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.
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 need to calculate the gradient of the validation error w.r.t inputs x. I'm trying to see how much the validation error changes when I perturb one of the training samples.
The validation error (E) explicitly depends on the model weights (W).
The model weights explicitly depend on the inputs (x and y).
Therefore, the validation error implicitly depends on the inputs.
I'm trying to calculate the gradient of E w.r.t x directly.
An alternative approach would be to calculate the gradient of E w.r.t W (can easily be calculated) and the gradient of W w.r.t x (cannot do at the moment), which would allow the gradient of E w.r.t x to be calculated.
I have attached a toy example. Thanks in advance!
import numpy as np
import mnist
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.keras.utils import to_categorical
import tensorflow as tf
from autograd import grad
train_images = mnist.train_images()
train_labels = mnist.train_labels()
test_images = mnist.test_images()
test_labels = mnist.test_labels()
# Normalize the images.
train_images = (train_images / 255) - 0.5
test_images = (test_images / 255) - 0.5
# Flatten the images.
train_images = train_images.reshape((-1, 784))
test_images = test_images.reshape((-1, 784))
# Build the model.
model = Sequential([
Dense(64, activation='relu', input_shape=(784,)),
Dense(64, activation='relu'),
Dense(10, activation='softmax'),
])
# Compile the model.
model.compile(
optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'],
)
# Train the model.
model.fit(
train_images,
to_categorical(train_labels),
epochs=5,
batch_size=32,
)
model.save_weights('model.h5')
# Load the model's saved weights.
# model.load_weights('model.h5')
calculate_mse = tf.keras.losses.MeanSquaredError()
test_x = test_images[:5]
test_y = to_categorical(test_labels)[:5]
train_x = train_images[:1]
train_y = to_categorical(train_labels)[:1]
train_y = tf.convert_to_tensor(train_y, np.float32)
train_x = tf.convert_to_tensor(train_x, np.float64)
with tf.GradientTape() as tape:
tape.watch(train_x)
model.fit(train_x, train_y, epochs=1, verbose=0)
valid_y_hat = model(test_x, training=False)
mse = calculate_mse(test_y, valid_y_hat)
de_dx = tape.gradient(mse, train_x)
print(de_dx)
# approach 2 - does not run
def calculate_validation_mse(x):
model.fit(x, train_y, epochs=1, verbose=0)
valid_y_hat = model(test_x, training=False)
mse = calculate_mse(test_y, valid_y_hat)
return mse
train_x = train_images[:1]
train_y = to_categorical(train_labels)[:1]
validation_gradient = grad(calculate_validation_mse)
de_dx = validation_gradient(train_x)
print(de_dx)
Here's how you can do this. Derivation is as below.
Few things to note,
I have reduced the feature size from 784 to 256 as I was running out of memory in colab (line marked in the code) . Might have to do some mem profiling to find out why
Only computed grads for the first layer. Easily extendable to other layers
Disclaimer: this derivation is correct to best of my knowledge. Please do some research and verify that it is the case. You will run into memory issues for larger inputs and layer sizes.
import numpy as np
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.keras.utils import to_categorical
import tensorflow as tf
f = 256
model = Sequential([
Dense(64, activation='relu', input_shape=(f,)),
Dense(64, activation='relu'),
Dense(10, activation='softmax'),
])
