带佬我明白了,需要self.kImageSize>>>>self.env.kImageSize,self.kFinaImageSize>>>>self.env.kFinaImageSize才可以。
还有一点不明白的地方,运行eval/kuka_reach_with_visual.py时,发现报错:
Traceback (most recent call last):
File "/home/zzz/guyueclass/machine_learning/deep_reinforcement_learning_grasping/drlgrasp/eval/kuka_reach_with_visual.py", line 12, in
actions = ac.act(torch.as_tensor(obs, dtype=torch.float32))
File "/home/zzz/anaconda3/envs/tensorflow/lib/python3.7/site-packages/torch/nn/modules/module.py", line 591, in __getattr__
type(self).__name__, name))
AttributeError: 'CNNGaussianActor' object has no attribute 'act'
翻了一下代码,发现act只在cpu版本的core.py中存在,而core_gpu.py里的CNNGaussianActor类中找不到act,请问这该怎么解决呢?谢谢您~
展示全文
第三方账号登入
QQ 微博 微信