# How can I get the batch shape in a Model class? **URL:** \ **Category:** data\ **Created:** [June 13, 2022, 9:01am UTC](https://discuss.pytorch.org/t/how-can-i-get-the-batch-shape-in-a-model-class/153973 "2022-06-13T09:01:11Z")\ **Posts on this page:** 6\ **Page:** 1
**Author:** ![IneedMrmeeseeks](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ineedmrmeeseeks/32/50491_2.png) [@IneedMrmeeseeks](https://discuss.pytorch.org/u/IneedMrmeeseeks)\ **Post date:** [June 13, 2022, 9:01am UTC](https://discuss.pytorch.org/t/how-can-i-get-the-batch-shape-in-a-model-class/153973/1 "2022-06-13T09:01:11Z")
This question is more like basic python Class question I think.(If this question is not belong here, plz let me know) I am trying to build a simple conditional GAN model. I created my own custom Dataset class and collate\_fn which is fed to DataLoader class. I customized those since input data has varying shape. Thankfully, I followed [this solution](https://discuss.pytorch.org/t/how-to-create-a-dataloader-with-variable-size-input/8278/2) using rnn.pad\_sequence function in order to padding **within each batches**.(thx to @jdhao and @pinocchio) ```auto n_epochs = 100 for epoch in range(n_epochs): for batch_idx, (data_input, labels) in enumerate(data_loader): print(data_input.size()) ``` Above code gives me the output looks like the following one. ```auto torch.Size([10, 86, 408]) torch.Size([10, 105, 408]) torch.Size([10, 110, 408]) torch.Size([10, 87, 408]) torch.Size([10, 76, 408]) torch.Size([10, 44, 408]) torch.Size([10, 54, 408]) torch.Size([10, 52, 408]) torch.Size([10, 89, 408]) torch.Size([10, 59, 408]) torch.Size([10, 60, 408]) torch.Size([10, 43, 408]) ``` So you can see that first one is the batch length, but the second varying number represents zero-padded input. The problem is that I need to get these second number inside Generator class. ```auto class Generator(nn.Module): def __init__ (self): super(Generator, self). __init__ () self.label_emb = nn.Embedding(n_class, n_class) self.model = nn.Sequential( nn.Linear(latent_dim + n_class, 256), nn.LeakyReLU(0.2, inplace= True), nn.Linear(256, 512), nn.LeakyReLU(0.2, inplace= True), nn.Linear(512, 1024), nn.LeakyReLU(0.2, inplace= True), nn.Linear(1024, int(dt_h * dt_w)), nn.Sigmoid() ) def forward(self, z, labels): gen_input = torch.cat((self.label_emb(labels), z), -1) tech = self.model(gen_input) tech = tech.view(batch_size, dt_h, dt_w) return tech ``` The **dt\_h** in the code is the one that should be replaced by the varying number. Any advice will be appriciated. Thanks! 🤜 🤛 ---
**Author:** ![AlphaBetaGamma96](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/a/3da27b/32.png) [@AlphaBetaGamma96](https://discuss.pytorch.org/u/AlphaBetaGamma96)\ **Post date:** [June 13, 2022, 11:43am UTC](https://discuss.pytorch.org/t/how-can-i-get-the-batch-shape-in-a-model-class/153973/2 "2022-06-13T11:43:00Z")
if `batch_size` and `dt_w` are of constant size, you can just replaced `dt_h` with `-1` and it will automatically select the right size. ---
**Author:** ![IneedMrmeeseeks](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ineedmrmeeseeks/32/50491_2.png) [@IneedMrmeeseeks](https://discuss.pytorch.org/u/IneedMrmeeseeks)\ **Post date:** [June 14, 2022, 12:29am UTC](https://discuss.pytorch.org/t/how-can-i-get-the-batch-shape-in-a-model-class/153973/3 "2022-06-14T00:29:10Z")
First, Thanks to the advice. I will give it a try. Just one thing in mind keep bothering me. Shouldn’t I write the code something like `self.data_input` and get the number with `self.data_input.size()[1]` inside the Generator class? 🤔 ---
**Author:** ![IneedMrmeeseeks](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ineedmrmeeseeks/32/50491_2.png) [@IneedMrmeeseeks](https://discuss.pytorch.org/u/IneedMrmeeseeks)\ **Post date:** [June 14, 2022, 3:15am UTC](https://discuss.pytorch.org/t/how-can-i-get-the-batch-shape-in-a-model-class/153973/4 "2022-06-14T03:15:48Z")
I get the idea of your advice since .view() is act like reshape in numpy. However What about the dt\_h in the last layer before the sigmoid activation? ---
**Author:** ![AlphaBetaGamma96](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/a/3da27b/32.png) [@AlphaBetaGamma96](https://discuss.pytorch.org/u/AlphaBetaGamma96)\ **Post date:** [June 14, 2022, 9:57am UTC](https://discuss.pytorch.org/t/how-can-i-get-the-batch-shape-in-a-model-class/153973/5 "2022-06-14T09:57:40Z")
You can indeed do something like `self.data_input.shape[1]` to get the same on-the-fly if you’d want to. The `-1` (as you said) is just to exploit reshaping and get pytorch to automatically select how many rows I can get if I specify the other dimensions. With regards to `dt_h` in the last `nn.Linear` module, I’m not too sure how to resolve that. I know there’s a `nn.LazyLinear` which takes arbitrary inputs but there’s no equivalent for outputs (documentation [here](https://pytorch.org/docs/stable/generated/torch.nn.LazyLinear.html)). You could do something along the lines of defining the final `nn.Linear` as 1024 inputs and the output as `110 * 408` (as 110 is the maximum output I see from your example output above), then you can just pad all outputs with zeros so they have the same shape. Perhaps, on the forum somewhere someone has asked about linear layers with variable outputs? ---
**Author:** ![IneedMrmeeseeks](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ineedmrmeeseeks/32/50491_2.png) [@IneedMrmeeseeks](https://discuss.pytorch.org/u/IneedMrmeeseeks)\ **Post date:** [June 15, 2022, 1:45am UTC](https://discuss.pytorch.org/t/how-can-i-get-the-batch-shape-in-a-model-class/153973/6 "2022-06-15T01:45:32Z")
Thanks for all the answers! you are the best! 🤗