Can't fit data to 3d convolutional U-net Keras - machine-learning

I have a problem. I want to make 3D convolutional U-net. For this purpose I'm using Keras.
My data are MRI images from Data Science Bowl 2017 Competition. All MRI's were saved in numpy arrays (all pixels are scaled from 0 to 1) with shape:
data_ch.shape
(94, 50, 50, 50, 1)
94 - patients, 50 MRI slices of 50x50 images, 1 channel:
I want to make 3D Convolutional U-net, so the inputs and outputs of this net are same 3d arrays.
The 3D U-net:
input_img= Input(shape=(data_ch.shape[1], data_ch.shape[2], data_ch.shape[3], data_ch.shape[4]))
x=Conv3D(filters=8, kernel_size=(3, 3, 3), activation='relu', padding='same')(input_img)
x=MaxPooling3D(pool_size=(2, 2, 2), padding='same')(x)
x=Conv3D(filters=8, kernel_size=(3, 3, 3), activation='relu', padding='same')(x)
x=MaxPooling3D(pool_size=(2, 2, 2), padding='same')(x)
x=UpSampling3D(size=(2, 2, 2))(x)
x=Conv3D(filters=8, kernel_size=(3, 3, 3), activation='relu', padding='same')(x) # PADDING IS NOT THE SAME!!!!!
x=UpSampling3D(size=(2, 2, 2))(x)
x=Conv3D(filters=1, kernel_size=(3, 3, 3), activation='sigmoid')(x)
model=Model(input_img, x)
model.compile(optimizer='adadelta', loss='binary_crossentropy')
model.summary()
Layer (type) Output Shape Param #
=================================================================
input_5 (InputLayer) (None, 50, 50, 50, 1) 0
_________________________________________________________________
conv3d_27 (Conv3D) (None, 50, 50, 50, 8) 224
_________________________________________________________________
max_pooling3d_12 (MaxPooling (None, 25, 25, 25, 8) 0
_________________________________________________________________
conv3d_28 (Conv3D) (None, 25, 25, 25, 8) 1736
_________________________________________________________________
max_pooling3d_13 (MaxPooling (None, 13, 13, 13, 8) 0
_________________________________________________________________
up_sampling3d_12 (UpSampling (None, 26, 26, 26, 8) 0
_________________________________________________________________
conv3d_29 (Conv3D) (None, 26, 26, 26, 8) 1736
_________________________________________________________________
up_sampling3d_13 (UpSampling (None, 52, 52, 52, 8) 0
_________________________________________________________________
conv3d_30 (Conv3D) (None, 50, 50, 50, 1) 217
=================================================================
Total params: 3,913
Trainable params: 3,913
Non-trainable params: 0
But, when I attempted to fit data to this net:
model.fit(data_ch, data_ch, epochs=1, batch_size=10, shuffle=True, verbose=1)
the program displayed an error:
ValueError Traceback (most recent call last)
C:\Users\Taranov\Anaconda3\lib\site-packages\theano\compile\function_module.py in __call__(self, *args, **kwargs)
883 outputs =\
--> 884 self.fn() if output_subset is None else\
885 self.fn(output_subset=output_subset)
ValueError: CudaNdarray_CopyFromCudaNdarray: need same dimensions for dim 1, destination=13, source=14
During handling of the above exception, another exception occurred:
ValueError Traceback (most recent call last)
<ipython-input-26-b334d38d9608> in <module>()
----> 1 model.fit(data_ch, data_ch, epochs=1, batch_size=10, shuffle=True, verbose=1)
C:\Users\Taranov\Anaconda3\lib\site-packages\keras\engine\training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, **kwargs)
1496 val_f=val_f, val_ins=val_ins, shuffle=shuffle,
1497 callback_metrics=callback_metrics,
-> 1498 initial_epoch=initial_epoch)
1499
1500 def evaluate(self, x, y, batch_size=32, verbose=1, sample_weight=None):
C:\Users\Taranov\Anaconda3\lib\site-packages\keras\engine\training.py in _fit_loop(self, f, ins, out_labels, batch_size, epochs, verbose, callbacks, val_f, val_ins, shuffle, callback_metrics, initial_epoch)
1150 batch_logs['size'] = len(batch_ids)
1151 callbacks.on_batch_begin(batch_index, batch_logs)
-> 1152 outs = f(ins_batch)
1153 if not isinstance(outs, list):
1154 outs = [outs]
C:\Users\Taranov\Anaconda3\lib\site-packages\keras\backend\theano_backend.py in __call__(self, inputs)
1156 def __call__(self, inputs):
1157 assert isinstance(inputs, (list, tuple))
-> 1158 return self.function(*inputs)
1159
1160
C:\Users\Taranov\Anaconda3\lib\site-packages\theano\compile\function_module.py in __call__(self, *args, **kwargs)
896 node=self.fn.nodes[self.fn.position_of_error],
897 thunk=thunk,
--> 898 storage_map=getattr(self.fn, 'storage_map', None))
899 else:
900 # old-style linkers raise their own exceptions
C:\Users\Taranov\Anaconda3\lib\site-packages\theano\gof\link.py in raise_with_op(node, thunk, exc_info, storage_map)
323 # extra long error message in that case.
324 pass
--> 325 reraise(exc_type, exc_value, exc_trace)
326
327
C:\Users\Taranov\Anaconda3\lib\site-packages\six.py in reraise(tp, value, tb)
683 value = tp()
684 if value.__traceback__ is not tb:
--> 685 raise value.with_traceback(tb)
686 raise value
687
C:\Users\Taranov\Anaconda3\lib\site-packages\theano\compile\function_module.py in __call__(self, *args, **kwargs)
882 try:
883 outputs =\
--> 884 self.fn() if output_subset is None else\
885 self.fn(output_subset=output_subset)
886 except Exception:
ValueError: CudaNdarray_CopyFromCudaNdarray: need same dimensions for dim 1, destination=13, source=14
Apply node that caused the error: GpuAlloc(GpuDimShuffle{0,2,x,3,4,1}.0, Shape_i{0}.0, TensorConstant{13}, TensorConstant{2}, TensorConstant{13}, TensorConstant{13}, TensorConstant{8})
Toposort index: 163
Inputs types: [CudaNdarrayType(float32, (False, False, True, False, False, False)), TensorType(int64, scalar), TensorType(int64, scalar), TensorType(int8, scalar), TensorType(int64, scalar), TensorType(int64, scalar), TensorType(int64, scalar)]
Inputs shapes: [(10, 14, 1, 14, 14, 8), (), (), (), (), (), ()]
Inputs strides: [(21952, 196, 0, 14, 1, 2744), (), (), (), (), (), ()]
Inputs values: ['not shown', array(10, dtype=int64), array(13, dtype=int64), array(2, dtype=int8), array(13, dtype=int64), array(13, dtype=int64), array(8, dtype=int64)]
Outputs clients: [[GpuReshape{5}(GpuAlloc.0, MakeVector{dtype='int64'}.0)]]
HINT: Re-running with most Theano optimization disabled could give you a back-trace of when this node was created. This can be done with by setting the Theano flag 'optimizer=fast_compile'. If that does not work, Theano optimizations can be disabled with 'optimizer=None'.
HINT: Use the Theano flag 'exception_verbosity=high' for a debugprint and storage map footprint of this apply node.
I tried to follow recommendations and use theano flags:
import theano
import os
os.environ["THEANO_FLAGS"] = "mode=FAST_RUN,device=gpu,floatX=float32, optimizer='None',exception_verbosity=high"
But it still doesn't work.
Could you help me?
Many thanks!

