We Keep Coding

Pytorch: non-positive stride is not supported

I have some MRI scans, where each scan is a set of 31 RGB images. The dimensions of the input data are (Channels, Depth, Height, Width). The images are png, and each scan is a folder containing its 31 images.
I created a custom Dataset class:
class TrainImages(Dataset):
def __init__(self, csv_file, root_dir, transform=None):
self.annotations = pd.read_csv(csv_file)
self.root_dir = root_dir
self.transform = transform
def __len__(self):
return len(self.annotations)
def __getitem__(self, index):
img_path = os.path.join(self.root_dir, str(self.annotations.iloc[index, 0]).zfill(5))
image = torch.from_numpy(np.array([np.array(Image.open(os.path.join(str(img_path),"rgb-"+str(i)+".png"))) for i in range(31)]).transpose(3,0,1,2).astype(np.float32))
y_label = torch.tensor(int(self.annotations.iloc[index, 1]))
return (image, y_label)
Then, I created a small 3D CNN class:
class CNN2(nn.Module):
def __init__(self):
super(CNN2, self).__init__()
self.conv_layer1 = self._conv_layer(3, 12)
def _conv_layer(self, in_c, out_c, conv_kernel_size=3, padding=0):
layer = nn.Sequential(
nn.Conv3d(in_c, out_c, conv_kernel_size, padding),
)
return layer
def forward(self, x):
out = self.conv_layer1(x)
return out
Then, I tried to feed one scan into the CNN2 object:
x=torch.unsqueeze(dataset[0][0], 0)
x.shape #torch.Size([1, 3, 31, 512, 512])
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
data = x.to(device)
model = CNN2().to(device)
model(x)
But it produces this error:
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
<ipython-input-24-c89306854a22> in <module>
1 model = CNN_test().to(device)
----> 2 model(x)
/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
725 result = self._slow_forward(*input, **kwargs)
726 else:
--> 727 result = self.forward(*input, **kwargs)
728 for hook in itertools.chain(
729 _global_forward_hooks.values(),
<ipython-input-22-ac66ca7a2459> in forward(self, x)
14
15 def forward(self, x):
---> 16 out = self.conv_layer1(x)
17
18 return out
/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
725 result = self._slow_forward(*input, **kwargs)
726 else:
--> 727 result = self.forward(*input, **kwargs)
728 for hook in itertools.chain(
729 _global_forward_hooks.values(),
/opt/conda/lib/python3.7/site-packages/torch/nn/modules/container.py in forward(self, input)
115 def forward(self, input):
116 for module in self:
--> 117 input = module(input)
118 return input
119
/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
725 result = self._slow_forward(*input, **kwargs)
726 else:
--> 727 result = self.forward(*input, **kwargs)
728 for hook in itertools.chain(
729 _global_forward_hooks.values(),
/opt/conda/lib/python3.7/site-packages/torch/nn/modules/conv.py in forward(self, input)
571 self.dilation, self.groups)
572 return F.conv3d(input, self.weight, self.bias, self.stride,
--> 573 self.padding, self.dilation, self.groups)
574
575
RuntimeError: non-positive stride is not supported
However, when I just create a Conv3D object and pass the same scan in, no error results:
x=torch.unsqueeze(dataset[0][0], 0)
m=nn.Conv3d(3,12,3)
out=m(x)
I think the error might have to do with the dimensions of the input data, but I don't understand what "non-positive stride" means. I'm also confused why no error occurs when I just pass the data into a Conv3D object, but an error occurs when I pass the same data into an instance of the CNN class that does the same thing.

