Related
I'm trying to do grid search for a multi class problem in neural networks.
I am not able to get the optimum parameters, the kernel keeps on compiling.
Is there any problem with my code? Please do help
import keras
from keras.models import Sequential
from keras.layers import Dense
# defining the baseline model:
def neural(output_dim=10,init_mode='glorot_uniform'):
model = Sequential()
model.add(Dense(output_dim=output_dim,
input_dim=2,
activation='relu',
kernel_initializer= init_mode))
model.add(Dense(output_dim=output_dim,
activation='relu',
kernel_initializer= init_mode))
model.add(Dense(output_dim=3,activation='softmax'))
# Compile model
model.compile(loss='sparse_categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
return model
from keras.wrappers.scikit_learn import KerasClassifier
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import KFold
from sklearn.model_selection import GridSearchCV
estimator = KerasClassifier(build_fn=neural,
epochs=5,
batch_size=5,
verbose=0)
# define the grid search parameters
batch_size = [10, 20, 40, 60, 80, 100]
epochs = [10, 50, 100]
init_mode = ['uniform', 'lecun_uniform', 'normal', 'zero',
'glorot_normal', 'glorot_uniform', 'he_normal', 'he_uniform']
output_dim = [10, 15, 20, 25, 30,40]
param_grid = dict(batch_size=batch_size,
epochs=epochs,
output_dim=output_dim,
init_mode=init_mode)
grid = GridSearchCV(estimator=estimator,
scoring= 'accuracy',
param_grid=param_grid,
n_jobs=-1,cv=5)
grid_result = grid.fit(X_train, Y_train)
# summarize results
print("Best: %f using %s" % (grid_result.best_score_,
grid_result.best_params_))
means = grid_result.cv_results_['mean_test_score']
stds = grid_result.cv_results_['std_test_score']
params = grid_result.cv_results_['params']
for mean, stdev, param in zip(means, stds, params):
print("%f (%f) with: %r" % (mean, stdev, param))
There's no error in your code.
Your current param grid has 864 different combinations of parameters possible.
(6 values in 'batch_size' × 3 values in 'epochs' × 8 in 'init_mode' × 6 in 'output_dim') = 864
GridSearchCV will iterate over all those possibilities and your estimator will be cloned that many times. And that is again repeated 5 times because you have set cv=5.
So your model will be cloned (compiled and params set according to the possibilities) a total of 864 x 5 = 4320 times.
So you keep seeing in output that the model is being compiled those many times.
To check if GridSearchCV is working or not, use its verbose param.
grid = GridSearchCV(estimator=estimator,
scoring= 'accuracy',
param_grid=param_grid,
n_jobs=1,cv=5, verbose=3)
This will print the current possible params being tried, the cv iteration, time taken to fit on it, current accuracy etc.
I am a little new to neural networks and keras. I have some images with size 6*7 and the size of the filter is 15. I want to have several filters and train a convolutional layer separately on each and then combine them. I have looked at one example here:
model = Sequential()
model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1],
border_mode='valid',
input_shape=input_shape))
model.add(Activation('relu'))
model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1]))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=pool_size))
model.add(Dropout(0.25))
model.add(Flatten(input_shape=input_shape))
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes))
model.add(Activation('tanh'))
This model works with one filter. Can anybody give me some hints on how to modify the model to work with parallel convolutional layers.
Thanks
Here is an example of designing a network of parallel convolution and sub sampling layers in keras version 2. I hope this resolves your problem.
rows, cols = 100, 15
def create_convnet(img_path='network_image.png'):
input_shape = Input(shape=(rows, cols, 1))
tower_1 = Conv2D(20, (100, 5), padding='same', activation='relu')(input_shape)
tower_1 = MaxPooling2D((1, 11), strides=(1, 1), padding='same')(tower_1)
tower_2 = Conv2D(20, (100, 7), padding='same', activation='relu')(input_shape)
tower_2 = MaxPooling2D((1, 9), strides=(1, 1), padding='same')(tower_2)
tower_3 = Conv2D(20, (100, 10), padding='same', activation='relu')(input_shape)
tower_3 = MaxPooling2D((1, 6), strides=(1, 1), padding='same')(tower_3)
merged = keras.layers.concatenate([tower_1, tower_2, tower_3], axis=1)
merged = Flatten()(merged)
out = Dense(200, activation='relu')(merged)
out = Dense(num_classes, activation='softmax')(out)
model = Model(input_shape, out)
plot_model(model, to_file=img_path)
return model
The image of this network will look like
My approach is to create other model that defines all parallel convolution and pulling operations and concat all parallel result tensors to single output tensor. Now you can add this parallel model graph in your sequential model just like layer. Here is my solution, hope it solves your problem.
