be [2.5, 2.5, 10.5, 26.5, 90.5, 160.5]? I think at least offsets should be less than 1.0 for original ssd's...

@xwjabc I met the same problem and I'm not familiar with pytorch. But change this line https://github.com/gidariss/FewShotWithoutForgetting/blob/master/algorithms/FewShot.py#L55 to self.nKbase = nKbase.squeeze()[0].cuda() fix the problem.