I'm trying to train a network for facial recognition, I can't get past this error. I'm really new to programming in Python and even more so with libraries like Tensorflow.
I keep on getting this error related to input shape. Any help would be highly appreciated. Thanks!
labeled_images = data.map(process_file)
print('labeled images: ', labeled_images)
test_data = labeled_images.take(50)
train_data = labeled_images.skip(50)
print('test data: ', test_data)
print('train data: ', train_data)
this is where the problems start
model = models.Sequential()
model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(192, 192, 3)))
model.add(layers.MaxPooling2D((2, 2))) model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu')) model.add(layers.Flatten())
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(40))
model.summary()
model.compile(optimizer='adam',
loss=tf.keras.losses.SparseCategoricalCrossentropy, metrics=['accuracy'])
history = model.fit(train_data, epochs=10, validation_data=test_data)
I printed the "variables"
data: <ZipDataset element_spec=(TensorSpec(shape=(), dtype=tf.string, name=None), TensorSpec(shape=(40,), dtype=tf.int64, name=None))>
labeled images: <MapDataset element_spec=(TensorSpec(shape=(192, 192, 3), dtype=tf.float32, name=None), TensorSpec(shape=(40,), dtype=tf.int64, name=None))>
test data: <TakeDataset element_spec=(TensorSpec(shape=(192, 192, 3), dtype=tf.float32, name=None), TensorSpec(shape=(40,), dtype=tf.int64, name=None))>
train data: <SkipDataset element_spec=(TensorSpec(shape=(192, 192, 3), dtype=tf.float32, name=None), TensorSpec(shape=(40,), dtype=tf.int64, name=None))>
this is the error
ValueError: in user code:
File "C:\Users\Dion\.conda\envs\KerASS\lib\site-packages\keras\engine\training.py", line 1021, in train_function *
return step_function(self, iterator)
File "C:\Users\Dion\.conda\envs\KerASS\lib\site-packages\keras\engine\training.py", line 1010, in step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "C:\Users\Dion\.conda\envs\KerASS\lib\site-packages\keras\engine\training.py", line 1000, in run_step **
outputs = model.train_step(data)
File "C:\Users\Dion\.conda\envs\KerASS\lib\site-packages\keras\engine\training.py", line 859, in train_step
y_pred = self(x, training=True)
File "C:\Users\Dion\.conda\envs\KerASS\lib\site-packages\keras\utils\traceback_utils.py", line 67, in error_handler
raise e.with_traceback(filtered_tb) from None
File "C:\Users\Dion\.conda\envs\KerASS\lib\site-packages\keras\engine\input_spec.py", line 264, in assert_input_compatibility
raise ValueError(f'Input {input_index} of layer "{layer_name}" is '
ValueError: Input 0 of layer "sequential_1" is incompatible with the layer: expected shape=(None, 192, 192, 3), found shape=(192, 192, 3)
Related
I'm working with the Google utterance dataset in spectrogram form. Each data point has dimension (160, 101). In my data loader, I used batch_size=128. Therefore, each batch has dimension (128, 160, 101).
I use a LeNet model with the following code as the model:
class LeNet(nn.Module):
def __init__(self):
super(LeNet, self).__init__()
self.conv1 = nn.Conv2d(1, 6, 5)
self.conv2 = nn.Conv2d(6, 16, 5)
self.fc1 = nn.Linear(16*5*5, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 30)
def forward(self, x):
out = F.relu(self.conv1(x))
out = F.max_pool2d(out, 2)
out = F.relu(self.conv2(out))
out = F.max_pool2d(out, 2)
out = out.view(out.size(0), -1)
out = F.relu(self.fc1(out))
out = F.relu(self.fc2(out))
out = self.fc3(out)
return out
I tried unsqueezing the data with dim=3, but got this error:
Traceback (most recent call last):
File "train_speech.py", line 359, in <module>
train_loss, reg_loss, train_acc, cost = train(epoch)
File "train_speech.py", line 258, in train
outputs = (net(inputs))['out']
File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/torch/nn/parallel/data_parallel.py", line 166, in forward
return self.module(*inputs[0], **kwargs[0])
File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/content/gdrive/My Drive/Colab Notebooks/mixup_erm-master/models/lenet.py", line 15, in forward
out = F.relu(self.conv1(x))
File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/conv.py", line 443, in forward
return self._conv_forward(input, self.weight, self.bias)
File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/conv.py", line 440, in _conv_forward
self.padding, self.dilation, self.groups)
RuntimeError: Given groups=1, weight of size [6, 1, 5, 5], expected input[128, 160, 101, 1] to have 1 channels, but got 160 channels instead
How do I fix this issue?