The issue is not with your input shape, it has to do with your layer initialization. You have essentially defined your 3D convolution with this line:
nn.Conv3d(in_c, out_c, conv_kernel_size, padding)
The issue is nn.Conv3d function head is the following:
torch.nn.Conv3d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True, padding_mode='zeros', device=None, dtype=None)
Notice how stride is placed before padding. In your code, variable padding ends up being assigned to the stride argument.
To solve the issue, you can specify the argument name with a keyword argument, i.e. padding=padding. This disambiguates the issue with positional arguments stride and padding.
class CNN2(nn.Module):
def __init__(self):
super(CNN2, self).__init__()
self.conv_layer1 = self._conv_layer(3, 12)
def _conv_layer(self, in_c, out_c, conv_kernel_size=3, padding=0):
layer = nn.Sequential(
nn.Conv3d(in_c, out_c, conv_kernel_size, padding=padding))
return layer
def forward(self, x):
out = self.conv_layer1(x)
return out

Pytorch got CUDA error: device-side assert triggered when training conv1d classifier

I'm implementing a CNN multi-label classifier with PyTorch, while it always shows this error:
"CUDA error: device-side assert triggered". In the error message it points out the loss function, but when I change a loss function, it still occurs and points to the other parts (really like randomly picked). When I changed to CPU, it said "index out of range in self", however when I investigated my dataloader, it is nothing weird.
I have 15 classes, 59462 unique tokens, and the len of each document is 30,000(token).
My model and loss function is like this:
class model(nn.Module):
def __init__(self, num_classes=15):
super(model, self).__init__()
self.embedding = nn.Sequential(nn.Embedding(59462,400),nn.Dropout(0.15))
self.features = nn.Sequential(
nn.Conv1d(400, 500, kernel_size=3, stride=1, padding=False), nn.ReLU(),
nn.Dropout(0.05), nn.MaxPool1d(kernel_size=2), nn.Dropout(0.15))
self.linear = nn.Linear(500*14999, 15)
def forward(self, x):
x = self.embedding(x)
x = x.permute(0,2,1)
x = self.features(x)
x = x.view(x.size(0), 500*14999)
x = self.linear(x)
return x
model = model()
model = model.to(device)
def loss_fn(outputs, targets):
return torch.nn.BCEWithLogitsLoss(pos_weight=pos_weight.to(device))(outputs, targets).to(device)
#pos_weight is for my unbalanced data
This is the error messsage when using CPU:
/usr/local/lib/python3.6/dist-packages/IPython/core/interactiveshell.py in run_cell_magic(self, magic_name, line, cell)
2115 magic_arg_s = self.var_expand(line, stack_depth)
2116 with self.builtin_trap:
-> 2117 result = fn(magic_arg_s, cell)
2118 return result
2119
<decorator-gen-60> in time(self, line, cell, local_ns)
/usr/local/lib/python3.6/dist-packages/IPython/core/magic.py in <lambda>(f, *a, **k)
186 # but it's overkill for just that one bit of state.
187 def magic_deco(arg):
--> 188 call = lambda f, *a, **k: f(*a, **k)
189
190 if callable(arg):
/usr/local/lib/python3.6/dist-packages/IPython/core/magics/execution.py in time(self, line, cell, local_ns)
1191 else:
1192 st = clock2()
-> 1193 exec(code, glob, local_ns)
1194 end = clock2()
1195 out = None
<timed exec> in <module>()
<ipython-input-67-09829392983d> in train_epoch(model, data_loader, loss_fn, optimizer, device, scheduler, n_examples)
27 targets = d["targets"].to(device)
28 outputs = model(
---> 29 tokens
30 )
31
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
725 result = self._slow_forward(*input, **kwargs)
726 else:
--> 727 result = self.forward(*input, **kwargs)
728 for hook in itertools.chain(
729 _global_forward_hooks.values(),
<ipython-input-59-2c2ec554cb05> in forward(self, x)
16
17 def forward(self, x):
---> 18 x = self.embedding(x)
19 x = x.permute(0,2,1)
20 x = self.features(x)
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
725 result = self._slow_forward(*input, **kwargs)
726 else:
--> 727 result = self.forward(*input, **kwargs)
728 for hook in itertools.chain(
729 _global_forward_hooks.values(),
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/container.py in forward(self, input)
115 def forward(self, input):
116 for module in self:
--> 117 input = module(input)
118 return input
119
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
725 result = self._slow_forward(*input, **kwargs)
726 else:
--> 727 result = self.forward(*input, **kwargs)
728 for hook in itertools.chain(
729 _global_forward_hooks.values(),
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/sparse.py in forward(self, input)
124 return F.embedding(
125 input, self.weight, self.padding_idx, self.max_norm,
--> 126 self.norm_type, self.scale_grad_by_freq, self.sparse)
127
128 def extra_repr(self) -> str:
/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py in embedding(input, weight, padding_idx, max_norm, norm_type, scale_grad_by_freq, sparse)
1850 # remove once script supports set_grad_enabled
1851 _no_grad_embedding_renorm_(weight, input, max_norm, norm_type)
-> 1852 return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
1853
1854
IndexError: index out of range in self
Does anyone know what this problem is, and how I can solve it?
Thanks in advance.

