x = np.load('/Users/bharddwajvemulapalli/Documents/tensorFlowProjects/Sign-language-digits-dataset 2/X.npy')
y = np.load('/Users/bharddwajvemulapalli/Documents/tensorFlowProjects/Sign-language-digits-dataset 2/Y.npy')
x = x/255
from tensorflow.keras.datasets import cifar10
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Activation,Flatten, Conv2D, MaxPooling2D #dense means fully connected
from tensorflow.keras.callbacks import TensorBoard
print(x.shape) # (2062, 64, 64)
BATCH_SIZE = 32
model = Sequential()
model.add(Conv2D(64,(6,6), input_shape = (64,64,1))) #figure out this input shape parameter to make this work
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size = (2,2)))
model.add(Conv2D(3,3))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size = (2,2)))
model.add(Flatten())
model.add(Dense(1))
model.add(Activation('relu'))
model.add(Flatten())
model.add(Dense(1)) #output layer
model.add(Activation('sigmoid'))
model.compile(loss = 'sparse_categorical_crossentropy', optimizer ='adam' , metrics = ['accuracy'])
#x = np.arange(8445952)
#x= np.reshape(64,64,1)
model.fit(x,y,batch_size = 32, epochs = 2, validation_split =.1)
The above is my code. I thought that keras would automatically attach batch_size to (64,64,1) so that I could get 4 dimensions, because when I add a fourth dimension myself, then I get an error that it wasn't expecting an array of dimension 5.
x must be 4-dimensional, where the 4th dimension is the number of channels. Since in your case there is only 1 channel, you can add the channel by
if x.ndim == 3:
x = np.expand_dims(x, axis=-1)
This will add a new dimension at the end.
Related
I am building an autoencoder for learning 28 ultrasound time signals of shape [262144,2] i.e. 262144 pairs of time and voltage points concatenated to form a [262144x2] tensor as input data to a stacked convolutional encoder. The latent space is set to produce a vector of length 16. The problem arise from the decoder, where a 'for loop' is used to stack two Conv2DTranspose layers each with a filter sizes of 64 and 32 and a kernel of 3 to the latent space output in order to reproduce the original input shape of [262144x2]. Instead, the decoder network gives a [262144x4] output tensor which does not match the validation and input data shapes of [262144x2]. What model parameters (filter, kernel, strides and padding) should I use to get appropriate tensor dimensions? the code and output are shown below. Your assistance is greatly appreciated!
from keras.layers import Dense, Input
from keras.layers import Conv2D, Flatten
from keras.layers import Reshape, Conv2DTranspose
from keras.models import Model
from keras.datasets import mnist
from keras.utils import plot_model
from keras import backend as K
import numpy as np
import matplotlib.pyplot as plt
x_Train = Signals
x_Test = Signals1
Sig_size1 = x_Train.shape[1]
Sig_size2 = x_Train.shape[2]
Sig_size11 = x_Test.shape[1]
Sig_size22 = x_Test.shape[2]
x_Train = np.reshape(x_Train,[-1, Sig_size1, Sig_size2, 1])
x_Train = x_Train.astype('float32') / np.max(x_Train)
x_Test = np.reshape(x_Test,[-1, Sig_size11, Sig_size22, 1])
x_Test = x_Test.astype('float32') / np.max(x_Test)
# network parameters# encoder/decoder number of filters per CNN layer
input_shape = (Sig_size1, Sig_size2, 1)
batch_size = 32 # Was 32
kernel_size = 1 # Was 3
latent_dim = 16 # Was 16
# encoder/decoder number of filters per CNN layer
layer_filters = [2, 6]
# build the autoencoder model
# first build the encoder model
inputs = Input(shape=input_shape, name='encoder_input')
x = inputs
# stack of Conv2D(32)-Conv2D(64)
for filters in layer_filters:
x = Conv2D(filters=filters,
kernel_size=kernel_size,