# Compile the model.
model.compile(
optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'],
)
w = model.weights[0]
# Inputs and labels
x_tr = tf.Variable(np.random.normal(size=(1,f)), shape=(1, f), dtype='float32')
y_tr = np.random.choice([0,1,2,3,4,5,6,7,8,9], size=(1,1))
y_tr_onehot = tf.keras.utils.to_categorical(y_tr, num_classes=10).astype('float32')
x_v = tf.Variable(np.random.normal(size=(1,f)), shape=(1, f), dtype='float32')
y_v = np.random.choice([0,1,2,3,4,5,6,7,8,9], size=(1,1))
y_v_onehot = tf.keras.utils.to_categorical(y_v, num_classes=10).astype('float32')
# In the context of GradientTape
with tf.GradientTape() as tape1:
with tf.GradientTape() as tape2:
y_tr_pred = model(x_tr)
tr_loss = tf.keras.losses.MeanSquaredError()(y_tr_onehot, y_tr_pred)
tmp_g = tape2.gradient(tr_loss, w)
print(tmp_g.shape)
# d(dE_tr/d(theta))/dx
# Warning this step consumes lot of memory for large layers
lr = 0.001
grads_1 = -lr * tape1.jacobian(tmp_g, x_tr)
with tf.GradientTape() as tape3:
y_v_pred = model(x_v)
v_loss = tf.keras.losses.MeanSquaredError()(y_v_onehot, y_v_pred)
# dE_val/d(theta)
grads_2 = tape3.gradient(v_loss, w)[tf.newaxis, :]
# Just crunching the dimension to get the final desired shape of (1,256)
grad = tf.matmul(tf.reshape(grads_2,[1, -1]), tf.reshape(tf.transpose(grads_1,[2,1,0,3]),[1, -1, 256]))
I am trying to predict one out of 8 classes for some short text data with word embeddings and CNN. The occuring problem is that the CNN Classifier predicts everything in one class (the biggest one of the training data, distribution ~40%). The text data should be preprocesed quite well, because the classification works fine with other classifiers like SVM or NB.
'''
#first, build index mapping words in the embeddings set to their embedding vector
import os
embeddings_index = {}
f = open(os.path.join('', 'embedding_word2vec.txt'), encoding='utf-8')
for line in f:
values = line.split()
words = values[0]
coefs = np.asarray(values[1:])
embeddings_index[word] = coefs
f.close()
#vectorize text samples in 2D Integer Tensor
from tensorflow.python.keras.preprocessing.text import Tokenizer
tokenizer_obj = Tokenizer()
tokenizer_obj.fit_on_texts(stemmed_text)
sequences = tokenizer_obj.texts_to_sequences(stemmed_text)
#pad sequences
from tensorflow.python.keras.preprocessing.sequence import pad_sequences
from keras.utils import to_categorical
max_length = max([len(s.split(',')) for s in total_texts])
print('MaxLength :', max_length)
word_index = tokenizer_obj.word_index
print('Found %s unique Tokens.' % len(word_index))
text_pad = pad_sequences(sequences)
labels = to_categorical(np.asarray(labels))
print('Shape of label tensor:', labels.shape)
print('Shape of Text Tensor: ', text_pad.shape)
embedding_dim = 100
num_words = len(word_index) + 1
#prepare embedding matrix
embedding_matrix = np.zeros((vocab_size, embedding_dim))
for index, word in enumerate(vocab):
embedding_vector = w2v.wv[word]
if embedding_vector is not None:
embedding_matrix[index] = embedding_vector
#train test split
validation_split = 0.2
indices = np.arange(text_pad.shape[0])
np.random.shuffle(indices)
text_pad = text_pad[indices]
labels = labels[indices]
num_validation_samples = int(validation_split * text_pad.shape[0])
x_train = text_pad[:-num_validation_samples]
y_train = labels[:-num_validation_samples]
x_test = text_pad[-num_validation_samples:]
y_test = labels[-num_validation_samples:]
from keras.models import Sequential
from keras.layers.core import Dense, Flatten, Dropout
from keras.layers.convolutional import Conv1D, MaxPooling1D
from keras.layers.embeddings import Embedding
model = Sequential()
model.add(Embedding(vocab_size, embedding_dim, input_length=max_length,
#embeddings_initializer = Constant(embedding_matrix),
weights=[embedding_matrix],
trainable=False))
model.add(Dropout(0.2))
model.add(Conv1D(filters=64, kernel_size=5, activation='relu'))
model.add(MaxPooling1D(pool_size=4))
#model.add(Conv1D(filters=64, kernel_size=5, activation='relu'))
#model.add(MaxPooling1D(pool_size=4))
model.add(Flatten())
model.add(Dense(8, activation='sigmoid'))
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
history = model.fit(x_train, y_train,
epochs=25,
validation_data=(x_test, y_test))
print(model.summary())
'''
I am grateful for every hint.