Ok.... that sounds weird, but MaxPooling3D has some kind of bug with padding='same'. So I wrote your code without it, and added an initial padding just to make your dimensions compatible:
import keras.backend as K
inputShape = (data_ch.shape[1], data_ch.shape[2], data_ch.shape[3], data_ch.shape[4])
paddedShape = (data_ch.shape[1]+2, data_ch.shape[2]+2, data_ch.shape[3]+2, data_ch.shape[4])
#initial padding
input_img= Input(shape=inputShape)
x = Lambda(lambda x: K.spatial_3d_padding(x, padding=((1, 1), (1, 1), (1, 1))),
output_shape=paddedShape)(input_img) #Lambda layers require output_shape
#your original code without padding for MaxPooling layers (replace input_img with x)
x=Conv3D(filters=8, kernel_size=3, activation='relu', padding='same')(x)
x=MaxPooling3D(pool_size=2)(x)
x=Conv3D(filters=8, kernel_size=3, activation='relu', padding='same')(x)
x=MaxPooling3D(pool_size=2)(x)
x=UpSampling3D(size=2)(x)
x=Conv3D(filters=8, kernel_size=3, activation='relu', padding='same')(x) # PADDING IS NOT THE SAME!!!!!
x=UpSampling3D(size=2)(x)
x=Conv3D(filters=1, kernel_size=3, activation='sigmoid')(x)
model=Model(input_img, x)
model.compile(optimizer='adadelta', loss='binary_crossentropy')
model.summary()
print(model.predict(data_ch)[1])
model.fit(data_ch,data_ch,epochs=1,verbose=2,batch_size=10)

Try reducing the batch size to something like 2, and if you see, your network needs more GPU, So try upgrading that as well.

