Pytorch CNN error: Expected input batch_size (4) to match target batch_size (64)

I've been teaching myself this since November and any help on this would be really appreciated, thank you for looking, as I seem to be going round in circles. I am trying to use a Pytorch CNN example that was used with the Mnist dataset. Now I am trying to modify the CNN for facial key point recognition. I am using the Kaggle dataset (CSV) of 7048 training images and key points (15 key points per face) and 1783 test images. I split training dataset and converted the images to jpeg, made separate file for the key points (shape 15, 2). I have made dataset and data loader and can iterate through and display images and plot key points. When I run the CNN I am getting this error.

> Net(
  (conv1): Conv2d(1, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2): Conv2d(32, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (conv2_drop): Dropout2d(p=0.5)
  (fc1): Linear(in_features=589824, out_features=100, bias=True)
  (fc2): Linear(in_features=100, out_features=30, bias=True)
)
Data and target shape:  torch.Size([64, 96, 96])   torch.Size([64, 15, 2])
Data and target shape:  torch.Size([64, 1, 96, 96])   torch.Size([64, 15, 2])

Traceback (most recent call last):
  File "/home/keith/PycharmProjects/FacialLandMarks/WorkOut.py", line 416, in <module>
    main()
  File "/home/keith/PycharmProjects/FacialLandMarks/WorkOut.py", line 412, in main
    train(args, model, device, train_loader, optimizer, epoch)
  File "/home/keith/PycharmProjects/FacialLandMarks/WorkOut.py", line 324, in train
    loss = F.nll_loss(output, target)
  File "/home/keith/Desktop/PycharmProjects/fkp/FacialLandMarks/lib/python3.6/site-packages/torch/nn/functional.py", line 1788, in nll_loss
    .format(input.size(0), target.size(0)))
ValueError: Expected input batch_size (4) to match target batch_size (64).

Process finished with exit code 1

Here are some links I have read, I could not figure out the problem but may help some one else.

https://github.com/pytorch/pytorch/issues/11762 How do I modify this PyTorch convolutional neural network to accept a 64 x 64 image and properly output predictions? pytorch-convolutional-neural-network-to-accept-a-64-x-64-im Pytorch Validating Model Error: Expected input batch_size (3) to match target batch_size (4) model-error-expected-input-batch-size-3-to-match-target-ba

Here is my code:

    class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 32, kernel_size=5, stride=1, padding=(2, 2))
        self.conv2 = nn.Conv2d(32, 64, kernel_size=5, stride=1, padding=(2, 2))
        self.conv2_drop = nn.Dropout2d()
        self.fc1 = nn.Linear(64 * 96 * 96, 100)
        self.fc2 = nn.Linear(100, 30)  # 30 is x and y key points

    def forward(self, x):
        x = F.relu(F.max_pool2d(self.conv1(x), 2))
        x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
        x = x.view(-1, 64 * 96 * 96)
        # x = x.view(x.size(0), -1)
        # x = x.view(x.size()[0], 30, -1)
        x = F.relu(self.fc1(x))
        x = F.dropout(x, training=self.training)
        x = self.fc2(x)
        return F.log_softmax(x, dim=1)


def train(args, model, device, train_loader, optimizer, epoch):
    model.train()
    for batch_idx, batch in enumerate(train_loader):
        data = batch['image']
        target = batch['key_points']
        print('Data and target shape: ', data.shape, ' ', target.shape)
        data, target = data.to(device), target.to(device)
        optimizer.zero_grad()
        data = data.unsqueeze(1).float()

        print('Data and target shape: ', data.shape, ' ', target.shape)

        output = model(data)
        loss = F.nll_loss(output, target)
        loss.backward()
        optimizer.step()
        if batch_idx % args.log_interval == 0:
            print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
                epoch, batch_idx * len(data), len(train_loader.dataset),
                100. * batch_idx / len(train_loader), loss.item()))


# def test(args, model, device, test_loader):
#     model.eval()
#     test_loss = 0
#     correct = 0
#     with torch.no_grad():
#         for data, target in test_loader:
#             data, target = data.to(device), target.to(device)
#             output = model(data)
#             test_loss += F.nll_loss(output, target, reduction='sum').item() # sum up batch loss
#             pred = output.max(1, keepdim=True)[1] # get the index of the max log-probability
#             correct += pred.eq(target.view_as(pred)).sum().item()
#
#     test_loss /= len(test_loader.dataset)
#     print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
#         test_loss, correct, len(test_loader.dataset),
#         100. * correct / len(test_loader.dataset)))



def main():
    # Training settings
    parser = argparse.ArgumentParser(description='Project')
    parser.add_argument('--batch-size', type=int, default=64, metavar='N',
                        help='input batch size for training (default: 64)')
    parser.add_argument('--test-batch-size', type=int, default=1000, metavar='N',
                        help='input batch size for testing (default: 1000)')
    parser.add_argument('--epochs', type=int, default=10, metavar='N',   # ========  epoch
                        help='number of epochs to train (default: 10)')
    parser.add_argument('--lr', type=float, default=0.01, metavar='LR',
                        help='learning rate (default: 0.01)')
    parser.add_argument('--momentum', type=float, default=0.5, metavar='M',
                        help='SGD momentum (default: 0.5)')
    parser.add_argument('--no-cuda', action='store_true', default=False,
                        help='disables CUDA training')
    parser.add_argument('--seed', type=int, default=1, metavar='S',
                        help='random seed (default: 1)')
    parser.add_argument('--log-interval', type=int, default=10, metavar='N',
                        help='how many batches to wait before logging training status')
    args = parser.parse_args()
    use_cuda = not args.no_cuda and torch.cuda.is_available()

    torch.manual_seed(args.seed)

    device = torch.device("cuda" if use_cuda else "cpu")

    kwargs = {'num_workers': 1, 'pin_memory': True} if use_cuda else {}
    train_data_set = FaceKeyPointDataSet(csv_file='faces/Kep_points_and_id.csv',
                                         root_dir='faces/',
                                         transform=transforms.Compose([
                                             # Rescale(96),
                                             ToTensor()
                                         ]))

    train_loader = DataLoader(train_data_set, batch_size=args.batch_size,
                              shuffle=True)

    print('Number of samples: ', len(train_data_set))
    print('Number of train_loader: ', len(train_loader))

    model = Net().to(device)
    print(model)
    optimizer = optim.SGD(model.parameters(), lr=args.lr, momentum=args.momentum)

    for epoch in range(1, args.epochs + 1):
        train(args, model, device, train_loader, optimizer, epoch)
        # test(args, model, device, test_loader)

if __name__ == '__main__':
    main()