dangao250

Results 15 issues of


                                            dangao250

train_net.py 问题

9

comment

![image](https://user-images.githubusercontent.com/44044170/68527251-e5a6ba00-031f-11ea-88d1-9959dc7ec90a.png)

generate_frames

5

comment

![image](https://user-images.githubusercontent.com/44044170/68441483-37105580-0209-11ea-9fff-cc6fda708c57.png)

command = ["ffmpeg", "-i", filename, "q:v", "1", "-r", str(fps), outfile]

Why does this statement not generate the image frame of the corresponding video after execution

No such file or directory: 'F:/lianxi/R-C3D.pytorch-master/thumos14_database/Training Data/THUMOS14/annotation_val\\BaseballPitch_val.txt' 请问怎么解决 #1

请问你2s-AGCN是图卷积操作的采样方式与ST-GCN的方式相同为什么你代码里没有在预处理将关节点进行分组呢

1

comment

Can AAGCN's attention explain why convolution can be used and the residual operation code is not reflected. Can you talk about the process? Why does the paper here say that it is a feature map, an attention map, and a graph convolution operation.

AAGCN的注意力可以解释一下吗为什么能用卷积而且还有残差操作代码没有体现啊可以说一下流程吗为什么这里论文会说是特征图注意力图图卷积操作有这些的存在吗

I would like to ask why the accuracy rate does not reach what the literature says. I am 16 is different. . . . Is there any solution?

预处理数据问题

8

comment

![image](https://user-images.githubusercontent.com/44044170/68771473-0a25cd80-0663-11ea-815c-45e61581fc8c.png)

预处理数据问题

4

comment

![image](https://user-images.githubusercontent.com/44044170/68832841-f2932700-06ec-11ea-8a35-631ac6ca72d6.png)

1
2
›