Hey guys, I am an ABSOLUTE newbie over here, and I am trying to use some frankensteined pytorch code to create a neural network for a final project. I’ve been getting mistakes and fixing them, but I really can’t figure out this one and all the explanations involve really complicated mathematical things. Any help is extremely appreciated.
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.autograd import Variable
import torch.utils.data as data
import torchvision
from torchvision import transforms
EPOCHS = 2
BATCH_SIZE = 10
LEARNING_RATE = 0.003
TRAIN_DATA_PATH = "./images/train/"
TEST_DATA_PATH = "./images/test/"
TRANSFORM_IMG = transforms.Compose([
transforms.Grayscale(num_output_channels=1),
transforms.Resize(256),
transforms.CenterCrop(256),
transforms.ToTensor(),
transforms.Normalize((0.5,), (0.5,))
])
train_data = torchvision.datasets.ImageFolder(root=TRAIN_DATA_PATH, transform=TRANSFORM_IMG)
train_data_loader = data.DataLoader(train_data, batch_size=BATCH_SIZE, shuffle=True, num_workers=4)
test_data = torchvision.datasets.ImageFolder(root=TEST_DATA_PATH, transform=TRANSFORM_IMG)
test_data_loader = data.DataLoader(test_data, batch_size=BATCH_SIZE, shuffle=True, num_workers=4)
class CNN(nn.Module):
def __init__(self):
super().__init__()
self.conv1 = nn.Conv2d(1, 32, 5)
self.conv2 = nn.Conv2d(32, 64, 5)
self.conv3 = nn.Conv2d(64, 128, 5)
x = torch.randn(50,50).view(-1,1,50,50)
self._to_linear = None
self.convs(x)
self.fc1 = nn.Linear(self._to_linear, 512)
self.fc2 = nn.Linear(512, 2)
def convs(self, x):
x = F.max_pool2d(F.relu(self.conv1(x)), (2,2))
x = F.max_pool2d(F.relu(self.conv2(x)), (2,2))
x = F.max_pool2d(F.relu(self.conv3(x)), (2,2))
if self._to_linear is None:
self._to_linear = x[0].shape[0]*x[0].shape[1]*x[0].shape[2]
return x
def forward(self, x):
x = self.convs(x)
x = x.view(-1, self._to_linear)
x = F.relu(self.fc1(x))
x = self.fc2(x)
return F.softmax(x, dim=1)
if __name__ == '__main__':
print("Number of train samples: ", len(train_data))
print("Number of test samples: ", len(test_data))
print("Detected Classes are: ", train_data.class_to_idx) # classes are detected by folder structure
model = CNN()
optimizer = torch.optim.Adam(model.parameters(), lr=LEARNING_RATE)
loss_func = nn.BCEWithLogitsLoss()
# Training and Testing
for epoch in range(EPOCHS):
for step, (x, y) in enumerate(train_data_loader):
b_x = Variable(x) # batch x (image)
b_y = Variable(y) # batch y (target)
output = model(b_x)[0]
loss = loss_func(output, b_y)
optimizer.zero_grad()
loss.backward()
optimizer.step()
if step % 50 == 0:
test_x = Variable(test_data_loader)
test_output, last_layer = model(test_x)
pred_y = torch.max(test_output, 1)[1].data.squeeze()
accuracy = sum(pred_y == test_y) / float(test_y.size(0))
print('Epoch: ', epoch, '| train loss: %.4f' % loss.data[0], '| test accuracy: %.2f' % accuracy)
