An Error in my python code from PYtorch library
I spent much time to solve this error, but I failed. I ask for a help with this type of error as I cannot run my code.
OSError: [WinError 126] The specified module could not be found. Error loading “C:UsersMoetasemAppDataLocalPackagesPythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0LocalCachelocal-packagesPython311site-packagestorchlibshm.dll” or one of its dependencies.
In PyTorch, when the nn.linear operation only increases the shape size, the result is slightly changed. What’s wrong?
test = nn.Linear(1440, 1440, bias=False) hidden1 = torch.randn(100, 1440) hidden2 = torch.randn(400, 1440) output1 = test(hidden1) output2 = test(hidden2) If I test it as above, shouldn’t the output1 and output2[:100,:] parts be exactly the same? There are slightly different parts, do you know why? It should be the same as simple matmul calculation, but it […]
How to define a torchrl policy where the allowable actions depend on the environment state?
I’m training a model to play a particular card game (a variant of poker). At each player’s turn, the set of acceptable moves will be a set (possibly empty) of subsets of the cards they hold. I am encoding the current hand and the move as a vector of 52 bools.