Stephen Zhao

deeplabv3支持图片最大输入??

8

请问deeplabv3支持的最大图片输入宽高是多少?谢谢

I have run your code successfully.Could you add the coco.names in the code？Thank you very much.

the error of compute_iou in loss.py

2

def compute_iou(self,bbox1,bbox2): # 获取box1的第一个维度 N = bbox1.size(0) # 获取box2的第一个维度 M = bbox2.size(0) # Compute left-top coordinate of the intersections # lt = torch.max( # [N, 2] -> [N, 1, 2]...

I have read some source code about many edge detection network, all of the network are without BN layer, why was that?

docker image is better

1

detectron is difficult to install....

I have read some source code about many edge detection network, all of the network are without BN layer, why was that?

this network has different layer with different learning rate, why was that?

python version

2

I am not very familiar with cpp, does python version of this algorithm exist? Thx for your help, looking forward to your response.

Traceback (most recent call last): File "voc_to_coco.py", line 166, in get_filename_as_int return int(filename) ValueError: invalid literal for int() with base 10: '000609af' During handling of the above exception, another exception...

非常期待作者复现一些NLP领域、视频理解领域的一些优秀作品