Open HYJJJJJJJJ opened 3 years ago
可以试试x = self.segmental_consensus.forward(x), 或者是具体调用segmental_consensus里的某个子模型, 我遇到相似的问题是这么解决的
I have the same issue,how did you solve it?
I have the same issue,how did you solve it?
I solved this problem whit this link https://github.com/decisionforce/TPN/pull/30/commits/b02523d94d39f4439bc081d8097c054ca010d6ce
@784682065 这个回答暂时解决了我的问题
运行环境:
背景&现象:
由于Pytorch 1.3以下版本,不支持CUDA11,无法兼容30系GPU,所以使用了Pytorch1.7,运行demo时,输出如下错误:
了解到在pytorch1.3及以后的版本需要规定forward方法为静态方法,给TPN/mmaction/models/tenons/segmental_consensuses/simple_consensus.py 中的forward方法加上静态修饰,报错: