Develop Reference

Error while training CNN for text classification in keras "ValueError: Input 0 is incompatible with layer"

I am building a prediction model for sequence data using conv1d layer provided by Keras. This is how I did
input_layer = Input(shape=(500,))
layer = Conv1D(128,5,activation="relu")(input_layer)
layer = MaxPooling1D(pool_size=2)(layer)
layer = Flatten()(layer)
layer = Dense(128, activation='relu')(layer)
output_layer = Dense(10, activation='softmax')(layer)
classifier = Model(input_layer, output_layer)
classifier.summary()
classifier.compile(optimizer=optimizers.Adam(), loss='sparse_categorical_crossentropy', metrics=['accuracy'])
return classifier
However, am facing the following error:
Traceback (most recent call last):
File "train.py", line 71, in <module>
classifier = create_cnn_model()
File "train.py", line 60, in create_cnn_model
layer = Conv1D(128,5, activation="relu")(input_layer)
File "C:\Python368\lib\site-packages\keras\backend\tensorflow_backend.py", line 75, in symbolic_fn
_wrapper
return func(*args, **kwargs)
File "C:\Python368\lib\site-packages\keras\engine\base_layer.py", line 446, in __call__
self.assert_input_compatibility(inputs)
File "C:\Python368\lib\site-packages\keras\engine\base_layer.py", line 342, in assert_input_compat
ibility
str(K.ndim(x)))
ValueError: Input 0 is incompatible with layer conv1d_1: expected ndim=3, found ndim=2
I think the input_shape in the first layer is not setup right. How to set it up?

Right, conv layers need 3 dimensional input.
I am assuming you have a univariate time series with 500 samples.
You need to write a function to split the time series into steps.
For example:
x y
[t-n,...,t-2,t-1] t
So you are basically using the last n values to predict the next value in your series.
Then your input shape will be [len(x), n, 1]

Dropout and BatchNormalization layers throw TypeError: Incompatible types: <dtype: 'variant'> vs. int32. Value is 1, model works without them

