Ndtyjky

I am trying to resize an image in Pytorch for later processing, while training a neural network. But get a broadcasting error, when I try to call transforms.Resize() on the image.
Here is my code snippet.

cuda:0

Classifier(

  (fc1): Linear(in_features=784, out_features=256, bias=True)

  (fc2): Linear(in_features=256, out_features=128, bias=True)

  (fc3): Linear(in_features=128, out_features=64, bias=True)

  (fc4): Linear(in_features=64, out_features=10, bias=True)

)

Traceback (most recent call last):

  File "netz.py", line 71, in <module>

    train()

  File "netz.py", line 46, in train

    outputs=model(inputs)

  File "/home/yyyy/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 477, in __call__

    result = self.forward(*input, **kwargs)

  File "netz.py", line 18, in forward

    x=F.relu(self.fc1(x))

  File "/home/yyy/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 477, in __call__

    result = self.forward(*input, **kwargs)

  File "/home/yyy/anaconda3/lib/python3.7/site-packages/torch/nn/modules/linear.py", line 55, in forward

    return F.linear(input, self.weight, self.bias)

  File "/home/yyy/anaconda3/lib/python3.7/site-packages/torch/nn/functional.py", line 1024, in linear

    return torch.addmm(bias, input, weight.t())

RuntimeError: size mismatch, m1: [64 x 59536], m2: [784 x 256] at /opt/conda/conda-bld/pytorch_1532584813488/work/aten/src/THC/generic/THCTensorMathBlas.cu:249



---- Corresponding Code ---





import torch

from torch import nn,optim

import torch.nn.functional as F

from torchvision import datasets,transforms



NUM_EPOCH=700

class Classifier(nn.Module):



    def __init__(self):

        super().__init__()

        self.fc1=nn.Linear(784,256)

        self.fc2=nn.Linear(256,128)

        self.fc3=nn.Linear(128,64)

        self.fc4=nn.Linear(64,10)



    def forward(self,x):

        x=x.view(x.shape[0],-1)

        x=F.relu(self.fc1(x))

        x=F.relu(self.fc2(x))

        x=F.relu(self.fc3(x))

        x=F.log_softmax(self.fc4(x),dim=1)

        return x









def train():

    transform=transforms.Compose([

                    transforms.Resize(244),

                    transforms.ToTensor(),

                    transforms.Normalize((0.5,0.5,0.5),(0.5,0.5,0.5))])

    trainset=datasets.FashionMNIST('./data',download=True,transform=transform)

    trainloader=torch.utils.data.DataLoader(trainset,batch_size=64,shuffle=True,num_workers=2)

    model=Classifier()

    model=model.to(device)

    criterion=nn.CrossEntropyLoss()

    optimizer=optim.Adam(model.parameters(),lr=0.001)



    for epoch in range(NUM_EPOCH):

        running_loss=0.0

        for i, data in enumerate(trainloader,0):

            inputs,labels=data

            inputs=inputs.to(device)

            labels=labels.to(device)

            optimizer.zero_grad()

            outputs=model(inputs)

            outputs.to(device)

            loss=criterion(outputs,labels)

            loss.backward()

            optimizer.step()

            running_loss+=loss.item()

            if(i%20 == 19):

                print("epoch: ",epoch+1)

                print("i + 1",i)

                print("loss: ",running_loss/20.0)

                #print('[%d, 5d] loss: %.3f' %(epoch+1,i+1,running_loss/20))

                running_loss=0.0









device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

print(device)



net=Classifier()

net.to(device)

print(net)

train()

So my question is, what is the most appropriate way to resize images while I am
training the network for my particular use case?

I am using Cuda8.0 and CudaDNN7.1 with Pytorch version 0.4.1 and Python3.7 on Ubuntu 16.04 LTS system.