Thank you.
I am new in Keras. I want to implement a layer where not all the weights will update. For example, in the following code, I want the dilation layer will update in a way that some center weights are never updated. For say, the shape of each feature matrix (out of 1024) in the dilation layer is 448, 448 and a block of 8x8 at the center of all feature matrices will never be updated, i.e. the 8x8 block is a (non-trainable) mask to the feature matrices.
input_layer=Input(shape=(896,896,3))
new_layer = Conv2D(32, kernel_size=(3,3), padding="same", activation='relu', kernel_initializer='he_normal')(input_layer)
new_layer = MaxPooling2D(pool_size=(2, 2), strides=(2,2), padding='same', data_format=None)(new_layer)
new_layer = Conv2D(64, kernel_size=(3,3), padding='same', activation='relu', kernel_initializer='he_normal')(new_layer)
new_layer = Conv2D(1024, kernel_size=(7,7), dilation_rate=8, padding="same", activation='relu', kernel_initializer='he_normal', name='dialation')(new_layer)
new_layer = Conv2D(32, kernel_size=(1,1), padding="same", activation='relu', kernel_initializer='he_normal')(new_layer)
new_layer = Conv2D(32, kernel_size=(1,1), padding="same", activation='relu', kernel_initializer='he_normal')(new_layer)
model = Model(input_layer, new_layer)
I was trying with the Keras's custom layer [link], but it was difficult for me to understand. Anyone would please help.
UPDATE:
I added the following figure for a better understanding. The dilation layer contains 1024 features. I want the middle region of each feature to be non-trainable (static).
Use this mask for both cases:
mask = np.zeros((1,448,448,1))
mask[:,220:228,220:228] = 1
Replacing part of the feature
If you replace part of the feature with constant values, this means the feature will be static, but it will still participate in backpropagation (because weights will still be multiplied and summed for this part of the image and there is a connection)
constant = 0 (will annulate kernel, but not bias)
def replace(x):
return x*(1-mask) + constant*mask
#before the dilation layer
new_layer=Lambda(replace)(new_layer)
Keeping the feature value, but stopping backpropagation
Here, the weights of the dilation layer and further will be updated normally, but the weights before the dilation layer will not receive the influence of the central region.
def stopBackprop(x):
stopped=K.stop_gradients(x)
return x*(1-mask) + stopped*mask
#before the dilation layer
new_layer=Lambda(stopBackprop)(new_layer)
I am working on clustering weights and then freezing specific clusters and train the network.
I am trying to freeze the specific weights in this network using the above example. But I'm not sure how to set the shape of the mask and custom layer in run_certain_weights().