Why tf.GradientTape() has less GPU memory usage when watch model variables manually?

So when I use tf.GradientTape() to automatically monitor the trainable variables in a resnet model, the computer threw an out of memory error. Below is the code:
x_mini = preprocess_input(x_train)
with tf.GradientTape() as tape:
outputs = model(x_mini, training=True)
However if I disable the auto-monitor and manually watch the trainable variables, I can feed in even larger data without any memory problem. The code is below:
x_mini = preprocess_input(x_train)
with tf.GradientTape(watch_accessed_variables=False) as tape:
tape.watch(model.trainable_variables)
outputs = model(x_mini, training=True)
I am wondering if the tape missed some variables when I do it manually.
Below is runable code(out of memory error will show if you comment option 1): I use Tesla T4 15G GPU and tensorflow 2.3.
import tensorflow as tf
import numpy as np
from keras.models import Model
import keras.layers as ly
x_train = tf.convert_to_tensor(np.random.randint(0, 255, (900,224,224,3)), dtype=tf.dtypes.float32)
y_train = tf.convert_to_tensor([0,1,0], dtype=tf.dtypes.float32)
print(x_train.shape)
tf.keras.backend.clear_session()
resnet_model = tf.keras.applications.resnet.ResNet50(weights='imagenet', include_top=False, input_shape=(224, 224, 3))
resnet_model.trainable = False
inputs = tf.keras.Input(shape=(224, 224, 3))
x = resnet_model(inputs, training=False)
x = ly.GlobalAveragePooling2D()(x)
x = ly.Dropout(0.2)(x)
outputs = ly.Dense(3, activation='softmax')(x)
model = Model(inputs, outputs)
mcross = tf.keras.losses.categorical_crossentropy
macc = tf.keras.metrics.categorical_accuracy
base_learning_rate = 0.0001
optimizer = tf.keras.optimizers.Adam(base_learning_rate)
def cross_entropy(y_true, y_pred):
y_pred = y_pred / tf.reduce_sum(y_pred, 1, True)
y_pred = tf.clip_by_value(y_pred, 1e-3, 1-1e-3)
return -tf.reduce_sum(y_true*tf.math.log(y_pred), 1)
# option 1
# manually tapping variables
with tf.GradientTape(watch_accessed_variables=False) as tape:
tape.watch(model.trainable_variables)
y_pred = model(x_train, training=True)
loss = cross_entropy(y_train, tf.reduce_mean(y_pred, 0, keepdims=True))
gradients = tape.gradient(loss, model.trainable_variables)
#option 2
# automatically tapping variable
with tf.GradientTape() as tape:
y_pred = model(x_train, training=True)
loss = cross_entropy(y_train, tf.reduce_mean(y_pred, 0, keepdims=True))
gradients = tape.gradient(loss, model.trainable_variables)
Also the error message:
--------------------------------------------------------------------------- ResourceExhaustedError Traceback (most recent call last) <ipython-input-4-42e45caeae41> in <module>
31 # automatically tapping variable
32 with tf.GradientTape() as tape:
---> 33 y_pred = model(x_train, training=True)
34 loss = cross_entropy(y_train, tf.reduce_mean(y_pred, 0, keepdims=True))
35 gradients = tape.gradient(loss, model.trainable_variables)
/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py in __call__(self, *args, **kwargs)
983
984 with ops.enable_auto_cast_variables(self._compute_dtype_object):
--> 985 outputs = call_fn(inputs, *args, **kwargs)
986
987 if self._activity_regularizer:
/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/functional.py in call(self, inputs, training, mask)
384 """
385 return self._run_internal_graph(
--> 386 inputs, training=training, mask=mask)
387
388 def compute_output_shape(self, input_shape):
/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/functional.py in _run_internal_graph(self, inputs, training, mask)