EDIT: New Error Message Below
torch.Size([128, 160, 101])
torch.Size([128, 1, 160, 101])
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:718: UserWarning: Named tensors and all their associated APIs are an experimental feature and subject to change. Please do not use them for anything important until they are released as stable. (Triggered internally at /pytorch/c10/core/TensorImpl.h:1156.)
return torch.max_pool2d(input, kernel_size, stride, padding, dilation, ceil_mode)
Traceback (most recent call last):
File "train_speech.py", line 363, in <module>
train_loss, reg_loss, train_acc, cost = train(epoch)
File "train_speech.py", line 262, in train
outputs = (net(inputs))['out']
IndexError: too many indices for tensor of dimension 2
I'm unsqueezing the data in each batch. The relevant section of my training code is below. inputs is analogous to x.
print(inputs.shape)
inputs = inputs.unsqueeze(1)
print(inputs.shape)
outputs = (net(inputs))['out']
Edit 2: New Error
Traceback (most recent call last):
File "train_speech.py", line 361, in <module>
train_loss, reg_loss, train_acc, cost = train(epoch)
File "train_speech.py", line 270, in train
loss.backward()
File "/usr/local/lib/python3.7/dist-packages/torch/_tensor.py", line 255, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph, inputs=inputs)
File "/usr/local/lib/python3.7/dist-packages/torch/autograd/__init__.py", line 149, in backward
allow_unreachable=True, accumulate_grad=True) # allow_unreachable flag
RuntimeError: Function AddmmBackward returned an invalid gradient at index 1 - got [128, 400] but expected shape compatible with [128, 13024]
Edit 3: Train Loop Below
def train(epoch):
print('\nEpoch: %d' % epoch)
net.train()
train_loss = 0
reg_loss = 0
correct = 0
total = 0
for batch_idx, (inputs, targets) in enumerate(trainloader):
if use_cuda:
inputs, targets = inputs.cuda(), targets.cuda()
inputs, targets_a, targets_b, lam,layer, cost = mixup_data(inputs, targets,
args.alpha,args.mixupBatch, use_cuda)
inputs, targets_a, targets_b = map(Variable, (inputs,
targets_a, targets_b))
outputs = net(inputs)
loss = mixup_criterion(criterion, outputs, targets_a, targets_b, lam)
train_loss += loss.item()
_, predicted = torch.max(outputs.data, 1)
total += targets.size(0)
correct += (lam * predicted.eq(targets_a.data).cpu().sum().float()
+ (1 - lam) * predicted.eq(targets_b.data).cpu().sum().float())
optimizer.zero_grad()
loss.backward()
optimizer.step()
return (train_loss/batch_idx, reg_loss/batch_idx, 100.*correct/total, cost/batch_idx)
You should expand on axis=1 a.k.a. the channel axis:
>>> x = x.unsqueeze(1)
If you're inside the dataset __getitem__, then it corresponds to axis=0.
I'm trying to train some data with CNN.
x_train.shape
(67197, 99, 81, 1)
y_train.shape
(67197, 12)
and trying to use Keras's Resnet method
import keras
import keras_resnet.models
input_shape = (98,81,1)
nclass = 12
x = keras.layers.Input(input_shape)
model = keras_resnet.models.ResNet50(x,classes=nclass)
model.compile("adam","categorical_crossentropy",["accuracy"])
model.fit(x_train,y_train,
batch_size = 300,
nb_epoch=5,
validation_data = (x_test,y_test),
shuffle = True,
)
but I got some shape error.
