anxu829

hello , i am confusing about your fomular for calculation of d , which use r*r . may i ask the relationship and prof of r and d?.thank you!

tiny bugs in oriented rcnn implementation

1

https://github.com/open-mmlab/mmrotate/blob/main/mmrotate/models/dense_heads/oriented_rpn_head.py#L279 this line should be 6 instead of 5 :)

我最近在做这方面的学习，但是我没有找到有中国人手写数字数据的相关的信息，想问下您这边可以共享一下么

will you release any pretrained model?

3

thank you for your open source code will you release your pretrain model trained by this repo?

bugs when calculating iou between gt and boxes ?

1

here is your code in function box_overlap_ignore_opr: ```python3 area_box = (box[:, 2] - box[:, 0] + 1) * (box[:, 3] - box[:, 1] + 1) area_gt = (gt[:, 2] -...

can not pruning following network with two continuous convolution block

1

```python class StrangeNet(nn.Module): def __init__(self): super().__init__() self.conv1 = nn.Conv2d(3,256,kernel_size=3) self.bn = nn.BatchNorm2d(256,256) self.conv2_1 = nn.Conv2d(256,128 , kernel_size=3) self.conv2_2 = nn.Conv2d(128,128 , kernel_size=3 ) self.bn2 = nn.BatchNorm2d(128 ) def forward(self, x):...