Я использую модель HAR CNN с использованием PyTorch 1.01 в Anaconda с графическим процессором
Делая итерацию, она дает мне ошибку
Размер тензора a (128) должен соответствовать размеру тензора b (9) при не синглетонном измерении 0.
Я полагаю, что это модель данных при перечислении train_model, выдающем ошибку. Кто-нибудь сталкивался с подобными проблемами в PyTorch? Нужна небольшая поддержка, как новичок в PyTorch.
Я перепробовал все трюки с датамоделами, найденные в Google.
'' '
def train(model, optimizer, train_loader, test_loader):
n_batch = len(train_loader.dataset) // BATCH_SIZE
criterion = nn.CrossEntropyLoss()
for e in range(N_EPOCH):
model.train()
correct, total_loss = 0, 0
total = 0
for index, (sample, target) in enumerate(train_loader):
sample, target = sample.to(DEVICE).float(), target.to(DEVICE).long()
sample = sample.view(-1, 9, 1, 128)
output = model(sample)
loss = criterion(output, target)
optimizer.zero_grad()
loss.backward()
optimizer.step()
total_loss += loss.item()
_, predicted = torch.max(output.data, 1)
total += target.size(0)
correct += (predicted == target).sum()
if index % 20 == 0:
tqdm.tqdm.write('Epoch: [{}/{}], Batch: [{}/{}], loss:{:.4f}'.format(e + 1, N_EPOCH, index + 1, n_batch,
loss.item()))
acc_train = float(correct) * 100.0 / (BATCH_SIZE * n_batch)
tqdm.tqdm.write(
'Epoch: [{}/{}], loss: {:.4f}, train acc: {:.2f}%'.format(e + 1, N_EPOCH, total_loss * 1.0 / n_batch,
acc_train))
# Testing
model.train(False)
with torch.no_grad():
correct, total = 0, 0
for sample, target in test_loader:
sample, target = sample.to(DEVICE).float(), target.to(DEVICE).long()
sample = sample.view(-1, 9, 1, 128)
output = model(sample)
_, predicted = torch.max(output.data, 1)
total += target.size(0)
correct += (predicted == target).sum()
acc_test = float(correct) * 100 / total
tqdm.tqdm.write('Epoch: [{}/{}], test acc: {:.2f}%'.format(e + 1, N_EPOCH, float(correct) * 100 / total))
result.append([acc_train, acc_test])
result_np = np.array(result, dtype=float)
np.savetxt('result.csv', result_np, fmt='%.2f', delimiter=',')
Error ----------------------------
(7352, 1152)
(7352, 128, 9)
(2947, 1152)
(2947, 128, 9)
-----------------------------------------------------------------
----------
RuntimeError Traceback (most recent
call last)
<ipython-input-1-64c1adae4ee0> in <module>
86 model = net.Network().to(DEVICE)
87 optimizer = optim.SGD(params=model.parameters(),
lr=LEARNING_RATE, momentum=0.9)
---> 88 train(model, optimizer, train_loader, test_loader)
89 result = np.array(result, dtype=float)
90 np.savetxt('result.csv', result, fmt='%.2f', delimiter=',')
<ipython-input-1-64c1adae4ee0> in train(model, optimizer,
train_loader, test_loader)
29 correct, total_loss = 0, 0
30 total = 0
---> 31 for index, (sample, target) in
enumerate(train_loader):
32 sample, target = sample.to(DEVICE).float(),
target.to(DEVICE).long()
33 print('Sample',sample)
~/anaconda3/envs/rnn_lstm_har_pytorch/lib/python3.6/site-
packages/torch/utils/data/dataloader.py in __next__(self)
613 if self.num_workers == 0: # same-process loading
614 indices = next(self.sample_iter) # may raise
StopIteration
--> 615 batch = self.collate_fn([self.dataset[i] for i
in indices])
616 if self.pin_memory:
617 batch = pin_memory_batch(batch)
~/anaconda3/envs/rnn_lstm_har_pytorch/lib/python3.6/site-
packages/torch/utils/data/dataloader.py in <listcomp>(.0)
613 if self.num_workers == 0: # same-process loading
614 indices = next(self.sample_iter) # may raise
StopIteration
--> 615 batch = self.collate_fn([self.dataset[i] for i
in
indices])
616 if self.pin_memory:
617 batch = pin_memory_batch(batch)
~/anaconda3/envs/rnn_lstm_har_pytorch/data_preprocess.py in
__getitem__(self, index)
97 def __getitem__(self, index):
98 sample, target = self.samples[index],
self.labels[index]
---> 99 return self.T(sample), target
100
101 def __len__(self):
~/anaconda3/envs/rnn_lstm_har_pytorch/lib/python3.6/site-
packages/torchvision/transforms/transforms.py in __call__(self,
img)
58 def __call__(self, img):
59 for t in self.transforms:
---> 60 img = t(img)
61 return img
62
~/anaconda3/envs/rnn_lstm_har_pytorch/lib/python3.6/site-
packages/torchvision/transforms/transforms.py in __call__(self,
tensor)