Related

Trained an convoluted autoencoder. Now need help extracting the feature space

I built an autoencoder using my own data set of about 32k images. I did a 75/25 split for training/testing, and I was able to get results I'm happy with.
Now I want to be able to extract the feature space and map them to every image in my dataset and to new data that wasn't tested. I couldn't find a tutorial online that delved into using the encoder as a feature space. All I could find was to build the full network.
My code:
> input_img = Input(shape=(200, 200, 1))
# encoder part of the model (increased filter lyaer after each filter)
x = Conv2D(16, (3, 3), activation='relu', padding='same')(input_img)
x = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(32, (3, 3), activation='relu', padding='same')(x)
x = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(64, (3, 3), activation='relu', padding='same')(x)
x = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(128, (3, 3), activation='relu', padding='same')(x)
encoded = MaxPooling2D((2, 2), padding='same')(x)
# decoder part of the model (went backwards from the encoder)
x = Conv2D(128, (3, 3), activation='relu', padding='same')(encoded)
x = UpSampling2D((2, 2))(x)
x = Conv2D(64, (3, 3), activation='relu', padding='same')(x)
x = UpSampling2D((2, 2))(x)
x = Conv2D(32, (3, 3), activation='relu', padding='same')(x)
x = UpSampling2D((2, 2))(x)
x = Conv2D(16, (3, 3), activation='relu', padding='same')(x)
x = UpSampling2D((2, 2))(x)
x = Conv2D(1, (3, 3), activation='sigmoid', padding='same')(x)
decoded = Cropping2D(cropping=((8,0), (8,0)), data_format=None)(x)
autoencoder = Model(input_img, decoded)
autoencoder.compile(optimizer='adam', loss='binary_crossentropy')
autoencoder.summary()
Here's my net setup if anybody is interested:
Model: "model_22"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_23 (InputLayer) (None, 200, 200, 1) 0
_________________________________________________________________
conv2d_186 (Conv2D) (None, 200, 200, 16) 160
_________________________________________________________________
max_pooling2d_83 (MaxPooling (None, 100, 100, 16) 0
_________________________________________________________________
conv2d_187 (Conv2D) (None, 100, 100, 32) 4640
_________________________________________________________________
max_pooling2d_84 (MaxPooling (None, 50, 50, 32) 0
_________________________________________________________________
conv2d_188 (Conv2D) (None, 50, 50, 64) 18496
_________________________________________________________________
max_pooling2d_85 (MaxPooling (None, 25, 25, 64) 0
_________________________________________________________________
conv2d_189 (Conv2D) (None, 25, 25, 128) 73856
_________________________________________________________________
max_pooling2d_86 (MaxPooling (None, 13, 13, 128) 0
_________________________________________________________________
conv2d_190 (Conv2D) (None, 13, 13, 128) 147584
_________________________________________________________________
up_sampling2d_82 (UpSampling (None, 26, 26, 128) 0
_________________________________________________________________
conv2d_191 (Conv2D) (None, 26, 26, 64) 73792
_________________________________________________________________
up_sampling2d_83 (UpSampling (None, 52, 52, 64) 0
_________________________________________________________________
conv2d_192 (Conv2D) (None, 52, 52, 32) 18464
_________________________________________________________________
up_sampling2d_84 (UpSampling (None, 104, 104, 32) 0
_________________________________________________________________
conv2d_193 (Conv2D) (None, 104, 104, 16) 4624
_________________________________________________________________
up_sampling2d_85 (UpSampling (None, 208, 208, 16) 0
_________________________________________________________________
conv2d_194 (Conv2D) (None, 208, 208, 1) 145
_________________________________________________________________
cropping2d_2 (Cropping2D) (None, 200, 200, 1) 0
=================================================================
Total params: 341,761
Trainable params: 341,761
Non-trainable params: 0
Then my training:
autoencoder.fit(train, train,
epochs=3,
batch_size=128,
shuffle=True,
validation_data=(test, test))
My results:
Train on 23412 samples, validate on 7805 samples
Epoch 1/3
23412/23412 [==============================] - 773s 33ms/step - loss: 0.0620 - val_loss: 0.0398
Epoch 2/3
23412/23412 [==============================] - 715s 31ms/step - loss: 0.0349 - val_loss: 0.0349
Epoch 3/3
23412/23412 [==============================] - 753s 32ms/step - loss: 0.0314 - val_loss: 0.0319
Rather not share the images, but they look well reconstructed.
Thank you for all and any help!
Not sure if I fully understand your questions, but do you want to get the resulting feature space for every image you trained on as well as others. Why not just do this?
Name your encoded layer in your autoencoder architecture as 'embedding.' Then create the encoder the following way:
embedding_layer = autoencoder.get_layer(name='embedding').output
encoder = Model(input_img,embedding_layer)

