# Which parameter is pass in view function? **URL:** \ **Category:** Uncategorized\ **Created:** [March 1, 2019, 3:48pm UTC](https://discuss.pytorch.org/t/which-parameter-is-pass-in-view-function/38655 "2019-03-01T15:48:55Z")\ **Posts on this page:** 12\ **Page:** 1
**Author:** ![MisBah\_Awan](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/m/e480ec/32.png) [@MisBah\_Awan](https://discuss.pytorch.org/u/MisBah_Awan)\ **Post date:** [March 1, 2019, 3:48pm UTC](https://discuss.pytorch.org/t/which-parameter-is-pass-in-view-function/38655/1 "2019-03-01T15:48:55Z")
i want to ask u,pass hidden layer or input layer in view function?`(x.view(-1,64))` and i am randomly choose the hidden layer and input layers? where as i have 3064 images with 512x512 dimensions. i am asking about this: ```auto self.fc1 = nn.Linear(262144, 64) self.fc2 = nn.Linear(64, 3) #self.fc3 = nn.Linear(84, 10) def forward(self, x): x = self.pool(F.relu(self.conv1(x))) x = self.pool(F.relu(self.conv2(x))) x = x.view(-1,64) ``` ---
**Author:** ![ptrblck](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ptrblck/32/1823_2.png) [@ptrblck](https://discuss.pytorch.org/u/ptrblck)\ **Post date:** [March 2, 2019, 12:14am UTC](https://discuss.pytorch.org/t/which-parameter-is-pass-in-view-function/38655/2 "2019-03-02T00:14:31Z")
Usually you use a line of code like `x = x.view(-1, 64)` to create a new view of the tensor `x`, so that for example you can feed the output of a conv layer into a linear layer. What exactly would you like to know? Currently the code snippet seems to be missing some important parts. Do you have trouble implementing some architecture? ---
**Author:** ![MisBah\_Awan](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/m/e480ec/32.png) [@MisBah\_Awan](https://discuss.pytorch.org/u/MisBah_Awan)\ **Post date:** [March 2, 2019, 5:48am UTC](https://discuss.pytorch.org/t/which-parameter-is-pass-in-view-function/38655/3 "2019-03-02T05:48:05Z")
here is full code have a look: ```auto class Net(nn.Module): def __init__ (self): super(Net, self). __init__ () self.conv1 = nn.Conv2d(3, 32, 3) self.pool = nn.MaxPool2d(2, 2) self.conv2 = nn.Conv2d(32, 64, 3) self.fc1 = nn.Linear(262144,1500) self.fc2 = nn.Linear(1500, 3) #self.fc3 = nn.Linear(84, 10) def forward(self, x): x = self.pool(F.relu(self.conv1(x))) x = self.pool(F.relu(self.conv2(x))) #x = x.view(x.size(0), -1) #output = Net(x) x = x.view(-1,262144) x = F.relu(self.fc1(x)) #x = F.relu(self.fc2(x)) x = self.fc2(x) return x ``` ---
**Author:** ![ptrblck](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ptrblck/32/1823_2.png) [@ptrblck](https://discuss.pytorch.org/u/ptrblck)\ **Post date:** [March 2, 2019, 11:32am UTC](https://discuss.pytorch.org/t/which-parameter-is-pass-in-view-function/38655/4 "2019-03-02T11:32:07Z")
Currently the number of input features to `fc1` is set as `512*512=262144`, which won’t work in this architecture. Note that you are using pooling layers, which decrease the spatial size with a factor of 2 in your setup. Also you are not using any padding in the conv layers, which will reduce the spatial size by 2 pixels using a kernel size of 3. Here is the working and annotated model: ```python class Net(nn.Module): def __init__ (self): super(Net, self). __init__ () self.conv1 = nn.Conv2d(3, 32, 3) self.pool = nn.MaxPool2d(2, 2) self.conv2 = nn.Conv2d(32, 64, 3) self.fc1 = nn.Linear(64*126*126,1500) self.fc2 = nn.Linear(1500, 3) def forward(self, x): x = self.pool(F.relu(self.conv1(x))) # output size: [batch_size, 32, 255, 255] x = self.pool(F.relu(self.conv2(x))) # output size: [batch_size, 64, 126, 126] x = x.view(x.size(0), -1) # output size: [batch_size, 64*126*126] x = F.relu(self.fc1(x)) x = self.fc2(x) return x x = torch.randn(1, 3, 512, 512) model = Net() output = model(x) ``` ---