# variable initialization
from keras import Input, Model, Sequential
from keras.layers import Conv2D, MaxPooling2D, Concatenate, Activation, Dropout, Flatten, Dense
nb_filters =100
kernel_size= {}
kernel_size[0]= [3,3]
kernel_size[1]= [4,4]
kernel_size[2]= [5,5]
input_shape=(32, 32, 3)
pool_size = (2,2)
nb_classes =2
no_parallel_filters = 3
# create seperate model graph for parallel processing with different filter sizes
# apply 'same' padding so that ll produce o/p tensor of same size for concatination
# cancat all paralle output
inp = Input(shape=input_shape)
convs = []
for k_no in range(len(kernel_size)):
conv = Conv2D(nb_filters, kernel_size[k_no][0], kernel_size[k_no][1],
border_mode='same',
activation='relu',
input_shape=input_shape)(inp)
pool = MaxPooling2D(pool_size=pool_size)(conv)
convs.append(pool)
if len(kernel_size) > 1:
out = Concatenate()(convs)
else:
out = convs[0]
conv_model = Model(input=inp, output=out)
# add created model grapg in sequential model
model = Sequential()
model.add(conv_model) # add model just like layer
model.add(Conv2D(nb_filters, kernel_size[1][0], kernel_size[1][0]))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=pool_size))
model.add(Dropout(0.25))
model.add(Flatten(input_shape=input_shape))
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes))
model.add(Activation('tanh'))
For more information refer similar question: Combining the outputs of multiple models into one model
I am currently looking for a way i can combine the output of multiple model into one model, I need to create a CNN network that does classification.
The image is separated into sections (as seen by the colors), each section is given as input to a certain model (1,2,3,4) the structure of each model is the same, but each section is given to a separate model to ensure that the the same weight is not applied on whole image - My attempt to avoid full weight sharing, and keeping the weight sharing local. Each model then perform convolution and max pooling, and generate some sort of output that has to fed into a dense layer that takes the outputs from the prior models (model 1,2,3,4,) and performs classifications.
My question here is it possible to create model 1,2,3,4 and connect it to the fully connected layer and train all the models given the input sections and and the output class - without having to define the outputs of the convolution and pooling layer in keras?
Yes, you can create such models using Multi-input and multi-output models, refer keras documentation for more details. Here I am sharing code sample, hope this helps
import numpy as np
import keras
from keras.optimizers import SGD
from keras.models import Sequential, Model
from keras.layers import Activation, Dense, Dropout, Flatten, Input, Merge, Convolution2D, MaxPooling2D
# Generate dummy data
train1 = np.random.random((100, 100, 100, 3))
train2 = np.random.random((100, 100, 100, 3))
train3 = np.random.random((100, 100, 100, 3))
train4 = np.random.random((100, 100, 100, 3))
y_train = keras.utils.to_categorical(np.random.randint(10, size=(100, 1)), num_classes=10)
#parallel ip for different sections of image
inp1 = Input(shape=train1.shape[1:])
inp2 = Input(shape=train2.shape[1:])
inp3 = Input(shape=train3.shape[1:])
inp4 = Input(shape=train4.shape[1:])
# paralle conv and pool layer which process each section of input independently
conv1 = Conv2D(64, (3, 3), activation='relu')(inp1)
conv2 = Conv2D(64, (3, 3), activation='relu')(inp2)
conv3 = Conv2D(64, (3, 3), activation='relu')(inp3)
conv4 = Conv2D(64, (3, 3), activation='relu')(inp4)
maxp1 = MaxPooling2D((3, 3))(conv1)
maxp2 =MaxPooling2D((3, 3))(conv2)
maxp3 =MaxPooling2D((3, 3))(conv3)
maxp4 =MaxPooling2D((3, 3))(conv4)
# can add multiple parallel conv, pool layes to reduce size
flt1 = Flatten()(maxp1)
flt2 = Flatten()(maxp2)
flt3 = Flatten()(maxp3)
flt4 = Flatten()(maxp4)
mrg = Merge(mode='concat')([flt1,flt2,flt3,flt4])
dense = Dense(256, activation='relu')(mrg)
op = Dense(10, activation='softmax')(dense)
model = Model(input=[inp1, inp2, inp3, inp4], output=op)
model.compile(optimizer='rmsprop',
loss='categorical_crossentropy',
metrics=['accuracy'])
model.fit([train1,train2,train3,train4], y_train,
nb_epoch=10, batch_size=28)
I am currently trying to get a decent score (> 40% accuracy) with Keras on CIFAR 100. However, I'm experiencing a weird behaviour of a CNN model: It tends to predict some classes (2 - 5) much more often than others:
The pixel at position (i, j) contains the count how many elements of the validation set from class i were predicted to be of class j. Thus the diagonal contains the correct classifications, everything else is an error. The two vertical bars indicate that the model often predicts those classes, although it is not the case.