ValueError: Input 0 is incompatible with layer conv1d_1: expected ndim=3, found ndim=4

I am building a prediction model for the sequence data using conv1d layer provided by Keras. This is how I did
model= Sequential()
model.add(Conv1D(60,32, strides=1, activation='relu',padding='causal',input_shape=(None,64,1)))
model.add(Conv1D(80,10, strides=1, activation='relu',padding='causal'))
model.add(Dropout(0.25))
model.add(Conv1D(100,5, strides=1, activation='relu',padding='causal'))
model.add(MaxPooling1D(1))
model.add(Dropout(0.25))
model.add(Dense(300,activation='relu'))
model.add(Dense(1,activation='relu'))
print(model.summary())
However, the debugging information has
Traceback (most recent call last):
File "processing_2a_1.py", line 96, in <module>
model.add(Conv1D(60,32, strides=1, activation='relu',padding='causal',input_shape=(None,64,1)))
File "build/bdist.linux-x86_64/egg/keras/models.py", line 442, in add
File "build/bdist.linux-x86_64/egg/keras/engine/topology.py", line 558, in __call__
File "build/bdist.linux-x86_64/egg/keras/engine/topology.py", line 457, in assert_input_compatibility
ValueError: Input 0 is incompatible with layer conv1d_1: expected ndim=3, found ndim=4
The training data and validation data shape are as follows
('X_train shape ', (1496000, 64, 1))
('Y_train shape ', (1496000, 1))
('X_val shape ', (374000, 64, 1))
('Y_val shape ', (374000, 1))
I think the input_shape in the first layer was not setup right. How to set it up?
Update: After using input_shape=(64,1), I got the following error message, even though the model summary runs through
________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv1d_1 (Conv1D) (None, 64, 60) 1980
_________________________________________________________________
conv1d_2 (Conv1D) (None, 64, 80) 48080
_________________________________________________________________
dropout_1 (Dropout) (None, 64, 80) 0
_________________________________________________________________
conv1d_3 (Conv1D) (None, 64, 100) 40100
_________________________________________________________________
max_pooling1d_1 (MaxPooling1 (None, 64, 100) 0
_________________________________________________________________
dropout_2 (Dropout) (None, 64, 100) 0
_________________________________________________________________
dense_1 (Dense) (None, 64, 300) 30300
_________________________________________________________________
dense_2 (Dense) (None, 64, 1) 301
=================================================================
Total params: 120,761
Trainable params: 120,761
Non-trainable params: 0
_________________________________________________________________
None
Traceback (most recent call last):
File "processing_2a_1.py", line 125, in <module>
history=model.fit(X_train, Y_train, batch_size=batch_size, validation_data=(X_val,Y_val), epochs=nr_of_epochs,verbose=2)
File "build/bdist.linux-x86_64/egg/keras/models.py", line 871, in fit
File "build/bdist.linux-x86_64/egg/keras/engine/training.py", line 1524, in fit
File "build/bdist.linux-x86_64/egg/keras/engine/training.py", line 1382, in _standardize_user_data
File "build/bdist.linux-x86_64/egg/keras/engine/training.py", line 132, in _standardize_input_data
ValueError: Error when checking target: expected dense_2 to have 3 dimensions, but got array with shape (1496000, 1)
You should either change input_shape to
input_shape=(64,1)
... or use batch_input_shape:
batch_input_shape=(None, 64, 1)
This discussion explains the difference between the two in keras in detail.
I had the same issue. I found expanding the dimensions of the input data fixed it using tf.expand_dims
x = expand_dims(x, axis=-1)
I my case I wanted to use Conv2D on a single 20*32 feature map, and did:
print(kws_x_train.shape) # (8000,20,32)
model = tf.keras.models.Sequential([
tf.keras.layers.Conv2D(16, (3, 8), input_shape=(20,32)),
])
...
model.fit(kws_x_train, kws_y_train, epochs=15)
which gives the expected ndim=4, found ndim=3. Full shape received: [None, 20, 32]. However you need to tell Conv2D that there is only 1 feature map, and add an extra dimension to the input vector. This worked:
kws_x_train2 = kws_x_train.reshape(kws_x_train.shape + (1,))
print(kws_x_train2.shape) # (8000,20,32,1)
model = tf.keras.models.Sequential([
tf.keras.layers.Conv2D(16, (3, 8), input_shape=(20,32,1)),
])
...
model.fit(kws_x_train2, kws_y_train, epochs=15)

