magic_zhang

Why the summary of dAps and bbox ap is not 100%?

4

 Why the sum of dAps and bbox ap is not 100%?

@implus 如题，按照我的理解，我将训练集1个epoch的regression_target保存了下来（shuffle设定为False），并可视化结果如下图所示。  感觉和论文中翔哥你展示的不一致。  我的做法是在gfl_head.py找那个将target_corners这个变量保存下来，然后画直方图，请问有什么问题吗？ ``` with open('./target_corners_results/{}.npy'.format(time.time()), 'wb') as f: np.save(f, target_corners.cpu().numpy()) ```

fix bugs when pos_inds.numel()=0, reg_targets_flatten and anchors_flatten is empty tensor. It will be wrong for some tensor operator in self.compute_centerness_targets function. For example the tensor operator "left_right.min(dim=-1)" the error info...

Direct download in browser is unstable. Could you offer a method by which we can download the data from the command line, e.g. wget?

2

Hi: Thank you for your datasets. Direct download in browser is unstable. Could you offer a method by which we can download the data from the command line, e.g. wget?...

@SeanNaren can you review this PR, it's essential to compile correctly against pytorch-1.12

Hi, every one, what is the mean of EFF-FT?

hello,everyone,I am using Resnet-50 to finetune my data.I have a question about BN layer param "use_global_stats". first,i learn that this param should be false when traing; when test should be...