ValueError: Error when checking input: expected input_3 to have shape (None, 98, 81, 1) but got array with shape (67197, 99, 81, 1)
Its just a typo, your training data has shape (samples, 99, 81, 1), so the input shape should be (99, 81, 1), not (98, 81, 1). Its just off by one.
I was having an issue when trying to create a convolution-deconvolution network. The original image dimensions are 565 * 584 and I'm trying to produce a segmentation of 565 * 584.
While I didn't have an issue before with my network with 1024*1024 images, I have been having some issues with these dimensions. I am getting this issue when computing the gradient:
segmentation_result.shape: (?, 565, 584, 1), targets.shape: (?, 565, 584, 1)
Process Process-1:
Traceback (most recent call last):
\Python\Python35\lib\site-packages\tensorflow\python\framework\tensor_shape.py", line 558, in merge_with
self.assert_is_compatible_with(other)
\Python\Python35\lib\site-packages\tensorflow\python\framework\tensor_shape.py", line 106, in assert_is_compatible_with
other))
ValueError: Dimensions 565 and 566 are not compatible
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
\Python\Python35\lib\multiprocessing\process.py", line 249, in _bootstrap
self.run()
\Python\Python35\lib\multiprocessing\process.py", line 93, in run
self._target(*self._args, **self._kwargs)
.py", line 418, in train
network = Network(net_id = count, weight=pos_weight)
.py", line 199, in __init__
self.train_op = tf.train.AdamOptimizer().minimize(self.cost)
\Python\Python35\lib\site-packages\tensorflow\python\training\optimizer.py", line 315, in minimize
grad_loss=grad_loss)
\Python\Python35\lib\site-packages\tensorflow\python\training\optimizer.py", line 386, in compute_gradients
colocate_gradients_with_ops=colocate_gradients_with_ops)
\Python\Python35\lib\site-packages\tensorflow\python\ops\gradients_impl.py", line 560, in gradients
in_grad.set_shape(t_in.get_shape())
\Python\Python35\lib\site-packages\tensorflow\python\framework\ops.py", line 443, in set_shape
self._shape = self._shape.merge_with(shape)
\Python\Python35\lib\site-packages\tensorflow\python\framework\tensor_shape.py", line 561, in merge_with
raise ValueError("Shapes %s and %s are not compatible" % (self, other))
ValueError: Shapes (?, 565, 584, 64) and (?, 566, 584, 64) are not compatible
The entire network has 10 convolutional layers and 10 deconvolutional layers. Each deconvolutional layer is a reversed version of the forward layer. Here is an example of the code to produce the convolutional layer:
def create_layer_reversed(self, input, prev_layer=None):
net_id = self.net_id
print(net_id)
with tf.variable_scope('conv', reuse=False):
W = tf.get_variable('W{}_{}_'.format(self.name[-3:], net_id),
shape=(self.kernel_size, self.kernel_size, self.input_shape[3], self.output_channels))
b = tf.Variable(tf.zeros([W.get_shape().as_list()[2]]))
output = tf.nn.conv2d_transpose(
input, W,
tf.stack([tf.shape(input)[0], self.input_shape[1], self.input_shape[2], self.input_shape[3]]),
strides=[1,1,1,1], padding='SAME')
Conv2d.layer_index += 1
output.set_shape([None, self.input_shape[1], self.input_shape[2], self.input_shape[3]])
output = lrelu(tf.add(tf.contrib.layers.batch_norm(output), b))
return output
Dears, does anyone has an ideia why 'dropout_rate' and 'learning_rate' returne only 0 and does not search for the range I gave when I am doing a RandomizedSearchCV on the hyperparameters?