Input dimension mismatch in Keras

Hi Can anyone help me out with the error, I have seemed to search through the documentation but to no avail.
The aim is to predict a time series. I have used a dummy data shape = (N, timesteps, features). I wish to predict x_2 from x_1, x_3 from x_2 and so on till x_11 from x_10 using LSTM. (Any suggestion to do it better is welcome). The output (below) shows the expected output shapes which seem correct. However, the error mentions an input dimension mismatch. As per documentation, I can't seem to find the problem.
import numpy as np
N = 13*12;
T = 10;
F = 3;
X = np.random.rand(N, T, F);
Y = np.random.rand(N, 1, F);
Y = np.concatenate((X[:,1:T,:], Y), axis=1);
import keras
from keras.models import Model
from keras.layers import Dense, Input, LSTM, Lambda, concatenate, Dropout
from keras.optimizers import Adam, SGD
from keras import regularizers
from keras.metrics import categorical_accuracy
from keras.models import load_model
input_ = Input(shape = (T, F), name ='input');
x = Dense(15, activation='sigmoid', name='fc1')(input_);
x = LSTM(25, return_sequences=True, activation='tanh', name='lstm')(x);
x = Dense(F, activation='sigmoid', name='fc2')(x);
model = Model(input_, x, name='dummy');
model.compile(optimizer='rmsprop', loss='mse', metrics=['accuracy']);
print(model.input_shape); print(X.shape);
print(model.output_shape); print(Y.shape);
print(model.summary());
model.fit(X, Y, batch_size = 13, epochs=30, validation_split=0.20, shuffle=False);
The error comes as
Using Theano backend.
(None, 10, 3)
(156, 10, 3)
(None, 10, 3)
(156, 10, 3)
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input (InputLayer) (None, 10, 3) 0
_________________________________________________________________
fc1 (Dense) (None, 10, 15) 60
_________________________________________________________________
lstm (LSTM) (None, 10, 25) 4100
_________________________________________________________________
fc2 (Dense) (None, 10, 3) 78
=================================================================
Total params: 4,238
Trainable params: 4,238
Non-trainable params: 0
_________________________________________________________________
None
Train on 124 samples, validate on 32 samples
Epoch 1/30
Traceback (most recent call last):
File "C:\Anaconda3\lib\site-packages\theano\compile\function_module.py", line 903, in __call__
self.fn() if output_subset is None else\
ValueError: Input dimension mis-match. (input[0].shape[1] = 10, input[1].shape[1] = 15)
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "b.py", line 34, in <module>
model.fit(X, Y, batch_size = 13, epochs=30, validation_split=0.20, shuffle=False);
File "C:\Anaconda3\lib\site-packages\keras\engine\training.py", line 1498, in fit
initial_epoch=initial_epoch)
File "C:\Anaconda3\lib\site-packages\keras\engine\training.py", line 1152, in _fit_loop
outs = f(ins_batch)
File "C:\Anaconda3\lib\site-packages\keras\backend\theano_backend.py", line 1158, in __call__
return self.function(*inputs)
File "C:\Anaconda3\lib\site-packages\theano\compile\function_module.py", line 917, in __call__
storage_map=getattr(self.fn, 'storage_map', None))
File "C:\Anaconda3\lib\site-packages\theano\gof\link.py", line 325, in raise_with_op
reraise(exc_type, exc_value, exc_trace)
File "C:\Anaconda3\lib\site-packages\six.py", line 692, in reraise
raise value.with_traceback(tb)
File "C:\Anaconda3\lib\site-packages\theano\compile\function_module.py", line 903, in __call__
self.fn() if output_subset is None else\
ValueError: Input dimension mis-match. (input[0].shape[1] = 10, input[1].shape[1] = 15)
Apply node that caused the error: Elemwise{Add}[(0, 0)](Reshape{3}.0, InplaceDimShuffle{x,0,x}.0)
Toposort index: 98
Inputs types: [TensorType(float32, 3D), TensorType(float32, (True, False, True))]
Inputs shapes: [(13, 10, 15), (1, 15, 1)]
Inputs strides: [(600, 60, 4), (60, 4, 4)]
Inputs values: ['not shown', 'not shown']
Outputs clients: [[Reshape{2}(Elemwise{Add}[(0, 0)].0, TensorConstant{[-1 15]}), Elemwise{Composite{((i0 + i1 + i2
+ i3) * scalar_sigmoid(i4) * (i5 - scalar_sigmoid(i4)))}}[(0, 0)](Reshape{3}.0, Reshape{3}.0, Reshape{3}.0, Reshape
{3}.0, Elemwise{Add}[(0, 0)].0, TensorConstant{(1, 1, 1) of 1.0})]]
HINT: Re-running with most Theano optimization disabled could give you a back-trace of when this node was created.
This can be done with by setting the Theano flag 'optimizer=fast_compile'. If that does not work, Theano optimizati
ons can be disabled with 'optimizer=None'.
HINT: Use the Theano flag 'exception_verbosity=high' for a debugprint and storage map footprint of this apply node.
I am unable to understand the error as to why the input shape would be (1,15,1) in the error and what are the 2 inputs which theano mentions?
The theano version I use is 0.9.0 and keras version is 2.0.4. If I rather use no features(F), the code runs smoothly.
Edit 1: batch size is 13, just for clarity in error log. Removing it also gives the exact same error.