CIFAR 100 is perfectly balanced: All 100 classes have 500 training samples.
Why does the model tend to predict some classes MUCH more often than other classes? How can this be fixed?
The code
Running this takes a while.
#!/usr/bin/env python
from __future__ import print_function
from keras.datasets import cifar100
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Convolution2D, MaxPooling2D
from keras.utils import np_utils
from sklearn.model_selection import train_test_split
import numpy as np
batch_size = 32
nb_classes = 100
nb_epoch = 50
data_augmentation = True
# input image dimensions
img_rows, img_cols = 32, 32
# The CIFAR10 images are RGB.
img_channels = 3
# The data, shuffled and split between train and test sets:
(X, y), (X_test, y_test) = cifar100.load_data()
X_train, X_val, y_train, y_val = train_test_split(X, y,
test_size=0.20,
random_state=42)
# Shuffle training data
perm = np.arange(len(X_train))
np.random.shuffle(perm)
X_train = X_train[perm]
y_train = y_train[perm]
print('X_train shape:', X_train.shape)
print(X_train.shape[0], 'train samples')
print(X_val.shape[0], 'validation samples')
print(X_test.shape[0], 'test samples')
# Convert class vectors to binary class matrices.
Y_train = np_utils.to_categorical(y_train, nb_classes)
Y_test = np_utils.to_categorical(y_test, nb_classes)
Y_val = np_utils.to_categorical(y_val, nb_classes)
model = Sequential()
model.add(Convolution2D(32, 3, 3, border_mode='same',
input_shape=X_train.shape[1:]))
model.add(Activation('relu'))
model.add(Convolution2D(32, 3, 3))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Convolution2D(64, 3, 3, border_mode='same'))
model.add(Activation('relu'))
model.add(Convolution2D(64, 3, 3))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(1024))
model.add(Activation('tanh'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
X_train = X_train.astype('float32')
X_val = X_val.astype('float32')
X_test = X_test.astype('float32')
X_train /= 255
X_val /= 255
X_test /= 255
if not data_augmentation:
print('Not using data augmentation.')
model.fit(X_train, Y_train,
batch_size=batch_size,
nb_epoch=nb_epoch,
validation_data=(X_val, y_val),
shuffle=True)
else:
print('Using real-time data augmentation.')
# This will do preprocessing and realtime data augmentation:
datagen = ImageDataGenerator(
featurewise_center=False, # set input mean to 0 over the dataset
samplewise_center=False, # set each sample mean to 0
featurewise_std_normalization=False, # divide inputs by std of the dataset
samplewise_std_normalization=False, # divide each input by its std
zca_whitening=False, # apply ZCA whitening
rotation_range=0, # randomly rotate images in the range (degrees, 0 to 180)
width_shift_range=0.1, # randomly shift images horizontally (fraction of total width)
height_shift_range=0.1, # randomly shift images vertically (fraction of total height)
horizontal_flip=True, # randomly flip images
vertical_flip=False) # randomly flip images
# Compute quantities required for featurewise normalization
# (std, mean, and principal components if ZCA whitening is applied).
datagen.fit(X_train)
# Fit the model on the batches generated by datagen.flow().
model.fit_generator(datagen.flow(X_train, Y_train,
batch_size=batch_size),
samples_per_epoch=X_train.shape[0],
nb_epoch=nb_epoch,
validation_data=(X_val, Y_val))
model.save('cifar100.h5')
Visualization code
#!/usr/bin/env python
"""Analyze a cifar100 keras model."""