When using custom estimators in Tensorflow 2, when the model contains BatchNorm or Dropout layers, tf fails while building the graph with the following error. It works just fine when I comment out the Dropout and BatchNorm layers.
The model I use is a simple CNN model with two conv blocks and dense layer at the end:
def build_conv_block(x: Model, filter_map_count: int, name: str):
x = Conv2D(filter_map_count, (3, 3), name=f'{name}_conv_2d')(x)
x = BatchNormalization(name=f'{name}_bn')(x) <------- Error when not commented out
x = ReLU(name=f'{name}_relu')(x)
x = MaxPool2D((2, 2), name=f'{name}_max_pool_2d')(x)
x = Dropout(0.25, name=f'{name}_dropout')(x) <------- Error when not commented out
return x
def get_model(params):
input_image = Input(shape=params.input_shape)
x = build_conv_block(input_image, filter_map_count=64, name='layer_1')
x = build_conv_block(x, filter_map_count=128, name='layer_2')
x = Flatten(name='flatten_conv')(x)
output_pred = Dense(10, activation='softmax', name='output')(x)
model = Model(inputs=input_image, outputs=output_pred)
model.optimizer = Adam(learning_rate=params.learning_rate)
return model
I have a standard train_op in the model_fn that takes mnist images and labels as input and the class as output:
# Calculate gradients
with tf.GradientTape() as tape:
y_pred = model(features, training=training)
loss = tf.losses.categorical_crossentropy(labels, y_pred)
if mode == tf.estimator.ModeKeys.TRAIN:
gradients = tape.gradient(loss, model.trainable_variables)
train_op = model.optimizer.apply_gradients(zip(gradients, model.trainable_variables))
return tf.estimator.EstimatorSpec(mode, loss=loss, train_op=train_op)
Here's the traceback of the error I get:
Traceback (most recent call last):
File "F:/Projects/python/my_project/train.py", line 38, in <module>
tf.estimator.train_and_evaluate(estimator, train_spec=train_spec, eval_spec=eval_spec)
File "F:\Python\envs\tf2\lib\site-packages\tensorflow_estimator\python\estimator\training.py", line 473, in train_and_evaluate
return executor.run()
File "F:\Python\envs\tf2\lib\site-packages\tensorflow_estimator\python\estimator\training.py", line 613, in run
return self.run_local()
File "F:\Python\envs\tf2\lib\site-packages\tensorflow_estimator\python\estimator\training.py", line 714, in run_local
saving_listeners=saving_listeners)
File "F:\Python\envs\tf2\lib\site-packages\tensorflow_estimator\python\estimator\estimator.py", line 370, in train
loss = self._train_model(input_fn, hooks, saving_listeners)
File "F:\Python\envs\tf2\lib\site-packages\tensorflow_estimator\python\estimator\estimator.py", line 1160, in _train_model
return self._train_model_default(input_fn, hooks, saving_listeners)
File "F:\Python\envs\tf2\lib\site-packages\tensorflow_estimator\python\estimator\estimator.py", line 1190, in _train_model_default
features, labels, ModeKeys.TRAIN, self.config)
File "F:\Python\envs\tf2\lib\site-packages\tensorflow_estimator\python\estimator\estimator.py", line 1148, in _call_model_fn
model_fn_results = self._model_fn(features=features, **kwargs)
File "F:\Projects\python\my_project\model.py", line 62, in model_fn
gradients = tape.gradient(loss, model.trainable_variables)
File "F:\Python\envs\tf2\lib\site-packages\tensorflow_core\python\eager\backprop.py", line 1014, in gradient
unconnected_gradients=unconnected_gradients)
File "F:\Python\envs\tf2\lib\site-packages\tensorflow_core\python\eager\imperative_grad.py", line 76, in imperative_grad
compat.as_str(unconnected_gradients.value))
File "F:\Python\envs\tf2\lib\site-packages\tensorflow_core\python\eager\backprop.py", line 138, in _gradient_function
return grad_fn(mock_op, *out_grads)
File "F:\Python\envs\tf2\lib\site-packages\tensorflow_core\python\ops\cond_v2.py", line 120, in _IfGrad
true_graph, grads, util.unique_grad_fn_name(true_graph.name))
File "F:\Python\envs\tf2\lib\site-packages\tensorflow_core\python\ops\cond_v2.py", line 395, in _create_grad_func
func_graph=_CondGradFuncGraph(name, func_graph))
File "F:\Python\envs\tf2\lib\site-packages\tensorflow_core\python\framework\func_graph.py", line 915, in func_graph_from_py_func
func_outputs = python_func(*func_args, **func_kwargs)
File "F:\Python\envs\tf2\lib\site-packages\tensorflow_core\python\ops\cond_v2.py", line 394, in <lambda>
lambda: _grad_fn(func_graph, grads), [], {},
File "F:\Python\envs\tf2\lib\site-packages\tensorflow_core\python\ops\cond_v2.py", line 373, in _grad_fn
src_graph=func_graph)
File "F:\Python\envs\tf2\lib\site-packages\tensorflow_core\python\ops\gradients_util.py", line 550, in _GradientsHelper
gradient_uid)
File "F:\Python\envs\tf2\lib\site-packages\tensorflow_core\python\ops\gradients_util.py", line 175, in _DefaultGradYs
constant_op.constant(1, dtype=y.dtype, name="grad_ys_%d" % i)))
File "F:\Python\envs\tf2\lib\site-packages\tensorflow_core\python\framework\constant_op.py", line 227, in constant
allow_broadcast=True)
File "F:\Python\envs\tf2\lib\site-packages\tensorflow_core\python\framework\constant_op.py", line 265, in _constant_impl
allow_broadcast=allow_broadcast))
File "F:\Python\envs\tf2\lib\site-packages\tensorflow_core\python\framework\tensor_util.py", line 484, in make_tensor_proto
(dtype, nparray.dtype, values))
TypeError: Incompatible types: <dtype: 'variant'> vs. int32. Value is 1
It looks similar to the error mentioned in TF Issue #31894, but it doesn't seem to solve this problem. The TypeError does not tell much about where and why the error is happening and directly googling it does not help.