keras autoencoder "Error when checking target"

i'm trying to adapt the 2d convolutional autoencoder example from the keras website: https://blog.keras.io/building-autoencoders-in-keras.html
to my own case where i use 1d inputs:
from keras.layers import Input, Dense, Conv1D, MaxPooling1D, UpSampling1D
from keras.models import Model
from keras import backend as K
import scipy as scipy
import numpy as np
mat = scipy.io.loadmat('edata.mat')
emat = mat['edata']
input_img = Input(shape=(64,1)) # adapt this if using `channels_first` image data format
x = Conv1D(32, (9), activation='relu', padding='same')(input_img)
x = MaxPooling1D((4), padding='same')(x)
x = Conv1D(16, (9), activation='relu', padding='same')(x)
x = MaxPooling1D((4), padding='same')(x)
x = Conv1D(8, (9), activation='relu', padding='same')(x)
encoded = MaxPooling1D(4, padding='same')(x)
x = Conv1D(8, (9), activation='relu', padding='same')(encoded)
x = UpSampling1D((4))(x)
x = Conv1D(16, (9), activation='relu', padding='same')(x)
x = UpSampling1D((4))(x)
x = Conv1D(32, (9), activation='relu')(x)
x = UpSampling1D((4))(x)
decoded = Conv1D(1, (9), activation='sigmoid', padding='same')(x)
autoencoder = Model(input_img, decoded)
autoencoder.compile(optimizer='adadelta', loss='binary_crossentropy')
x_train = emat[:,0:80000]
x_train = np.reshape(x_train, (x_train.shape[1], 64, 1))
x_test = emat[:,80000:120000]
x_test = np.reshape(x_test, (x_test.shape[1], 64, 1))
from keras.callbacks import TensorBoard
autoencoder.fit(x_train, x_train,
epochs=50,
batch_size=128,
shuffle=True,
validation_data=(x_test, x_test),
callbacks=[TensorBoard(log_dir='/tmp/autoencoder')])
however, i receive this error when i try to run the autoencoder.fit():
ValueError: Error when checking target: expected conv1d_165 to have
shape (None, 32, 1) but got array with shape (80000, 64, 1)
i know i'm probably doing something wrong when i set up my layers, i just changed the maxpool and conv2d sizes to a 1d form...i have very little experience with keras or autoencoders, anyone see what i'm doing wrong?
thanks
EDIT:
the error when i run it on a fresh console:
ValueError: Error when checking target: expected conv1d_7 to have
shape (None, 32, 1) but got array with shape (80000, 64, 1)
here is the output of autoencoder.summary()
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) (None, 64, 1) 0
_________________________________________________________________
conv1d_1 (Conv1D) (None, 64, 32) 320
_________________________________________________________________
max_pooling1d_1 (MaxPooling1 (None, 16, 32) 0
_________________________________________________________________
conv1d_2 (Conv1D) (None, 16, 16) 4624
_________________________________________________________________
max_pooling1d_2 (MaxPooling1 (None, 4, 16) 0
_________________________________________________________________
conv1d_3 (Conv1D) (None, 4, 8) 1160
_________________________________________________________________
max_pooling1d_3 (MaxPooling1 (None, 1, 8) 0
_________________________________________________________________
conv1d_4 (Conv1D) (None, 1, 8) 584
_________________________________________________________________
up_sampling1d_1 (UpSampling1 (None, 4, 8) 0
_________________________________________________________________
conv1d_5 (Conv1D) (None, 4, 16) 1168
_________________________________________________________________
up_sampling1d_2 (UpSampling1 (None, 16, 16) 0
_________________________________________________________________
conv1d_6 (Conv1D) (None, 8, 32) 4640
_________________________________________________________________
up_sampling1d_3 (UpSampling1 (None, 32, 32) 0
_________________________________________________________________
conv1d_7 (Conv1D) (None, 32, 1) 289
=================================================================
Total params: 12,785
Trainable params: 12,785
Non-trainable params: 0
_________________________________________________________________
Since the autoencoder output should reconstruct the input, a minimum requirement is that their dimensions should match, right?
Looking at your autoencoder.summary(), it is easy to confirm that this is not the case: your input is of shape (64,1), while the output of your last convolutional layer conv1d_7 is (32,1) (we ignore the None in the first dimension, since they refer to the batch size).
Let's have a look at the example in the Keras blog you link to (it is a 2D autoencoder, but the idea is the same):
from keras.layers import Input, Dense, Conv2D, MaxPooling2D, UpSampling2D
from keras.models import Model
from keras import backend as K
input_img = Input(shape=(28, 28, 1)) # adapt this if using `channels_first` image data format
x = Conv2D(16, (3, 3), activation='relu', padding='same')(input_img)
x = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
x = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
encoded = MaxPooling2D((2, 2), padding='same')(x)