This is the code I'm using:
from keras.layers import Dense, Flatten, Lambda
from keras.utils import to_categorical
from keras.models import Sequential, load_model
from keras.datasets import mnist
from keras.losses import categorical_crossentropy
from keras.backend import stop_gradient
import numpy as np
def load_data():
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
y_train = to_categorical(y_train, num_classes=10)
y_test = to_categorical(y_test, num_classes=10)
return x_train, y_train, x_test, y_test
def run():
x_train, y_train, x_test, y_test = load_data()
model=Sequential(Flatten(input_shape=(28, 28)))
layer = Dense(300, name='dense1', activation='relu')
layer.trainable=True
model.add(layer)
layer2 = Dense(100, name='dense2', activation='relu')
layer2.trainable=False
model.add(layer2)
layer3 = Dense(10, name='dense3', activation='softmax')
model.add(layer3)
model.compile(loss=categorical_crossentropy, optimizer='Adam',metrics ['accuracy'])
print(model.summary())
print("x_train.shape():",x_train.shape)
print("y_train.shape()",y_train.shape)
model.fit(x_train, y_train, epochs=5, verbose=2)
print(model.evaluate(x_test, y_test))
return model
def stopBackprop(x):
stopped=stop_gradient(x)
return x*(1-mask) + stopped*mask
def run_certain_weights():
x_train, y_train, x_test, y_test = load_data()
model=Sequential(Flatten(input_shape=(28, 28)))
mask = np.zeros((300,))
print(mask.shape)
mask[220:228,] = 1
layer = Dense(300, name='dense1', activation='relu')
layer.trainable=False
model.add(layer)
#before the dense2 layer
new_layer=Lambda(stopBackprop)(layer)
model.add(new_layer)
layer2 = Dense(300, name='dense2', activation='relu')
layer2.trainable=True
model.add(layer2)
layer3 = Dense(10, name='dense3', activation='softmax')
model.add(layer3)
model.compile(loss=categorical_crossentropy, optimizer='Adam',metrics = ['accuracy'])
print(model.summary())
print("x_train.shape():",x_train.shape)
print("y_train.shape()",y_train.shape)
model.fit(x_train, y_train, epochs=5, verbose=2)
print(model.evaluate(x_test, y_test))
return model
def freeze(model):
x_train, y_train, x_test, y_test = load_data()
name = 'dense2'
weightsAndBias = model.get_layer(name=name).get_weights()
# freeze the weights of this layer
model.get_layer(name=name).trainable = False
# record the weights before retrain
weights_before = weightsAndBias[0]
# retrain
print("x_train.shape():",x_train.shape)
print("y_train.shape()",y_train.shape)
model.fit(x_train, y_train, verbose=2, epochs=1)
weights_after = model.get_layer(name=name).get_weights()[0]
if (weights_before == weights_after).all():
print('the weights did not change!!!')
else:
print('the weights changed!!!!')
if __name__ == '__main__':
model = run()
freeze(model)
model = run_certain_weights()
freeze(model)
I have a simple code, which DOES work, for training a Keras model in Tensorflow using numpy arrays as features and labels. If I then wrap these numpy arrays using tf.data.Dataset.from_tensor_slices in order to train the same Keras model using a tensorflow dataset, I get an error. I haven't been able to figure out why (it may be a tensorflow or keras bug, but I may also be missing something). I'm on python 3, tensorflow is 1.10.0, numpy is 1.14.5, no GPU involved.
OBS1: The possibility of using tf.data.Dataset as a Keras input is showed in https://www.tensorflow.org/guide/keras, under "Input tf.data datasets".
OBS2: In the code below, the code under "#Train with numpy arrays" is being executed, using numpy arrays. If this code is commented and the code under "#Train with tf.data datasets" is used instead, the error will be reproduced.
OBS3: In line 13, which is commented and starts with "###WORKAROUND 1###", if the comment is removed and the line is used for tf.data.Dataset inputs, the error changes, even though I can't completely understand why.
The complete code is:
import tensorflow as tf
import numpy as np
np.random.seed(1)
tf.set_random_seed(1)
print(tf.__version__)
print(np.__version__)
#Import mnist dataset as numpy arrays
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()#Import
x_train, x_test = x_train / 255.0, x_test / 255.0 #normalizing
###WORKAROUND 1###y_train, y_test = (y_train.astype(dtype='float32'), y_test.astype(dtype='float32'))
x_train = np.reshape(x_train, (x_train.shape[0], x_train.shape[1]*x_train.shape[2])) #reshaping 28 x 28 images to 1D vectors, similar to Flatten layer in Keras
batch_size = 32
#Create a tf.data.Dataset object equivalent to this data
tfdata_dataset_train = tf.data.Dataset.from_tensor_slices((x_train, y_train))
tfdata_dataset_train = tfdata_dataset_train.batch(batch_size).repeat()
#Creates model
keras_model = tf.keras.models.Sequential([
tf.keras.layers.Dense(512, activation=tf.nn.relu),
tf.keras.layers.Dropout(0.2, seed=1),
tf.keras.layers.Dense(10, activation=tf.nn.softmax)
])
#Compile the model
keras_model.compile(optimizer='adam',
loss=tf.keras.losses.sparse_categorical_crossentropy,
metrics=['accuracy'])
#Train with numpy arrays
keras_training_history = keras_model.fit(x_train,
y_train,
initial_epoch=0,
epochs=1,
batch_size=batch_size
)
#Train with tf.data datasets
#keras_training_history = keras_model.fit(tfdata_dataset_train,
# initial_epoch=0,
# epochs=1,
# steps_per_epoch=60000//batch_size
# )
print(keras_training_history.history)
The error observed when using tf.data.Dataset as input is:
(...)