strides=2,
activation='relu',
padding='same')(x)
shape = K.int_shape(x)
# generate latent vector
x = Flatten()(x)
latent = Dense(latent_dim, name='latent_vector')(x)
# instantiate encoder model
encoder = Model(inputs, latent, name='encoder')
encoder.summary()
plot_model(encoder, to_file='encoder.png', show_shapes=True)
# build the decoder model
latent_inputs = Input(shape=(latent_dim,), name='decoder_input')
# use the shape (7, 7, 64) that was earlier saved
x = Dense(shape[1] * shape[2] * shape[3])(latent_inputs)
# from vector to suitable shape for transposed conv
x = Reshape((shape[1], shape[2], shape[3]))(x)
# stack of Conv2DTranspose(64)-Conv2DTranspose(32)
layer_filters = [1,8] ########change
kernel_size = 3 # Was 3
# for filters in layer_filters[::-1]:
for filters in layer_filters[::-1]:
x = Conv2DTranspose(filters=filters,
kernel_size=kernel_size,
strides=2,
activation='relu',
padding='same')(x)
# layer_filters = [64, 32]
kernel_size = 3 # Was 3
# reconstruct the input
outputs = Conv2DTranspose(filters=1, #Was 1
kernel_size=kernel_size,
activation='sigmoid',
padding='same',
name='decoder_output')(x)
# instantiate decoder model
decoder = Model(latent_inputs, outputs, name='decoder')
decoder.summary()
plot_model(decoder, to_file='decoder.png', show_shapes=True)
# autoencoder = encoder + decoder
# instantiate autoencoder model
autoencoder = Model(inputs,
decoder(encoder(inputs)),
name='autoencoder')
autoencoder.summary()
plot_model(autoencoder,
to_file='autoencoder.png',
show_shapes=True)
# Mean Square Error (MSE) loss funtion, Adam optimizer
autoencoder.compile(loss='mse', optimizer='adam')
# train the autoencoder
autoencoder.fit(x_Train,
x_Train,
validation_data=(x_Test, x_Test),
epochs=1,
batch_size=batch_size)
# predict the autoencoder output from test data
x_decoded = autoencoder.predict(x_Test)
This code was adapted from Advanced Deep Learning with Keras by Rowel Atienza (Chapter 3 for a denoising decoder for MNIST data)
I want to convert pretrained ResNet50 model from keras.application to a Sequential model but it gives input_shape error.
Input 0 is incompatible with layer res2a_branch1: expected axis -1 of input shape to have value 64 but got shape (None, 25, 25, 256)
I read this https://github.com/keras-team/keras/issues/9721 and as I understand the reason of error is skip_connections.
Is there a way to convert it to a Sequential or how can I add my custom model to end of this ResNet Model.
This is the code I've tried.
from keras.applications import ResNet50
height = 100 #dimensions of image
width = 100
channel = 3 #RGB
# Create pre-trained ResNet50 without top layer
model = ResNet50(include_top=False, weights="imagenet", input_shape=(height, width, channel))
# Get the ResNet50 layers up to res5c_branch2c
model = Model(input=model.input, output=model.get_layer('res5c_branch2c').output)
model.trainable = False
for layer in model.layers:
layer.trainable = False
model = Sequential(model.layers)
I want to add this to end of it. Where can I start?
model.add(Conv2D(32, (3,3), activation = 'relu', input_shape = inputShape))
model.add(MaxPooling2D(2,2))
model.add(BatchNormalization(axis = chanDim))
model.add(Dropout(0.2))
model.add(Conv2D(32, (3,3), activation = 'relu'))
model.add(MaxPooling2D(2,2))
model.add(BatchNormalization(axis = chanDim))
model.add(Dropout(0.2))
model.add(Conv2D(64, (3,3), activation = 'relu'))
model.add(MaxPooling2D(2,2))
model.add(BatchNormalization(axis = chanDim))
model.add(Dropout(0.2))
model.add(Flatten())
model.add(Dense(64, activation = 'relu'))
model.add(BatchNormalization(axis = chanDim))
model.add(Dropout(0.5))
model.add(Dense(classes, activation = 'softmax'))
Use functionl API of Keras.