# at this point the representation is (4, 4, 8) i.e. 128-dimensional
x = Conv2D(8, (3, 3), activation='relu', padding='same')(encoded)
x = UpSampling2D((2, 2))(x)
x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
x = UpSampling2D((2, 2))(x)
x = Conv2D(16, (3, 3), activation='relu')(x)
x = UpSampling2D((2, 2))(x)
decoded = Conv2D(1, (3, 3), activation='sigmoid', padding='same')(x)
autoencoder = Model(input_img, decoded)
autoencoder.compile(optimizer='adadelta', loss='binary_crossentropy')
Here is the result of autoencoder.summary() in this case:
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) (None, 28, 28, 1) 0
_________________________________________________________________
conv2d_1 (Conv2D) (None, 28, 28, 16) 160
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 14, 14, 16) 0
_________________________________________________________________
conv2d_2 (Conv2D) (None, 14, 14, 8) 1160
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 7, 7, 8) 0
_________________________________________________________________
conv2d_3 (Conv2D) (None, 7, 7, 8) 584
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 4, 4, 8) 0
_________________________________________________________________
conv2d_4 (Conv2D) (None, 4, 4, 8) 584
_________________________________________________________________
up_sampling2d_1 (UpSampling2 (None, 8, 8, 8) 0
_________________________________________________________________
conv2d_5 (Conv2D) (None, 8, 8, 8) 584
_________________________________________________________________
up_sampling2d_2 (UpSampling2 (None, 16, 16, 8) 0
_________________________________________________________________
conv2d_6 (Conv2D) (None, 14, 14, 16) 1168
_________________________________________________________________
up_sampling2d_3 (UpSampling2 (None, 28, 28, 16) 0
_________________________________________________________________
conv2d_7 (Conv2D) (None, 28, 28, 1) 145
=================================================================
Total params: 4,385
Trainable params: 4,385
Non-trainable params: 0
It is easy to confirm that here the dimensions of the input and the output (last convolutional layer conv2d_7) are indeed both (28, 28, 1).
So, the summary() method is your friend when building autoencoders; you should experiment with the parameters until you are sure that you produce an output of the same dimensionality as your input. I managed to do so with your autoencoder simply by changing the size argument of the last UpSampling1D layer from 4 to 8:
input_img = Input(shape=(64,1))
x = Conv1D(32, (9), activation='relu', padding='same')(input_img)
x = MaxPooling1D((4), padding='same')(x)
x = Conv1D(16, (9), activation='relu', padding='same')(x)
x = MaxPooling1D((4), padding='same')(x)
x = Conv1D(8, (9), activation='relu', padding='same')(x)
encoded = MaxPooling1D(4, padding='same')(x)
x = Conv1D(8, (9), activation='relu', padding='same')(encoded)
x = UpSampling1D((4))(x)
x = Conv1D(16, (9), activation='relu', padding='same')(x)
x = UpSampling1D((4))(x)
x = Conv1D(32, (9), activation='relu')(x)
x = UpSampling1D((8))(x) ## <-- change here (was 4)
decoded = Conv1D(1, (9), activation='sigmoid', padding='same')(x)
autoencoder = Model(input_img, decoded)
autoencoder.compile(optimizer='adadelta', loss='binary_crossentropy')
In which case, the autoencoder.summary() becomes:
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) (None, 64, 1) 0
_________________________________________________________________
conv1d_1 (Conv1D) (None, 64, 32) 320
_________________________________________________________________
max_pooling1d_1 (MaxPooling1 (None, 16, 32) 0
_________________________________________________________________
conv1d_2 (Conv1D) (None, 16, 16) 4624
_________________________________________________________________
max_pooling1d_2 (MaxPooling1 (None, 4, 16) 0
_________________________________________________________________
conv1d_3 (Conv1D) (None, 4, 8) 1160
_________________________________________________________________
max_pooling1d_3 (MaxPooling1 (None, 1, 8) 0
_________________________________________________________________
conv1d_4 (Conv1D) (None, 1, 8) 584
_________________________________________________________________
up_sampling1d_1 (UpSampling1 (None, 4, 8) 0
_________________________________________________________________
conv1d_5 (Conv1D) (None, 4, 16) 1168
_________________________________________________________________
up_sampling1d_2 (UpSampling1 (None, 16, 16) 0
_________________________________________________________________
conv1d_6 (Conv1D) (None, 8, 32) 4640
_________________________________________________________________
up_sampling1d_3 (UpSampling1 (None, 64, 32) 0
_________________________________________________________________
conv1d_7 (Conv1D) (None, 64, 1) 289
=================================================================
Total params: 12,785
Trainable params: 12,785
Non-trainable params: 0
with the dimensionality of your input and output matched, as it should be...