161 Tensor: Normalized Tensor image.
162 """
--> 163 return F.normalize(tensor, self.mean, self.std,
self.inplace)
164
165 def __repr__(self):
~/anaconda3/envs/rnn_lstm_har_pytorch/lib/python3.6/site-
packages/torchvision/transforms/functional.py in normalize(tensor,
mean, std, inplace)
206 mean = torch.tensor(mean, dtype=torch.float32)
207 std = torch.tensor(std, dtype=torch.float32)
--> 208 tensor.sub_(mean[:, None, None]).div_(std[:, None,
None])
209 return tensor
210
RuntimeError: The size of tensor a (128) must match the size of
tensor b (9) at non-singleton dimension 0
# This is for parsing the X data, you can ignore it if you do not
need preprocessing
def format_data_x(datafile):
x_data = None
for item in datafile:
item_data = np.loadtxt(item, dtype=np.float)
if x_data is None:
x_data = np.zeros((len(item_data), 1))
x_data = np.hstack((x_data, item_data))
x_data = x_data[:, 1:]
print(x_data.shape)
X = None
for i in range(len(x_data)):
row = np.asarray(x_data[i, :])
row = row.reshape(9, 128).T
if X is None:
X = np.zeros((len(x_data), 128, 9))
X[i] = row
print(X.shape)
return X
# This is for parsing the Y data, you can ignore it if you do not
need preprocessing
def format_data_y(datafile):
data = np.loadtxt(datafile, dtype=np.int) - 1
YY = np.eye(6)[data]
return YY
# Load data function, if there exists parsed data file, then use
it
# If not, parse the original dataset from scratch
def load_data():
import os
# This for processing the dataset from scratch
# After downloading the dataset, program put it in the DATA_PATH
folder
#str_folder = 'data/' + 'UCI HAR Dataset/'
DATA_PATH = 'data/'
DATASET_PATH = DATA_PATH + 'UCI HAR Dataset/'
TRAIN = 'train/'
TEST = 'test/'
INPUT_SIGNAL_TYPES = [
"body_acc_x_",
"body_acc_y_",
"body_acc_z_",
"body_gyro_x_",
"body_gyro_y_",
"body_gyro_z_",
"total_acc_x_",
"total_acc_y_",
"total_acc_z_"
]
str_train_files = [DATASET_PATH + TRAIN + 'Inertial Signals/' +
item + 'train.txt' for item in
INPUT_SIGNAL_TYPES]
str_test_files = [DATASET_PATH + TEST + 'Inertial Signals/' + item
+ 'test.txt' for item in INPUT_SIGNAL_TYPES]
str_train_y = DATASET_PATH + TRAIN + 'y_train.txt'
str_test_y = DATASET_PATH + TEST + 'y_test.txt'
X_train = format_data_x(str_train_files)
X_test = format_data_x(str_test_files)
Y_train = format_data_y(str_train_y)
Y_test = format_data_y(str_test_y)
return X_train, onehot_to_label(Y_train), X_test,
onehot_to_label(Y_test)
def onehot_to_label(y_onehot):
a = np.argwhere(y_onehot == 1)
return a[:, -1]
class data_loader(Dataset):
def __init__(self, samples, labels, t):
self.samples = samples
self.labels = labels
self.T = t
def __getitem__(self, index):
sample, target = self.samples[index], self.labels[index]
return self.T(sample), target
def __len__(self):
return len(self.samples)
def load(batch_size=64):
x_train, y_train, x_test, y_test = load_data()
x_train, x_test = x_train.reshape((-1, 9, 1, 128)),
x_test.reshape((-1, 9, 1, 128))
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize(mean=(0,0,0,0,0,0,0,0,0), std=
(1,1,1,1,1,1,1,1,1))
])
train_set = data_loader(x_train, y_train, transform)
test_set = data_loader(x_test, y_test, transform)
train_loader = DataLoader(train_set, batch_size=batch_size,
shuffle=True, drop_last=True)
test_loader = DataLoader(test_set, batch_size=batch_size,
shuffle=False)
return train_loader, test_loader
'' '