from keras.models import load_model
from keras.datasets import cifar100
from sklearn.model_selection import train_test_split
import numpy as np
import json
import io
import matplotlib.pyplot as plt
try:
to_unicode = unicode
except NameError:
to_unicode = str
n_classes = 100
def plot_cm(cm, zero_diagonal=False):
"""Plot a confusion matrix."""
n = len(cm)
size = int(n / 4.)
fig = plt.figure(figsize=(size, size), dpi=80, )
plt.clf()
ax = fig.add_subplot(111)
ax.set_aspect(1)
res = ax.imshow(np.array(cm), cmap=plt.cm.viridis,
interpolation='nearest')
width, height = cm.shape
fig.colorbar(res)
plt.savefig('confusion_matrix.png', format='png')
# Load model
model = load_model('cifar100.h5')
# Load validation data
(X, y), (X_test, y_test) = cifar100.load_data()
X_train, X_val, y_train, y_val = train_test_split(X, y,
test_size=0.20,
random_state=42)
# Calculate confusion matrix
y_val_i = y_val.flatten()
y_val_pred = model.predict(X_val)
y_val_pred_i = y_val_pred.argmax(1)
cm = np.zeros((n_classes, n_classes), dtype=np.int)
for i, j in zip(y_val_i, y_val_pred_i):
cm[i][j] += 1
acc = sum([cm[i][i] for i in range(100)]) / float(cm.sum())
print("Validation accuracy: %0.4f" % acc)
# Create plot
plot_cm(cm)
# Serialize confusion matrix
with io.open('cm.json', 'w', encoding='utf8') as outfile:
str_ = json.dumps(cm.tolist(),
indent=4, sort_keys=True,
separators=(',', ':'), ensure_ascii=False)
outfile.write(to_unicode(str_))
Red herrings
tanh
I've replaced tanh by relu. The history csv looks ok, but the visualization has the same problem:
Please also note that the validation accuracy here is only 3.44%.
Dropout + tanh + border mode
Removing dropout, replacing tanh by relu, setting border mode to same everywhere: history csv
The visualization code still gives a much lower accuracy (8.50% this time) than the keras training code.
Q & A
The following is a summary of the comments:
The data is evenly distributed over the classes. So there is no "over training" of those two classes.
Data augmentation is used, but without data augmentation the problem persists.
The visualization is not the problem.
If you get good accuracy during training and validation, but not when testing, make sure you do exactly the same preprocessing on your dataset in both cases.
Here you have when training:
X_train /= 255
X_val /= 255
X_test /= 255
But no such code when predicting for your confusion matrix. Adding to testing:
X_val /= 255.
Gives the following nice looking confusion matrix:
I don't have a good feeling with this part of the code:
model.add(Dense(1024))
model.add(Activation('tanh'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes))
model.add(Activation('softmax'))
The remaining model is full of relus, but here there is a tanh.
tanh sometimes vanishes or explodes (saturates at -1 and 1), which might lead to your 2-class overimportance.
keras-example cifar 10 basically uses the same architecture (dense-layer sizes might be different), but also uses a relu there (no tanh at all). The same goes for this external keras-based cifar 100 code.
One important part of the problem was that my ~/.keras/keras.json was
{
"image_dim_ordering": "th",
"epsilon": 1e-07,
"floatx": "float32",
"backend": "tensorflow"
}
Hence I had to change image_dim_ordering to tf. This leads to
and an accuracy of 12.73%. Obviously, there is still a problem as the validation history gave 45.1% accuracy.
I don't see you doing mean-centering, even in datagen. I suspect this is the main cause. To do mean centering using ImageDataGenerator, set featurewise_center = 1. Another way is to subtract the ImageNet mean from each RGB pixel. The mean vector to be subtracted is [103.939, 116.779, 123.68].