506
507 args, kwargs = node.map_arguments(tensor_dict)
--> 508 outputs = node.layer(*args, **kwargs)
509
510 # Update tensor_dict.
/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py in __call__(self, *args, **kwargs)
983
984 with ops.enable_auto_cast_variables(self._compute_dtype_object):
--> 985 outputs = call_fn(inputs, *args, **kwargs)
986
987 if self._activity_regularizer:
/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/functional.py in call(self, inputs, training, mask)
384 """
385 return self._run_internal_graph(
--> 386 inputs, training=training, mask=mask)
387
388 def compute_output_shape(self, input_shape):
/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/functional.py in _run_internal_graph(self, inputs, training, mask)
506
507 args, kwargs = node.map_arguments(tensor_dict)
--> 508 outputs = node.layer(*args, **kwargs)
509
510 # Update tensor_dict.
/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py in __call__(self, *args, **kwargs)
983
984 with ops.enable_auto_cast_variables(self._compute_dtype_object):
--> 985 outputs = call_fn(inputs, *args, **kwargs)
986
987 if self._activity_regularizer:
/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/layers/convolutional.py in call(self, inputs)
245 inputs = array_ops.pad(inputs, self._compute_causal_padding(inputs))
246
--> 247 outputs = self._convolution_op(inputs, self.kernel)
248
249 if self.use_bias:
/opt/conda/lib/python3.7/site-packages/tensorflow/python/util/dispatch.py in wrapper(*args, **kwargs)
199 """Call target, and fall back on dispatchers if there is a TypeError."""
200 try:
--> 201 return target(*args, **kwargs)
202 except (TypeError, ValueError):
203 # Note: convert_to_eager_tensor currently raises a ValueError, not a
/opt/conda/lib/python3.7/site-packages/tensorflow/python/ops/nn_ops.py in convolution_v2(input, filters, strides, padding, data_format, dilations, name) 1016 data_format=data_format, 1017 dilations=dilations,
-> 1018 name=name) 1019 1020
/opt/conda/lib/python3.7/site-packages/tensorflow/python/ops/nn_ops.py in convolution_internal(input, filters, strides, padding, data_format, dilations, name, call_from_convolution, num_spatial_dims) 1146 data_format=data_format, 1147 dilations=dilations,
-> 1148 name=name) 1149 else: 1150 if channel_index == 1:
/opt/conda/lib/python3.7/site-packages/tensorflow/python/ops/nn_ops.py in _conv2d_expanded_batch(input, filters, strides, padding, data_format, dilations, name) 2590 data_format=data_format, 2591 dilations=dilations,
-> 2592 name=name) 2593 return squeeze_batch_dims( 2594 input,
/opt/conda/lib/python3.7/site-packages/tensorflow/python/ops/gen_nn_ops.py in conv2d(input, filter, strides, padding, use_cudnn_on_gpu, explicit_paddings, data_format, dilations, name)
936 return _result
937 except _core._NotOkStatusException as e:
--> 938 _ops.raise_from_not_ok_status(e, name)
939 except _core._FallbackException:
940 pass
/opt/conda/lib/python3.7/site-packages/tensorflow/python/framework/ops.py in raise_from_not_ok_status(e, name) 6841 message = e.message + (" name: " + name if name is not None else "") 6842 # pylint: disable=protected-access
-> 6843 six.raise_from(core._status_to_exception(e.code, message), None) 6844 # pylint: enable=protected-access 6845
/opt/conda/lib/python3.7/site-packages/six.py in raise_from(value, from_value)
ResourceExhaustedError: OOM when allocating tensor with shape[900,56,56,256] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc [Op:Conv2D]

