Size Mismatch when passing a state batch to network

Question

Since I’m a beginner in ML, this question or the design overall may sound silly, sorry about that. I’m open to any suggestions.

I have a simple network with three linear layers one of which is output layer.

self.fc1 = nn.Linear(in_features=2, out_features=12)
self.fc2 = nn.Linear(in_features=12, out_features=16)
self.out = nn.Linear(in_features=16, out_features=4)

My states are consisting of two values, coordinate x and y. That’s why input layer has two features.

In main.py I’m sampling and extracting memories in ReplayMemory class and pass them to get_current function:

    experiences = memory.sample(batch_size)
    states, actions, rewards, next_states = qvalues.extract_tensors(experiences)

    current_q_values = qvalues.QValues.get_current(policy_net, states, actions)

Since a single state is consisting of two values, length of the states tensor is batchsize x 2 while length of the actions is batchsize. (Maybe that’s the problem?)

When I pass “states” to my network in get_current function to obtain predicted q-values for the state, I get this error:

size mismatch, m1: [1x16], m2: [2x12]

It looks like it is trying to grab the states tensor as if it is a single state tensor. I don’t want that. In the tutorials that I follow, they pass the states tensor which is a stack of multiple states, and there is no problem. What am I doing wrong? :)

This is how I store an experience:

memory.push(dqn.Experience(state, action, next_state, reward))

This is my extract tensors function:

def extract_tensors(experiences):
    # Convert batch of Experiences to Experience of batches
    batch = dqn.Experience(*zip(*experiences))

    state_batch = torch.cat(tuple(d[0] for d in experiences))
    action_batch = torch.cat(tuple(d[1] for d in experiences))
    reward_batch = torch.cat(tuple(d[2] for d in experiences))
    nextState_batch = torch.cat(tuple(d[3] for d in experiences))

    print(action_batch)

    return (state_batch,action_batch,reward_batch,nextState_batch)

Tutorial that I follow is this project's tutorial.

https://github.com/nevenp/dqn_flappy_bird/blob/master/dqn.py

Look between 148th and 169th lines. And especially 169th line where it passes the states batch to the network.

could you post your complete code? Also, link to the tutorial you are following might help? — rawwar, Nov 27 '19 at 14:39
one thing i would suggest you to do is put a debug point. Keep track of the variables you want and check if their shape is different than what you expected. — rawwar, Nov 27 '19 at 14:40
@InAFlash Full project of the tutorial is added. You can check the lines I mentioned. By the way, I'm a newbie in this area so I don't know what to expect really. For the start, I'm just following tutorials and only changing the environment (the game). — K.Yazoglu, Nov 27 '19 at 14:45
Does this answer your question? [RuntimeError: size mismatch m1: \[a x b\], m2: \[c x d\]](https://stackoverflow.com/questions/53828518/runtimeerror-size-mismatch-m1-a-x-b-m2-c-x-d) — prosti, Nov 27 '19 at 19:24

score 0 · Answer 1 · answered Nov 28 '19 at 18:33

0

SOLVED. It turned out that I didn't know how to properly create 2d tensor. 2D Tensor must be like this:

states = torch.tensor([[1, 1], [2,2]], dtype=torch.float)

answered Nov 28 '19 at 18:33

K.Yazoglu

207
3
13

Size Mismatch when passing a state batch to network

1 Answers1