First take ResNet50,
from keras.models import Model
from keras.applications import ResNet50
height = 100 #dimensions of image
width = 100
channel = 3 #RGB
# Create pre-trained ResNet50 without top layer
model_resnet = ResNet50(include_top=False, weights="imagenet", input_shape=(height, width, channel))
And add module of your model as follows, and use output of ResNet to input of the next layer
conv1 = Conv2D(32, (3,3), activation = 'relu')(model_resnet.output)
pool1 = MaxPooling2D(2,2)(conv1)
bn1 = BatchNormalization(axis=chanDim)(pool1)
drop1 = Dropout(0.2)(bn1)
Add this way all of your layer and at last for example,
flatten1 = Flatten()(drop1)
fc2 = Dense(classes, activation='softmax')(flatten1)
And, use Model() to create the final model.
model = Model(inputs=model_resnet.input, outputs=fc2)
Currently I'm trying to implement a multi-layer autoencoder using Keras, working on the Mnist dataset (handwritten digits). My code is looking like this:
from keras.layers import Input, Dense, initializers
from keras.models import Model
import numpy as np
from Dataset import Dataset
import matplotlib.pyplot as plt
from keras import optimizers, losses
from keras import backend as K
import tensorflow as tf
from keras.callbacks import TensorBoard
from keras.layers import Dropout
from keras.models import Sequential
from keras import models
from keras import layers
import keras
from keras.optimizers import Adam
#global variables
d = Dataset()
num_features = d.X_train.shape[1]
low_dim = 32
def autoencoder(epochs):
w = initializers.RandomNormal(mean=0.0, stddev=0.05, seed=None)
model = Sequential()
#First autoencoder
model.add(Dense(400, activation='relu', kernel_initializer=w, input_dim=num_features, name='hidden'))
model.add(Dropout(0.2))
model.add(Dense(num_features, activation='sigmoid', input_dim = 400, name = 'output'))
#Second autoencoder
model.add(Dense(100, activation='relu', kernel_initializer=w, input_dim=num_features, name='hidden2'))
model.add(Dropout(0.2))
model.add(Dense(num_features, activation = 'sigmoid', input_dim = 100, name='output2'))
#Third autoencoder
model.add(Dense(50, activation='relu', kernel_initializer=w, input_dim=num_features, name='hidden3'))
model.add(Dropout(0.2))
model.add(Dense(num_features, activation='sigmoid', input_dim=10, name='output3'))
model.compile(optimizer=Adam(lr=0.01), loss='binary_crossentropy', metrics=['accuracy'])
history = model.fit(d.X_train, d.X_train,
epochs=epochs,
batch_size=64,
shuffle=True,
validation_data=(d.X_test, d.X_test))
model.test_on_batch(d.X_test, d.X_test)
print(history.history.keys())
plt.plot(history.history['acc'])
print(history.history['acc'])
plt.show()
return model
def finding_index():
elements, index = np.unique(d.Y_test, return_index = True)
return elements, index
def plotting():
ae = autoencoder(2)
elements, index = finding_index()
y_proba = ae.predict(d.X_test)
plt.figure(figsize=(20, 4))
#size = 20
for i in range(len(index)):
ax = plt.subplot(2, len(index), i + 1)
plt.imshow(d.X_test[index[i]].reshape(28, 28))
plt.gray()
ax.get_xaxis().set_visible(False)
ax.get_yaxis().set_visible(False)
ax = plt.subplot(2, len(index), i + 1 + len(index))
plt.imshow(y_proba[index[i]].reshape(28, 28))
plt.gray()
ax.get_xaxis().set_visible(False)
ax.get_yaxis().set_visible(False)
plt.show()
plotting()
I have two questions, is it supposed to be like this when you stack autoencoders or should I let one layer reduce dimensions to let's say 400 and then the next to a 100 and so on, or the way I have done it? The second one is, can you different optimizers (in my case Adam) for different layers? I would like to use SGD (stochastic gradient descent) for the last layer. Thanks in advance!