pytorch vgg model test on one image

I've trained a vgg model, this is how I transformed the test data
test_transform_2= transforms.Compose([transforms.RandomResizedCrop(224),
transforms.ToTensor()])
test_data = datasets.ImageFolder(test_dir, transform=test_transform_2)
the model's finished training now I want to test it on a single image
from scipy import misc
test_image = misc.imread('flower_data/valid/1/image_06739.jpg')
vgg16(torch.from_numpy(test_image))
Error
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
<ipython-input-60-b83587325fea> in <module>
----> 1 vgg16(torch.from_numpy(test_image))
c:\users\sam\mydocu~1\code\envs\data-science\lib\site-packages\torch\nn\modules\module.py in __call__(self, *input, **kwargs)
475 result = self._slow_forward(*input, **kwargs)
476 else:
--> 477 result = self.forward(*input, **kwargs)
478 for hook in self._forward_hooks.values():
479 hook_result = hook(self, input, result)
c:\users\sam\mydocu~1\code\envs\data-science\lib\site-packages\torchvision\models\vgg.py in forward(self, x)
40
41 def forward(self, x):
---> 42 x = self.features(x)
43 x = x.view(x.size(0), -1)
44 x = self.classifier(x)
c:\users\sam\mydocu~1\code\envs\data-science\lib\site-packages\torch\nn\modules\module.py in __call__(self, *input, **kwargs)
475 result = self._slow_forward(*input, **kwargs)
476 else:
--> 477 result = self.forward(*input, **kwargs)
478 for hook in self._forward_hooks.values():
479 hook_result = hook(self, input, result)
c:\users\sam\mydocu~1\code\envs\data-science\lib\site-packages\torch\nn\modules\container.py in forward(self, input)
89 def forward(self, input):
90 for module in self._modules.values():
---> 91 input = module(input)
92 return input
93
c:\users\sam\mydocu~1\code\envs\data-science\lib\site-packages\torch\nn\modules\module.py in __call__(self, *input, **kwargs)
475 result = self._slow_forward(*input, **kwargs)
476 else:
--> 477 result = self.forward(*input, **kwargs)
478 for hook in self._forward_hooks.values():
479 hook_result = hook(self, input, result)
c:\users\sam\mydocu~1\code\envs\data-science\lib\site-packages\torch\nn\modules\conv.py in forward(self, input)
299 def forward(self, input):
300 return F.conv2d(input, self.weight, self.bias, self.stride,
--> 301 self.padding, self.dilation, self.groups)
302
303
RuntimeError: Expected 4-dimensional input for 4-dimensional weight [64, 3, 3, 3], but got input of size [628, 500, 3] instead
I can tell I need to shape the input, however I don't know how to based on the way it seems to expect the input to be inform of a batch.

Your image is [h, w, 3] where 3 means the rgb channel, and pytorch expects [b, 3, h, w] where b is batch size. So you can reshape it by calling do that by calling reshaped = img.permute(2, 0, 1).unsqueeze(0). I think there is also a utility function for that somewhere, but I can't find it right now.
So in your case
tensor = torch.from_numpy(test_image)
reshaped = tensor.permute(2, 0 1).unsqueeze(0)
your_result = vgg16(reshaped)

RuntimeError: size mismatch, m1: [672 x 224], m2: [672 x 224]

