pku-rl / endi Goto Github PK

"Traceback (most recent call last):
File "train.py", line 330, in
train(args)
File "train.py", line 134, in train
action1 = ppo1.policy_old.act(buffer1.get_obs(), text, memory1)
File "g:\a_phd_learning\ABM\EnDi\endi_messenger\model.py", line 227, in act
labor_weights = self.labor_weight(labor_weights.permute(2, 0, 1))
File "H:\Anaconda\envs\lavis\lib\site-packages\torch\nn\modules\module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "H:\Anaconda\envs\lavis\lib\site-packages\torch\nn\modules\conv.py", line 446, in forward
return self._conv_forward(input, self.weight, self.bias)
File "H:\Anaconda\envs\lavis\lib\site-packages\torch\nn\modules\conv.py", line 442, in _conv_forward
return F.conv2d(input, weight, bias, self.stride,
RuntimeError: Expected 4-dimensional input for 4-dimensional weight[2, 4608, 3, 3], but
got 3-dimensional input of size [4608, 10, 10] instead "