Issue with Keras input array when implementing Convolutional Neural Network

I'm trying to implement a convolutional neural network within Keras using a TF backend for image segmentation of 111 images of size 141 x 166. When I run the code below, I get the error message:
Error when checking target: expected dense_36 to have 2 dimensions, but got array with shape (88, 141, 166, 1)
My X_train variable is the shape (88, 141, 166, 1) as well as the y_train variable. My X_test variable is the shape (23, 141, 166, 1) as well as the y_test variable, as split by the function train_test_split from sklearn.
I'm not sure what the error message means as per dense_36. I have tried using the Flatten() function before fitting the model, but it says that I have a ndim = 2 and cannot be flattened.
# set input
batch_size = 111
num_epochs = 50
img_rows = 141
img_cols = 166
input_shape = (img_rows, img_cols, 1)
num_classes = img_rows*img_cols
# split training and test data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 4)
X_train = X_train.astype('float32')
X_test = X_train.astype('float32')
# CNN itself
model = Sequential()
model.add(Conv2D(32, kernel_size=(3,3), activation='relu',
input_shape=input_shape))
model.add(Conv2D(64, (3,3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Dropout(0.5))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))
# compile CNN
model.compile(loss=keras.losses.categorical_crossentropy,
optimizer=keras.optimizers.Adadelta(), metrics=['accuracy'])
# fit CNN
model.fit(X_train, y_train, batch_size=batch_size, epochs=num_epochs,
verbose=1, validation_data=(X_test, y_test))
My model summary is:
Layer (type) Output Shape Param #
=================================================================
conv2d_35 (Conv2D) (None, 139, 164, 32) 320
_________________________________________________________________
conv2d_36 (Conv2D) (None, 137, 162, 64) 18496
_________________________________________________________________
max_pooling2d_18 (MaxPooling (None, 68, 81, 64) 0
_________________________________________________________________
dropout_35 (Dropout) (None, 68, 81, 64) 0
_________________________________________________________________
flatten_28 (Flatten) (None, 352512) 0
_________________________________________________________________
dense_33 (Dense) (None, 128) 45121664
_________________________________________________________________
dropout_36 (Dropout) (None, 128) 0
_________________________________________________________________
dense_34 (Dense) (None, 2) 258
_________________________________________________________________
Total params: 45,140,738
Trainable params: 45,140,738
Non-trainable params: 0
_________________________________________________________________
None

Resources