While working on Udacity's AI course I encountered the error in the title.
At first it looks like the image isn't formatted for the model, however the instruction for the course has us format the images using resize, so I get an image dimension of 3x224x224, that's 3 color channels and 224 pixels by 224 pixels. The image array is in the required dimensions, [3,224,224].
Return/Output:
(3, 224, 224)
(3, 224, 224)
torch.Size([1, 3, 224, 224])
Next, I figured it was the model, but when I go back, before the training loop and change the original model to fix this error I get a similar error in revers "up stream".
I want this predict function to use my model to predict the category of an image.
Posted are:
Original classifier
Save checkpoint block
Process image function
Predict image function
classifier = nn.Sequential(OrderedDict([
('fc1', nn.Linear(25088, 500)),
('relu', nn.ReLU()),
('drop', nn.Dropout(0.25)),
('fc2', nn.Linear(500, 102)),
('output', nn.LogSoftmax(dim=1))
]))
model.load_state_dict(state_dict)
checkpoint= {'input_size': 672,
'output_size': 102,
'hidden_layers': 224,
'state_dict': model.state_dict()}
torch.save(checkpoint, 'checkpoint.pth')
def predict(image_path, model, topk=5):
''' Predict the class (or classes) of an image using a trained deep learning model.
'''
model= model.cuda()
model.eval()
# TODO: Implement the code to predict the class from an image file
pil_img= Image.open(image_path)
#print(pil_img)
processed_image= process_image(pil_img)
print(processed_image.shape)
torch_image= torch.from_numpy(processed_image)
torch_image= torch_image.unsqueeze_(0)
print(torch_image.shape)
torch_image= torch_image.float().to('cuda')
output= model.forward(torch_image)
#top_k= predict.topk(topk)
#print(top_k)
return torch_img
image_path = 'flowers/test/8/image_03299.jpg'
predict(image_path, model, 5)
> RuntimeError Traceback (most recent call last)
<ipython-input-21-d84c5999ad68> in <module>()
23
24 image_path = 'flowers/test/8/image_03299.jpg'
---> 25 predict(image_path, model, 5)
<ipython-input-21-d84c5999ad68> in predict(image_path, model, topk)
16 print(torch_image.shape)
17 torch_image= torch_image.float().to('cuda')
---> 18 output= model.forward(torch_image)
19 #top_k= predict.topk(topk)
20 #print(top_k)
/opt/conda/lib/python3.6/site-packages/torch/nn/modules/container.py in forward(self, input)
89 def forward(self, input):
90 for module in self._modules.values():
---> 91 input = module(input)
92 return input
93
/opt/conda/lib/python3.6/site-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
489 result = self._slow_forward(*input, **kwargs)
490 else:
--> 491 result = self.forward(*input, **kwargs)
492 for hook in self._forward_hooks.values():
493 hook_result = hook(self, input, result)
/opt/conda/lib/python3.6/site-packages/torch/nn/modules/linear.py in forward(self, input)
53
54 def forward(self, input):
---> 55 return F.linear(input, self.weight, self.bias)
56
57 def extra_repr(self):
/opt/conda/lib/python3.6/site-packages/torch/nn/functional.py in linear(input, weight, bias)
992 return torch.addmm(bias, input, weight.t())
993
--> 994 output = input.matmul(weight.t())
995 if bias is not None:
996 output += bias
RuntimeError Traceback (most recent call last)
<ipython-input-21-d84c5999ad68> in <module>()
23
24 image_path = 'flowers/test/8/image_03299.jpg'
---> 25 predict(image_path, model, 5)
<ipython-input-21-d84c5999ad68> in predict(image_path, model, topk)
16 print(torch_image.shape)
17 torch_image= torch_image.float().to('cuda')
---> 18 output= model.forward(torch_image)
19 #top_k= predict.topk(topk)
20 #print(top_k)
/opt/conda/lib/python3.6/site-packages/torch/nn/modules/container.py in forward(self, input)
89 def forward(self, input):
90 for module in self._modules.values():
---> 91 input = module(input)
92 return input
93
/opt/conda/lib/python3.6/site-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
489 result = self._slow_forward(*input, **kwargs)
490 else:
--> 491 result = self.forward(*input, **kwargs)
492 for hook in self._forward_hooks.values():
493 hook_result = hook(self, input, result)
/opt/conda/lib/python3.6/site-packages/torch/nn/modules/linear.py in forward(self, input)
53
54 def forward(self, input):
---> 55 return F.linear(input, self.weight, self.bias)
56
57 def extra_repr(self):
/opt/conda/lib/python3.6/site-packages/torch/nn/functional.py in linear(input, weight, bias)
992 return torch.addmm(bias, input, weight.t())
993
--> 994 output = input.matmul(weight.t())
995 if bias is not None:
996 output += bias
RuntimeError: size mismatch, m1: [672 x 224], m2: [672 x 224] at /opt/conda/conda-bld/pytorch_1524584710464/work/aten/src/THC/generic/THCTensorMathBlas.cu:249