You should not do it the way you've done it, but the way you described it in the question. Also you should go down first and then up again (e.g 400, 100, 50, 25, 10, 25, 50, 100, 400) in granular steps.
For the second question is the answer that it depends. You could train the model with Adam first and then freeze all but the last layer to train this further with SGD. But you can't tell Keras to use different classifiers for different layers.
I'm worked on sentiment analysis task using universal sentence encoder embed_size=512 with CNN but have an error says: Input 0 is incompatible with layer conv1d_6: expected ndim=3, found ndim=2.
and wanna know if this is right to add universal sentence encoder with CNN in this way or not?
pickle_in=open("X.pickle","rb")
X=pickle.load(pickle_in)
X = X.tolist() #convert x to list as The embedding code works once I
converted
the pandas.series data type to list.
X = np.array(X, dtype=object)[:, np.newaxis]
pickle_in=open("Y.pickle","rb")
Y=pickle.load(pickle_in)
Y = np.asarray(pd.get_dummies(Y), dtype = np.int8)
import tensorflow as tf
import tensorflow_hub as hub
module_url = "https://tfhub.dev/google/universal-sentence-encoder-large/3"
embed = hub.Module(module_url)
X_train, X_test, Y_train, Y_test = train_test_split(X,Y, test_size = 0.15,
random_state = 42)
X_train, X_Val, Y_train, Y_Val = train_test_split(X_train,Y_train, test_size
= 0.15, random_state = 42)
print(X_train.shape,Y_train.shape)
print(X_test.shape,Y_test.shape)
print(X_Val.shape,Y_Val.shape)
type(Y_test)
embed_size = embed.get_output_info_dict()['default'].get_shape()[1].value
def UniversalEmbedding(x):
return embed(tf.squeeze(tf.cast(x, tf.string)),
signature="default", as_dict=True)["default"]
import keras
seed=7
np.random.seed(seed)
from keras.layers import Input, Dense, concatenate, Activation,
GlobalMaxPooling1D
from keras import layers
from keras.models import Model
input_text = layers.Input(shape=(1,), dtype=tf.string)
embedding = layers.Lambda(UniversalEmbedding,
output_shape=(embed_size,))(input_text)
bigram_branch = Conv1D(filters=64, kernel_size=1, padding='same',
activation='relu', strides=1)(embedding)
bigram_branch = GlobalMaxPooling1D()(bigram_branch)
trigram_branch = Conv1D(filters=64, kernel_size=2, padding='same',
activation='relu', strides=1)(embedding)
trigram_branch = GlobalMaxPooling1D()(trigram_branch)
fourgram_branch = Conv1D(filters=64, kernel_size=3, padding='same',
activation='relu', strides=1)(embedding)
fourgram_branch = GlobalMaxPooling1D()(fourgram_branch)
merged = concatenate([bigram_branch, trigram_branch, fourgram_branch],
axis=1)
merged = Dense(512, activation='relu')(merged)
merged = Dropout(0.8)(merged)
merged = Dense(2)(merged)
output = Activation('sigmoid')(merged)
model = Model(inputs=[tweet_input], outputs=[output])
adam=keras.optimizers.Adam(lr=0.001, beta_1=0.9, beta_2=0.999, epsilon=None,
decay=0.0, amsgrad=False)
model.compile(loss='mean_squared_error',
optimizer= adam,
metrics=['accuracy'])
model.summary()
You can not directly pass Universal Sentence Encoder to Conv1D because Conv1D expected a tensor with shape [batch, sequence, feature] while the output of Universal Sentence Encoder is [batch, feature]. It is also stated in tfhub.dev:
The input is variable length English text and the output is a 512
dimensional vector.
How can I fix this?
In my view, the easiest possible solution is to use ELMo on Tensorhub. With ELMo you can map each sentence to [batch, sequence, feature] and then feed into the Conv1D.