Although it may not be too obvious from the TypeError variant vs int32, if we carefully check the logs, we can see that the error occurs when finding gradients:
File "F:\Projects\python\my_project\model.py", line 62, in model_fn
gradients = tape.gradient(loss, model.trainable_variables)
Also, it should be noted that we get the same error even if one of them is present. So, if we try and analyze the common attributes in BatchNormalization and Dropout layer, both may seem to not come under the core layers, but when we look carefully, only those two layers in the model have a different train/test phase i.e. dropout doesn't zero out the values in test phase and batch norm uses a moving mean and variance during test phase.
Now the problem is narrowed down to using any layer that has a different train/test phase. This happens because tensorflow identifies if training mode is on or not using training parameter passed to the model.
This problem can be solved by using
y_pred = model(features, training=True)
when finding the gradients i.e. for the training phase and by using
y_pred = model(features, training=False)
otherwise i.e. for predict and eval phases.
Linked: Errors where moving mean is not updating is also reported, which can be solved by adding the same attribute.

conv2d in custom Keras loss function

I am trying to implement a custom loss function in Keras with TF backend based on the Laplacian of two images.
def blur_loss(y_true, y_pred):
#weighting of blur loss
alpha = 1
mae = losses.mean_absolute_error(y_true, y_pred)
lapKernel = K.constant([0, 1, 0, 1, -4, 1, 0, 1, 0],shape = [3, 3])
trueLap = K.conv2d(y_true, lapKernel)
predLap = K.conv2d(y_pred, lapKernel)
trueBlur = K.var(trueLap)
predBlur = K.var(predLap)
blurLoss = alpha * K.abs(trueBlur - predBlur)
loss = (1-alpha) * mae + alpha * blurLoss
return loss
When I try to compile the model I get this error
Traceback (most recent call last):
File "kitti_train.py", line 65, in <module>
model.compile(loss='mean_absolute_error', optimizer='adam', metrics=[blur_loss])
File "/home/ubuntu/.virtualenvs/dl4cv/lib/python3.5/site-packages/keras/engine/training.py", line 924, in compile
handle_metrics(output_metrics)
File "/home/ubuntu/.virtualenvs/dl4cv/lib/python3.5/site-packages/keras/engine/training.py", line 921, in handle_metrics
mask=masks[i])
File "/home/ubuntu/.virtualenvs/dl4cv/lib/python3.5/site-packages/keras/engine/training.py", line 450, in weighted
score_array = fn(y_true, y_pred)
File "/home/ubuntu/prednet/blur_loss.py", line 14, in blur_loss
trueLap = K.conv2d(y_true, lapKernel)
File "/home/ubuntu/.virtualenvs/dl4cv/lib/python3.5/site-packages/keras/backend/tensorflow_backend.py", line 3164, in conv2d
data_format='NHWC')
File "/home/ubuntu/.virtualenvs/dl4cv/lib/python3.5/site-packages/tensorflow/python/ops/nn_ops.py", line 655, in convolution
num_spatial_dims, strides, dilation_rate)
File "/home/ubuntu/.virtualenvs/dl4cv/lib/python3.5/site-packages/tensorflow/python/ops/nn_ops.py", line 483, in _get_strides_and_dilation_rate
(len(dilation_rate), num_spatial_dims))
ValueError: len(dilation_rate)=2 but should be 0
After reading other questions, my understanding is that this problem stems from the compilation using placeholder tensors for y_true and y_pred. I've tried checking if the inputs are placeholders and replacing them with zero tensors, but this gives me other errors.
How do I use a convolution (the image processing function, not a layer) in my loss function without getting these errors?

