Hi, I’m a bit confused about an error i have.
[torch.FloatTensor of size 3x1x296]
Traceback (most recent call last):
File “pytorch.py”, line 168, in
train(epoch)
File “pytorch.py”, line 139, in train
output = model(data)
File “/home/david/anaconda3/lib/python3.5/site-packages/torch/nn/modules/module.py”, line 206, in call
result = self.forward(*input, **kwargs)
File “pytorch.py”, line 118, in forward
x = F.relu(self.fc1(x))
File “/home/david/anaconda3/lib/python3.5/site-packages/torch/nn/modules/module.py”, line 206, in call
result = self.forward(*input, **kwargs)
File “/home/david/anaconda3/lib/python3.5/site-packages/torch/nn/modules/linear.py”, line 54, in forward
return self._backend.Linear()(input, self.weight, self.bias)
File "/home/david/anaconda3/lib/python3.5/site-packages/torch/nn/functions/linear.py", line 10, in forward
output.addmm(0, 1, input, weight.t())
RuntimeError: matrices expected, got 3D, 2D tensors at /b/wheel/pytorch-src/torch/lib/TH/generic/THTensorMath.c:1232
my tensor is as i would have hope 3x1x196 which is the expected size with 3 being the batch size.
i think it’s the batch of 3 which is causing the 3d, 2d tensor confusion but not sure how to get around this. is the input to NN the whole batch or just one record ?
full code below.
from __future__ import print_function
import argparse
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
from torch.autograd import Variable
import torch.utils.data as utils_data
import numpy
from random import randrange
# fix random seed for reproducibility
numpy.random.seed(7)
# Training settings
parser = argparse.ArgumentParser(description='PyTorch MNIST Example')
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',
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()
args.cuda = not args.no_cuda and torch.cuda.is_available()
torch.manual_seed(args.seed)
if args.cuda:
torch.cuda.manual_seed(args.seed)
kwargs = {'num_workers': 1, 'pin_memory': True} if args.cuda else {}
class MyDataset():
def __init__(self):
dataset = numpy.genfromtxt("vectorFile.csv", delimiter=",")
self.features = dataset[:,0:148]
self.labels = dataset[:,149]
self.size = len(dataset)
def __getitem__(self, index):
# choose random index in features
firstPick = randrange(0,self.size)
firstPlayer = self.features[firstPick][0]#dealer or not ?
while True:
secondPick = randrange(0,self.size)
#print('secondPick')
if firstPlayer==self.features[secondPick][0]:
#print('match')
break
if self.labels[firstPick]>self.labels[secondPick]:
#print('adding to outputAnswer')
target = numpy.array([(1,0)])
else:
#print('adding to outputAnswer')
target = numpy.array([(1,0)])
target = torch.from_numpy(target).float()
data = numpy.array([(self.features[firstPick], self.features[secondPick])])
data = data.reshape((1, 296))
data = torch.from_numpy(data).float()
#print('data', data)
#print('target', target)
return data, target
def __len__(self):
return self.size
train_loader = torch.utils.data.DataLoader(MyDataset(), batch_size=3)
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
#self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
#self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
#self.conv2_drop = nn.Dropout2d()
self.fc1 = nn.Linear(296, 50)
self.fc2 = nn.Linear(50, 2)
def forward(self, x):
print('x')
print(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, 320)
x = F.relu(self.fc1(x))
#x = F.dropout(x, training=self.training)
x = self.fc2(x)
return F.log_softmax(x)
model = Net()
if args.cuda:
model.cuda()
optimizer = optim.SGD(model.parameters(), lr=args.lr, momentum=args.momentum)
def train(epoch):
model.train()
for batch_idx, (data, target) in enumerate(train_loader):
print(batch_idx)
print(data)
print(target)
if args.cuda:
data, target = data.cuda(), target.cuda()
data, target = Variable(data), Variable(target)
optimizer.zero_grad()
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.data[0]))
def test():
model.eval()
test_loss = 0
correct = 0
for data, target in test_loader:
if args.cuda:
data, target = data.cuda(), target.cuda()
data, target = Variable(data, volatile=True), Variable(target)
output = model(data)
test_loss += F.nll_loss(output, target, size_average=False).data[0] # sum up batch loss
pred = output.data.max(1)[1] # get the index of the max log-probability
correct += pred.eq(target.data).cpu().sum()
test_loss /= len(test_loader.dataset)
print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
test_loss, correct, len(train_loader.dataset),
100. * correct / len(train_loader.dataset)))
for epoch in range(1, args.epochs + 1):
train(epoch)
#test()