ValueError: Tensor conversion requested dtype uint8 for Tensor with dtype float32: 'Tensor("metrics/acc/Cast:0", shape=(?,), dtype=float32)'
During handling of the above exception, another exception occurred:
(...)
TypeError: Input 'y' of 'Equal' Op has type float32 that does not match type uint8 of argument 'x'.
The error when removing the comment from line 13, as commented above in OBS3, is:
(...)
tensorflow.python.framework.errors_impl.InvalidArgumentError: In[0] is not a matrix
[[Node: dense/MatMul = MatMul[T=DT_FLOAT, _class=["loc:#training/Adam/gradients/dense/MatMul_grad/MatMul_1"], transpose_a=false, transpose_b=false, _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_sequential_input_0_0, dense/MatMul/ReadVariableOp)]]
Any help would be appreciated, including comments that you were able to reproduce the errors, so I can report the bug if it is the case.
I just upgraded to Tensorflow 1.10 to execute this code. I think that is the answer which is also discussed in the other Stackoverflow thread
This code executes but only if I remove the normalization as that line seems to use too much CPU memory. I see messages indicating that. I also reduced the cores.
import tensorflow as tf
import numpy as np
from tensorflow.keras.layers import Conv2D, MaxPool2D, Flatten, Dense, Dropout, Input
np.random.seed(1)
tf.set_random_seed(1)
batch_size = 128
NUM_CLASSES = 10
print(tf.__version__)
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()
#x_train, x_test = x_train / 255.0, x_test / 255.0 #normalizing
def tfdata_generator(images, labels, is_training, batch_size=128):
'''Construct a data generator using tf.Dataset'''
def preprocess_fn(image, label):
'''A transformation function to preprocess raw data
into trainable input. '''
x = tf.reshape(tf.cast(image, tf.float32), (28, 28, 1))
y = tf.one_hot(tf.cast(label, tf.uint8), NUM_CLASSES)
return x, y
dataset = tf.data.Dataset.from_tensor_slices((images, labels))
if is_training:
dataset = dataset.shuffle(1000) # depends on sample size
# Transform and batch data at the same time
dataset = dataset.apply(tf.contrib.data.map_and_batch(
preprocess_fn, batch_size,
num_parallel_batches=2, # cpu cores
drop_remainder=True if is_training else False))
dataset = dataset.repeat()
dataset = dataset.prefetch(tf.contrib.data.AUTOTUNE)
return dataset
training_set = tfdata_generator(x_train, y_train,is_training=True, batch_size=batch_size)
testing_set = tfdata_generator(x_test, y_test, is_training=False, batch_size=batch_size)
inputs = Input(shape=(28, 28, 1))
x = Conv2D(32, (3, 3), activation='relu', padding='valid')(inputs)
x = MaxPool2D(pool_size=(2, 2))(x)
x = Conv2D(64, (3, 3), activation='relu')(x)
x = MaxPool2D(pool_size=(2, 2))(x)
x = Flatten()(x)
x = Dense(512, activation='relu')(x)
x = Dropout(0.5)(x)
outputs = Dense(NUM_CLASSES, activation='softmax')(x)
keras_model = tf.keras.Model(inputs, outputs)
#Compile the model
keras_model.compile('adam', 'categorical_crossentropy', metrics=['acc'])
#Train with tf.data datasets
keras_training_history = keras_model.fit(
training_set.make_one_shot_iterator(),
steps_per_epoch=len(x_train) // batch_size,
epochs=5,
validation_data=testing_set.make_one_shot_iterator(),
validation_steps=len(x_test) // batch_size,
verbose=1)
print(keras_training_history.history)
Installing the tf-nightly build, together with changing dtypes of some tensors (the error changes after installing tf-nightly), solved the problem, so it is an issue which (hopefully) will be solved in 1.11.