Make all activations relus, unless you have a specific reason to have a single tanh.
Remove two dropouts of 0.25 and see what happens. If you want to apply dropouts to convolution layer, it is better to use SpatialDropout2D. It is somehow removed from Keras online documentation but you can find it in the source.
You have two conv layers with same and two with valid. There is nothing wrong in this, but it would be simpler to keep all conv layers with same and control your size just based on max-poolings.
Autoencoder networks seems to be way trickier than normal classifier MLP networks. After several attempts using Lasagne all what I get in the reconstructed output is something that resembles at its best a blurry averaging of all the images of the MNIST database without distinction on what the input digit actually is.
The networks structure I chose are the following cascade layers:
input layer (28x28)
2D convolutional layer, filter size 7x7
Max Pooling layer, size 3x3, stride 2x2
Dense (fully connected) flattening layer, 10 units (this is the bottleneck)
Dense (fully connected) layer, 121 units
Reshaping layer to 11x11
2D convolutional layer, filter size 3x3
2D Upscaling layer factor 2
2D convolutional layer, filter size 3x3
2D Upscaling layer factor 2
2D convolutional layer, filter size 5x5
Feature max pooling (from 31x28x28 to 28x28)
All the 2D convolutional layers have the biases untied, sigmoid activations and 31 filters.
All the fully connected layers have sigmoid activations.
The loss function used is squared error, the updating function is adagrad. The length of the chunk for the learning is 100 samples, multiplied for 1000 epochs.
Just for completeness, the following is the code I used:
import theano.tensor as T
import theano
import sys
sys.path.insert(0,'./Lasagne') # local checkout of Lasagne
import lasagne
from theano import pp
from theano import function
import gzip
import numpy as np
from sklearn.preprocessing import OneHotEncoder
import matplotlib.pyplot as plt
def load_mnist():
def load_mnist_images(filename):
with gzip.open(filename, 'rb') as f:
data = np.frombuffer(f.read(), np.uint8, offset=16)
# The inputs are vectors now, we reshape them to monochrome 2D images,
# following the shape convention: (examples, channels, rows, columns)
data = data.reshape(-1, 1, 28, 28)
# The inputs come as bytes, we convert them to float32 in range [0,1].
# (Actually to range [0, 255/256], for compatibility to the version
# provided at http://deeplearning.net/data/mnist/mnist.pkl.gz.)
return data / np.float32(256)
def load_mnist_labels(filename):
# Read the labels in Yann LeCun's binary format.
with gzip.open(filename, 'rb') as f:
data = np.frombuffer(f.read(), np.uint8, offset=8)
# The labels are vectors of integers now, that's exactly what we want.
return data
X_train = load_mnist_images('train-images-idx3-ubyte.gz')
y_train = load_mnist_labels('train-labels-idx1-ubyte.gz')
X_test = load_mnist_images('t10k-images-idx3-ubyte.gz')
y_test = load_mnist_labels('t10k-labels-idx1-ubyte.gz')
return X_train, y_train, X_test, y_test
def plot_filters(conv_layer):
W = conv_layer.get_params()[0]
W_fn = theano.function([],W)
params = W_fn()
ks = np.squeeze(params)
kstack = np.vstack(ks)
plt.imshow(kstack,interpolation='none')
plt.show()
def main():
#theano.config.exception_verbosity="high"
#theano.config.optimizer='None'
X_train, y_train, X_test, y_test = load_mnist()
ohe = OneHotEncoder()
y_train = ohe.fit_transform(np.expand_dims(y_train,1)).toarray()
chunk_len = 100
visamount = 10
num_epochs = 1000
num_filters=31
