Traning the image classification with pytorch
got following error messageK
RuntimeError Traceback (most recent call last) in 29 print(len(train_loader.dataset),len(valid_loader.dataset)) 30 #break ---> 31 train_loss, train_acc ,model= train(model, device, train_loader, optimizer, criterion) 32 valid_loss, valid_acc,model = evaluate(model, device, valid_loader, criterion) 33
in train(model, device, iterator, optimizer, criterion) 21 acc = calculate_accuracy(fx, y) 22 #print("5.") ---> 23 loss.backward() 24 25 optimizer.step()
~/venv/lib/python3.7/site-packages/torch/tensor.py in backward(self, gradient, retain_graph, create_graph) 164 products. Defaults to
False
. 165 """ --> 166 torch.autograd.backward(self, gradient, retain_graph, create_graph) 167 168 def register_hook(self, hook):~/venv/lib/python3.7/site-packages/torch/autograd/init.py in backward(tensors, grad_tensors, retain_graph, create_graph, grad_variables) 97 Variable._execution_engine.run_backward( 98 tensors, grad_tensors, retain_graph, create_graph, ---> 99 allow_unreachable=True) # allow_unreachable flag 100 101
RuntimeError: cuda runtime error (710) : device-side assert triggered at /pytorch/aten/src/THC/generic/THCTensorMath.cu:26
Related code block is here
def train(model, device, iterator, optimizer, criterion):
print('train')
epoch_loss = 0
epoch_acc = 0
model.train()
for (x, y) in iterator:
#print(x,y)
x,y = x.cuda(), y.cuda()
#x = x.to(device)
#y = y.to(device)
#print('1')
optimizer.zero_grad()
#print('2')
fx = model(x)
#print('3')
loss = criterion(fx, y)
#print("4.loss->",loss)
acc = calculate_accuracy(fx, y)
#print("5.")
loss.backward()
optimizer.step()
epoch_loss += loss.item()
epoch_acc += acc.item()
return epoch_loss / len(iterator), epoch_acc / len(iterator),model
EPOCHS = 5
SAVE_DIR = 'models'
MODEL_SAVE_PATH = os.path.join(SAVE_DIR, 'please.pt')
from torch.utils.data import DataLoader
best_valid_loss = float('inf')
if not os.path.isdir(f'{SAVE_DIR}'):
os.makedirs(f'{SAVE_DIR}')
print("start")
for epoch in range(EPOCHS):
print('================================',epoch ,'================================')
for i , (train_idx, valid_idx) in enumerate(zip(train_indexes, valid_indexes)):
print(i,train_idx,valid_idx,len(train_idx),len(valid_idx))
traindf = df_train.iloc[train_index, :].reset_index()
validdf = df_train.iloc[valid_index, :].reset_index()
#traindf = df_train
#validdf = df_train
train_dataset = TrainDataset(traindf, mode='train', transforms=data_transforms)
valid_dataset = TrainDataset(validdf, mode='valid', transforms=data_transforms)
train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
valid_loader = DataLoader(valid_dataset, batch_size=batch_size, shuffle=False)
print(len(train_loader.dataset),len(valid_loader.dataset))
#break
train_loss, train_acc ,model= train(model, device, train_loader, optimizer, criterion)
valid_loss, valid_acc,model = evaluate(model, device, valid_loader, criterion)
if valid_loss < best_valid_loss:
best_valid_loss = valid_loss
torch.save(model,MODEL_SAVE_PATH)
print(f'| Epoch: {epoch+1:02} | Train Loss: {train_loss:.3f} | Train Acc: {train_acc*100:05.2f}% | Val. Loss: {valid_loss:.3f} | Val. Acc: {valid_acc*100:05.2f}% |')
splits = zip(train_indexes, valid_indexes) [ 3692 3696 3703 ... 30733 30734 30735] [ 0 1 2 ... 4028 4041 4046] [ 0 1 2 ... 30733 30734 30735] [3692 3696 3703 ... 7986 7991 8005] [ 0 1 2 ... 30733 30734 30735] [ 7499 7500 7502 ... 11856 11858 11860] [ 0 1 2 ... 30733 30734 30735] [11239 11274 11280 ... 15711 15716 15720] [ 0 1 2 ... 30733 30734 30735] [15045 15051 15053 ... 19448 19460 19474] [
0 1 2 ... 30733 30734 30735] [18919 18920 18926 ... 23392 23400 23402] [ 0 1 2 ... 30733 30734 30735] [22831 22835 22846 ... 27118 27120 27124] [ 0 1 2 ... 27118 27120 27124] [26718 26721 26728 ... 30733 30734 30735]