So I have this error message that ruins all the fun with my work:
Traceback (most recent call last):
File "C:\Python\Python36\Scripts\Masterarbeit-1308\CNN - Kopie.py", line 97, in <module>
model.fit(np.asarray(X_train), np.asarray(Y_train), batch_size=32, epochs=100, verbose=1, validation_data=(np.asarray(X_test), np.asarray(Y_test)))
File "C:\Users\\****\AppData\Roaming\Python\Python36\site-packages\numpy\core\numeric.py", line 492, in asarray
return array(a, dtype, copy=False, order=order)
MemoryError
Does anyone has a solution for this?
I work on a machine i7 7th generation with 16 GB RAM.
To explain more, That's my code, It take al list of arrays (.npy) converted from sounds spectograms to .npy and saved in Input-CNN:
import os, numpy as np
from keras.models import Sequential
from keras.layers import Convolution2D, MaxPooling2D, Activation, Flatten, Conv2D, Dropout, Dense
from keras.layers.normalization import BatchNormalization
import tensorflow as tf
from sklearn.utils import shuffle
from sklearn.cross_validation import train_test_split
from keras.utils import to_categorical
folder = 'D:\InputCNN - Copie'
folder1 = 'C:\Python\Python36\Scripts\Masterarbeit-1308\Data'
from keras import backend as K
My_Data = os.listdir(folder)
num_data= len(My_Data)
Classnames = os.listdir(folder1)
class_num = len(Classnames)
arr =[np.load(os.path.join(folder, filename), fix_imports=True) for filename in os.listdir(folder)]
labels = np.ones((num_data,))
labels[0:31]= 0
labels[31:80] = 1
labels[80:128] = 2
labels[128:131] = 3
labels[131:143] = 4
labels[143:157] = 5
labels[157:209] = 6
labels[209:] = 7
Y = to_categorical(labels,class_num)
x, y = shuffle(arr, Y, random_state=2)
dataset = tf.data.Dataset.from_tensor_slices(My_Data)
X_train, X_test, Y_train, Y_test = train_test_split(x, Y, test_size=0.2)
##
def build_model(idx,X,Y,nb_classes):
K.set_image_data_format('channels_last')
nb_filters = 64 # number of convolutional filters to use
pool_size = (2, 2) # size of pooling area for max pooling
kernel_size = (3, 3) # convolution kernel size
nb_layers = 4
input_shape = (X[idx].shape[1], X[idx].shape[2], X[idx].shape[3])
model = Sequential()
model.add(Conv2D(nb_filters, kernel_size, padding='valid', input_shape=input_shape))
model.add(BatchNormalization(axis=1))
model.add(Activation('relu'))
for layer in range(nb_layers-1):
model.add(Conv2D(nb_filters, kernel_size, padding='valid', input_shape=input_shape))
model.add(BatchNormalization(axis=1))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=pool_size))
model.add(Dropout(0.5))
model.add(Flatten())
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dropout(0.6))
model.add(Dense(nb_classes, activation='sigmoid'))
return model
for idx in range(len(X_train)-1):
model = build_model(idx,X_train,Y_train, class_num)
model.summary()
model.compile(loss='categorical_crossentropy',
optimizer='adadelta',
metrics=['accuracy'])
model.fit(np.array(X_train), np.array(Y_train), batch_size=8, epochs=100, verbose=1, validation_data=(np.array(X_test), np.array(Y_test))) #Here I have the problem
score = model.evaluate(np.array(X_test), np.array(Y_test), verbose=0)
print('Test score:', score[0])
print('Test accuracy:', score[1])
The model fit function is the problem in my code, that should train my preconfigured model and returns an history object (A record of the training). I tried np.array and np.asarray and I got the same error message.
If someone think that the model`s summary can be helpful, I'll post it.
I solved this issue. Actually I changed the shape of my data in the list "X_train" (from (218,128,740,1) to (128,740,1)).
I found that, thanks to Keras, it will add automatically another axis with the number of my data injected to the network, and np.asarray works well even with more data.