**Author:** ![MisBah\_Awan](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/m/e480ec/32.png) [@MisBah\_Awan](https://discuss.pytorch.org/u/MisBah_Awan)\ **Post date:** [April 29, 2019, 4:55pm UTC](https://discuss.pytorch.org/t/which-parameter-is-pass-in-view-function/38655/5 "2019-04-29T16:55:04Z")
kindly tell me the formula. how to find the the input layers? ---
**Author:** ![ptrblck](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ptrblck/32/1823_2.png) [@ptrblck](https://discuss.pytorch.org/u/ptrblck)\ **Post date:** [April 30, 2019, 6:32am UTC](https://discuss.pytorch.org/t/which-parameter-is-pass-in-view-function/38655/6 "2019-04-30T06:32:45Z")
The output sizes are beautifully explained in Stanford’s [CS231n](http://cs231n.github.io/convolutional-networks/). In my architecture each conv layer will reduce the spatial size by two in both dimensions, while the pooling layers will divide them by two. For an input size of `[batch_size, 3, 512, 512]` you will end up as: ```auto conv1: 512 - 2 = 510 pool: 510 / 2 = 255 conv2: 255 - 2 = 253 pool: 253 / 2 = 126 (floor) ``` ---
**Author:** ![adarsh\_pandey](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/adarsh_pandey/32/14907_2.png) [@adarsh\_pandey](https://discuss.pytorch.org/u/adarsh_pandey)\ **Post date:** [December 24, 2019, 8:31am UTC](https://discuss.pytorch.org/t/which-parameter-is-pass-in-view-function/38655/7 "2019-12-24T08:31:00Z")
@ptrblck what are the parameters taken by the view() function please explain… Thanking You, ---
**Author:** ![ptrblck](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ptrblck/32/1823_2.png) [@ptrblck](https://discuss.pytorch.org/u/ptrblck)\ **Post date:** [December 24, 2019, 9:07am UTC](https://discuss.pytorch.org/t/which-parameter-is-pass-in-view-function/38655/8 "2019-12-24T09:07:24Z")
`.view` takes the desired shape as the input arguments. E.g. `x.view(x.size(0), -1)` flattens the tensor while keeping the batch dimension intact. As the name suggests, you will get a view of the tensor, so that no copy will be performed, but rather just the strides and shape will be charged. ---
**Author:** ![adarsh\_pandey](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/adarsh_pandey/32/14907_2.png) [@adarsh\_pandey](https://discuss.pytorch.org/u/adarsh_pandey)\ **Post date:** [December 24, 2019, 9:10am UTC](https://discuss.pytorch.org/t/which-parameter-is-pass-in-view-function/38655/9 "2019-12-24T09:10:40Z")
@ptrblck can we innput anything other then then -1 as the second argument … ---
**Author:** ![ptrblck](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ptrblck/32/1823_2.png) [@ptrblck](https://discuss.pytorch.org/u/ptrblck)\ **Post date:** [December 24, 2019, 9:14am UTC](https://discuss.pytorch.org/t/which-parameter-is-pass-in-view-function/38655/10 "2019-12-24T09:14:34Z")
Sure, the `-1` just means that PyTorch should automatically fill up this dimension, so that the number of elements stay the same. You could of course specify is manually: ```python x = torch.arange(10) y = x.view(2, 1, 5) ``` ---
**Author:** ![adarsh\_pandey](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/adarsh_pandey/32/14907_2.png) [@adarsh\_pandey](https://discuss.pytorch.org/u/adarsh_pandey)\ **Post date:** [December 24, 2019, 9:17am UTC](https://discuss.pytorch.org/t/which-parameter-is-pass-in-view-function/38655/11 "2019-12-24T09:17:35Z")
@ptrblck that means the second argument means the size to which we want to reshape ??? also how does PyTorch automatically fills up this dimension?? ---
**Author:** ![ptrblck](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ptrblck/32/1823_2.png) [@ptrblck](https://discuss.pytorch.org/u/ptrblck)\ **Post date:** [December 24, 2019, 9:55pm UTC](https://discuss.pytorch.org/t/which-parameter-is-pass-in-view-function/38655/12 "2019-12-24T21:55:04Z")
No, each passed value results in the desired shape of the new view on this tensor. Have a look at [this post](https://discuss.pytorch.org/t/contigious-vs-non-contigious-tensor/30107/2) for some additional information. It’s more focused on the `contiguous` call, however it might also give you a better idea about the `view` operation.