Related material: https://github.com/tensorflow/tensorflow/issues/21894
I am wondering how Keras is able to do 5 epochs when the
make_one_shot_iterator() which only supports iterating once through a
dataset?
could be given smth like iterations = len(y_train) * epochs - here shown for tf.v1
the code from Mohan Radhakrishnan still works in tf.v2 with little corrections in objects' belongings to new classes (in tf.v2) fixings - to make the code up-to-date... No more make_one_shot_iterator() needed
# >> author: Mohan Radhakrishnan
import tensorflow as tf
import tensorflow.keras
import numpy as np
from tensorflow.keras.layers import Conv2D, MaxPool2D, Flatten, Dense, Dropout, Input
np.random.seed(1)
tf.random.set_seed(1)
batch_size = 128
NUM_CLASSES = 10
print(tf.__version__)
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()
#x_train, x_test = x_train / 255.0, x_test / 255.0 #normalizing
def tfdata_generator(images, labels, is_training, batch_size=128):
'''Construct a data generator using tf.Dataset'''
def preprocess_fn(image, label):
'''A transformation function to preprocess raw data
into trainable input. '''
x = tf.reshape(tf.cast(image, tf.float32), (28, 28, 1))
y = tf.one_hot(tf.cast(label, tf.uint8), NUM_CLASSES)
return x, y
dataset = tf.data.Dataset.from_tensor_slices((images, labels))
if is_training:
dataset = dataset.shuffle(1000) # depends on sample size
# Transform and batch data at the same time
dataset = dataset.apply( tf.data.experimental.map_and_batch(
preprocess_fn, batch_size,
num_parallel_batches=2, # cpu cores
drop_remainder=True if is_training else False))
dataset = dataset.repeat()
dataset = dataset.prefetch( tf.data.experimental.AUTOTUNE)
return dataset
training_set = tfdata_generator(x_train, y_train,is_training=True, batch_size=batch_size)
testing_set = tfdata_generator(x_test, y_test, is_training=False, batch_size=batch_size)
inputs = Input(shape=(28, 28, 1))
x = Conv2D(32, (3, 3), activation='relu', padding='valid')(inputs)
x = MaxPool2D(pool_size=(2, 2))(x)
x = Conv2D(64, (3, 3), activation='relu')(x)
x = MaxPool2D(pool_size=(2, 2))(x)
x = Flatten()(x)
x = Dense(512, activation='relu')(x)
x = Dropout(0.5)(x)
outputs = Dense(NUM_CLASSES, activation='softmax')(x)
keras_model = tf.keras.Model(inputs, outputs)
#Compile the model
keras_model.compile('adam', 'categorical_crossentropy', metrics=['acc'])
#Train with tf.data datasets
# training_set.make_one_shot_iterator() - 'PrefetchDataset' object has no attribute 'make_one_shot_iterator'
keras_training_history = keras_model.fit(
training_set,
steps_per_epoch=len(x_train) // batch_size,
epochs=5,
validation_data=testing_set,
validation_steps=len(x_test) // batch_size,
verbose=1)
print(keras_training_history.history)
not loading data locally, just easy DataFlow - that is very convinient - Thanks a lot - hope my corrections are proper