Here is my code for a ANN using keras/tensoflow:
# Create the model
def create_model(neurons = 1, init_mode = 'uniform', activation='relu', inputDim = 8792, dropout_rate=0.7, learn_rate=0.01, momentum=0, weight_constraint=0): #, learn_rate=0.01, momentum=0):
model = Sequential()
model.add(Dense(neurons, input_dim=inputDim, kernel_initializer=init_mode, activation=activation, kernel_constraint=maxnorm(weight_constraint), kernel_regularizer=regularizers.l2(0.001))) # one inner layer
#model.add(Dense(neurons, input_dim=inputDim, activation=activation)) # second inner layer
model.add(Dropout(dropout_rate))
model.add(Dense(1, activation='sigmoid'))
optimizer = RMSprop(lr=learn_rate)
# compile model
model.compile(loss='binary_crossentropy', optimizer=optimizer, metrics=['accuracy'])
return model
# model
model = KerasClassifier(build_fn=create_model, verbose=0)
# Define K-fold cross validation test harness
kfold = StratifiedKFold(n_splits=3, shuffle=True, random_state=seed)
for train, test in kfold.split(X_train, Y_train):
print("TRAIN:", train, "VALIDATION:", test)
# Define Hyperparameters
# specify parameters and distributions to sample from
from scipy.stats import randint as sp_randint
param_dist = {'neurons': sp_randint(300, 360), #, 175, 180, 185, 190, 195, 200],
'learn_rate': sp_randint (0.001, 0.01),
'batch_size': sp_randint(50, 60),
'epochs': sp_randint(20, 30),
'dropout_rate': sp_randint(0.2, 0.8),
'weight_constraint': sp_randint(3, 8)
}
# run randomized search
n_iter_search = 100
print("[INFO] Starting training digits")
print("[INFO] Tuning hyper-parameters for accuracy")
grid = RandomizedSearchCV(estimator=model, param_distributions=param_dist,
n_iter=n_iter_search, n_jobs=10, cv=kfold)
start = time.time()
grid_result = grid.fit(X_train, Y_train)
print("[INFO] GridSearch took {:.2f} seconds".format(time.time() - start))
My answer:
[INFO] GridSearch took 1164.39 seconds
[INFO] GridSearch best score 1.000000 using parameters: {'batch_size': 54, 'dropout_rate': 0, 'epochs': 20, 'learn_rate': 0, 'neurons': 331, 'weight_constraint': 7}
[INFO] Grid scores on development set:
0.614679 (0.034327) with: {'batch_size': 54, 'dropout_rate': 0, 'epochs': 29, 'learn_rate': 0, 'neurons': 354, 'weight_constraint': 6}
0.883792 (0.008650) with: {'batch_size': 53, 'dropout_rate': 0, 'epochs': 27, 'learn_rate': 0, 'neurons': 339, 'weight_constraint': 7}
0.256881 (0.012974) with: {'batch_size': 59, 'dropout_rate': 0, 'epochs': 27, 'learn_rate': 0, 'neurons': 308, 'weight_constraint': 4}
...
Thanks for helping.
0.2 and 0.8 are not integers, so when you use sp_randint(0.2, 0.8), these are converted to integers so its the same as sp_randint(0, 0). You have to use an equivalent function that generates floating point numbers, not integers.
For example, you can use a uniform distribution (uniform from scipy.stats) to generate real numbers.
Some style transfer examples that use Keras initialize the content, style and combination images and feed them into the first layer of VGG16.
However the Convolution2D objects do not seem to accept the set_input method.
input_tensor = K.concatenate([base_image,
style_reference_image,
combination_image], axis=0)
# build the VGG16 network with 3 images as input
first_layer = Convolution2D(64, 3, 3, activation='relu', name='conv1_1')
first_layer.set_input(input_tensor, shape)
model = Sequential()
model.add(first_layer)
model.add(Convolution2D(64, 3, 3, activation='relu', name='conv1_2', border_mode='same'))
model.add(pooling_func())
model.add(Convolution2D(128, 3, 3, activation='relu', name='conv2_1', border_mode='same'))
model.add(Convolution2D(128, 3, 3, activation='relu', name='conv2_2', border_mode='same'))
model.add(pooling_func())