dropout_p=.0
print "X_train.shape",X_train.shape,"y_train.shape",y_train.shape
input_var = T.tensor4('X')
output_var = T.tensor4('X')
conv_nonlinearity = lasagne.nonlinearities.sigmoid
net = lasagne.layers.InputLayer((chunk_len,1,28,28), input_var)
conv1 = net = lasagne.layers.Conv2DLayer(net,num_filters,(7,7),nonlinearity=conv_nonlinearity,untie_biases=True)
net = lasagne.layers.MaxPool2DLayer(net,(3,3),stride=(2,2))
net = lasagne.layers.DropoutLayer(net,p=dropout_p)
#conv2_layer = lasagne.layers.Conv2DLayer(dropout_layer,num_filters,(3,3),nonlinearity=conv_nonlinearity)
#pool2_layer = lasagne.layers.MaxPool2DLayer(conv2_layer,(3,3),stride=(2,2))
net = lasagne.layers.DenseLayer(net,10,nonlinearity=lasagne.nonlinearities.sigmoid)
#augment_layer1 = lasagne.layers.DenseLayer(reduction_layer,33,nonlinearity=lasagne.nonlinearities.sigmoid)
net = lasagne.layers.DenseLayer(net,121,nonlinearity=lasagne.nonlinearities.sigmoid)
net = lasagne.layers.ReshapeLayer(net,(chunk_len,1,11,11))
net = lasagne.layers.Conv2DLayer(net,num_filters,(3,3),nonlinearity=conv_nonlinearity,untie_biases=True)
net = lasagne.layers.Upscale2DLayer(net,2)
net = lasagne.layers.Conv2DLayer(net,num_filters,(3,3),nonlinearity=conv_nonlinearity,untie_biases=True)
#pool_after0 = lasagne.layers.MaxPool2DLayer(conv_after1,(3,3),stride=(2,2))
net = lasagne.layers.Upscale2DLayer(net,2)
net = lasagne.layers.DropoutLayer(net,p=dropout_p)
#conv_after2 = lasagne.layers.Conv2DLayer(upscale_layer1,num_filters,(3,3),nonlinearity=conv_nonlinearity,untie_biases=True)
#pool_after1 = lasagne.layers.MaxPool2DLayer(conv_after2,(3,3),stride=(1,1))
#upscale_layer2 = lasagne.layers.Upscale2DLayer(pool_after1,4)
net = lasagne.layers.Conv2DLayer(net,num_filters,(5,5),nonlinearity=conv_nonlinearity,untie_biases=True)
net = lasagne.layers.FeaturePoolLayer(net,num_filters,pool_function=theano.tensor.max)
print "output_shape:",lasagne.layers.get_output_shape(net)
params = lasagne.layers.get_all_params(net, trainable=True)
prediction = lasagne.layers.get_output(net)
loss = lasagne.objectives.squared_error(prediction, output_var)
#loss = lasagne.objectives.binary_crossentropy(prediction, output_var)
aggregated_loss = lasagne.objectives.aggregate(loss)
updates = lasagne.updates.adagrad(aggregated_loss,params)
train_fn = theano.function([input_var, output_var], loss, updates=updates)
test_prediction = lasagne.layers.get_output(net, deterministic=True)
predict_fn = theano.function([input_var], test_prediction)
print "starting training..."
for epoch in range(num_epochs):
selected = list(set(np.random.random_integers(0,59999,chunk_len*4)))[:chunk_len]
X_train_sub = X_train[selected,:]
_loss = train_fn(X_train_sub, X_train_sub)
print("Epoch %d: Loss %g" % (epoch + 1, np.sum(_loss) / len(X_train)))
"""
chunk = X_train[0:chunk_len,:,:,:]
result = predict_fn(chunk)
vis1 = np.hstack([chunk[j,0,:,:] for j in range(visamount)])
vis2 = np.hstack([result[j,0,:,:] for j in range(visamount)])
plt.imshow(np.vstack([vis1,vis2]))
plt.show()
"""
print "done."
chunk = X_train[0:chunk_len,:,:,:]
result = predict_fn(chunk)
print "chunk.shape",chunk.shape
print "result.shape",result.shape
plot_filters(conv1)
for i in range(chunk_len/visamount):
vis1 = np.hstack([chunk[i*visamount+j,0,:,:] for j in range(visamount)])
vis2 = np.hstack([result[i*visamount+j,0,:,:] for j in range(visamount)])
plt.imshow(np.vstack([vis1,vis2]))
plt.show()
import ipdb; ipdb.set_trace()
if __name__ == "__main__":
main()
Any ideas on how to improve this network to get a reasonably functioning autoencoder?