The problem here was a misunderstanding of the conv2d function which is not simply a 2-dimensional convolution. It is a batched 2-d convolution of multiple channels. So while you might expect a *2d function to accept 2-dimensional tensors, the input should actually 4 dimensions (batch_size, height, width, channels) and the filter should also be 4 dimensions (filter_height, filter_width, input_channels, output_channels). Details can be found in the TF docs

Cannot feed value of shape (1600,) for Tensor 'TargetsData/Y:0', which has shape '(?, 1)'

I'm trying to get into machine learning and I've decided on using tflearn for a start.
I used tflearn's quickstart guide to get the basics and tried using that neural network for a task I've set myself:
Predicting the age of abalones from their dimensions. For this I downloaded the according dataset as .csv from the UCI repository. The table is in this format:
SEX|LENGTH|DIAMETER|HEIGHT|WHOLE WEIGHT|SHUCKED WEIGHT|VISCERA WEIGHT|SHELL WEIGHT|RINGS
Since the age is the same as the number of rings, I imported the .csv like this:
data, labels = load_csv("abalone.csv", categorical_labels=False, has_header=False)
The task is to predict the number of rings based on the data, so I set up my input layer like this:
net = tflearn.input_data(shape=[None, 8])
Added four hidden layers with the default linear activation function:
net = tflearn.fully_connected(net, 320)
net = tflearn.fully_connected(net, 200)
net = tflearn.fully_connected(net, 200)
net = tflearn.fully_connected(net, 320)
And an output layer with one node since there is only one result (no. of rings):
net = tflearn.fully_connected(net, 1, activation="sigmoid")
net = tflearn.regression(net)
Now I initialize the model but during training the above error occurs:
model = tflearn.DNN(net)
model.fit(data, labels, n_epoch=1000, show_metric=True, batch_size=1600)
The entire exception:
Traceback (most recent call last):
File "D:\OneDrive\tensornet.py", line 34, in <module>
model.fit(data, labels, n_epoch=1000, show_metric=True, batch_size=1600)
File "C:\Python3\lib\site-packages\tflearn\models\dnn.py", line 215, in fit
callbacks=callbacks)
File "C:\Python3\lib\site-packages\tflearn\helpers\trainer.py", line 333, in fit
show_metric)
File "C:\Python3\lib\site-packages\tflearn\helpers\trainer.py", line 774, in _train
feed_batch)
File "C:\Python3\lib\site-packages\tensorflow\python\client\session.py", line 767, in run
run_metadata_ptr)
File "C:\Python3\lib\site-packages\tensorflow\python\client\session.py", line 944, in _run
% (np_val.shape, subfeed_t.name, str(subfeed_t.get_shape())))
ValueError: Cannot feed value of shape (1600,) for Tensor 'TargetsData/Y:0', which has shape '(?, 1)'
From what I understand, the exception occurs when trying to fit my labels (which are a 1600x1 Tensor) with my output layer. But I don't know how to fix this.

You need to add another axis to the labels so they'll have a (1600,1) shape instead of (1600,)
The simplest way to do it is like this:
labels = labels[:, np.newaxis]

Inserting data into regression network in keras

I am currently struggling to understand how i should train my regression network using keras. I am not sure how I should pass my input data to the network.
Both the input data and the output data is stored as a list of numpy arrays.
Each input numpy array is a matrix which has (400 rows, x columns)
Each output numpy array is a matrix which has (x number of rows, 13 columns)
So input dimension is 400 and output is 13.
But how do I pass each of these sets within the list to the training?
# Multilayer Perceptron
model = Sequential() # Feedforward
model.add(Dense(3, input_dim=400))
model.add(Activation('tanh'))
model.add(Dense(1))
model.compile('sgd', 'mse')
Just by parsing data into gives me this error message :
Traceback (most recent call last):
File "tensorflow_datapreprocess_mfcc_extraction_rnn.py", line 167, in <module>
model.fit(train_set_data,train_set_output,verbose=1)
File "/usr/local/lib/python2.7/dist-packages/keras/models.py", line 620, in fit
sample_weight=sample_weight)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 1034, in fit
batch_size=batch_size)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 961, in _standardize_user_data
exception_prefix='model input')
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 51, in standardize_input_data
'...')
Exception: Error when checking model input: the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 1 arrays but instead got the following list of 270 arrays: [array([[ -1.52587891e-04, 3.05175781e-05, -1.52587891e-04,
-5.18798828e-04, 3.05175781e-05, -3.96728516e-04,
1.52587891e-04, 3.35693359e-04, -9.15527344e-05,
3.3...