I am running a simple CNN model in Keras. Code:
from __future__ import print_function
import numpy as np
import keras
from keras.datasets import mnist
from keras.models import Sequential, Model
from keras.layers import Dense, Dropout, Flatten, Activation, Input
from keras.layers import Conv2D, MaxPooling2D
from keras import backend as K
import tensorflow as tf
batch_size = 128
num_classes = 10
epochs = 1
# input image dimensions
img_rows, img_cols = 28, 28
# the data, shuffled and split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()
if K.image_data_format() == 'channels_first':
x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
input_shape = (1, img_rows, img_cols)
else:
x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
input_shape = (img_rows, img_cols, 1)
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')
# convert class vectors to binary class matrices
y_train = tf.keras.utils.to_categorical(y_train, num_classes)
y_test = tf.keras.utils.to_categorical(y_test, num_classes)
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(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax', name='preds'))
model.compile(loss=keras.losses.categorical_crossentropy,
optimizer=tf.keras.optimizers.Adam(),
metrics=['accuracy'])
model.fit(x_train, y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_data=(x_test, y_test))
I want to visualize the dense layers. For this, I am using keras-vis
While running the following code:
from vis.visualization import visualize_activation
from vis.utils import utils
from keras import activations
from matplotlib import pyplot as plt
%matplotlib inline
plt.rcParams['figure.figsize'] = (18, 6)
# Utility to search for layer index by name.
# Alternatively we can specify this as -1 since it corresponds to the last layer.
layer_idx = utils.find_layer_idx(model, 'preds')
# Swap softmax with linear
model.layers[layer_idx].activation = activations.linear
model = utils.apply_modifications(model)
# This is the output node we want to maximize.
filter_idx = 0
img = visualize_activation(model, layer_idx, filter_indices=filter_idx)
plt.imshow(img[..., 0])
I am getting the following error:
InvalidArgumentError: conv2d_2_input_2:0 is both fed and fetched.
Solutions that I have tried
Installing Keras-vis from source for the latest build
Applying Changes from PR mentioned in issues
Version:
Keras : 2.7
Keras-Vis : 0.5
Related
I've been trying to train a convlstm model on mnist dataset to broaden my knowledge in model development. I cannot escape the error that I have included in the title. Any help or hint is appreciated!
I know the default for strides is (1,1) but am unsure how 2 is being set.
import tensorflow as tf
from keras.models import Sequential
from keras.layers import Dense, Dropout, LSTM, CuDNNLSTM, TimeDistributed, Reshape
from keras.utils import to_categorical
from keras.layers.convolutional import Conv2D, Conv3D
from keras.layers.pooling import MaxPooling2D, MaxPool3D
from keras.layers.core import Flatten
def prep_pixels(train, test):
# convert from integers to floats
train_norm = train.astype('float32')
test_norm = test.astype('float32')
# normalize to range 0-1
train_norm = train_norm / 255.0
test_norm = test_norm / 255.0
# return normalized images
return train_norm, test_norm
mnist = tf.keras.datasets.mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = x_train.reshape((x_train.shape[0], 28, 28, 1))
x_test = x_test.reshape((x_test.shape[0], 28, 28, 1))
y_train = to_categorical(y_train)
y_test = to_categorical(y_test)
x_train, x_test = prep_pixels(x_train, x_test)
model = Sequential()
model.add(TimeDistributed(Conv2D(32, (3, 3), activation='relu', input_shape=(28, 28, 1))))
model.add(TimeDistributed((MaxPooling2D((2, 2)))))
model.add(TimeDistributed(Flatten()))
model.add(LSTM(32, activation='relu', return_sequences=True))
model.add(Dropout(0.2))
model.add(Dense(10, activation='softmax'))
opt = tf.keras.optimizers.Adam(lr=1e-3, decay=1e-5)
model.compile(loss='categorical_crossentropy', optimizer=opt, metrics=['accuracy'])
model.fit(x_train, y_train, epochs=1, validation_data=(x_test, y_test))
ERROR
model.fit(x_train, y_train, epochs=1, validation_data=(x_test, y_test))
strides = _get_sequence(strides, n, channel_index, "strides")
ValueError: strides should be of length 1, 1 or 3 but was 2
It seems like you haven't created a windowed dataset for your ConvLSTM. So you might want to do this before calling model.fit
d_train = tf.keras.preprocessing.sequence.TimeseriesGenerator(x_train, y_train, length=5, batch_size=64) # window size = 5
d_test = tf.keras.preprocessing.sequence.TimeseriesGenerator(x_test, y_test, length=5)
model.fit(d_train, epochs=1, validation_data=d_test)
To be consistent with your loss function, you will need to disable return sequences (or add another layer that does not return sequences).
model.add(tf.keras.layers.LSTM(32, activation='relu', return_sequences=False))
I work with the Keras MNIST dataset and I now I want to use the google dataset Street view house numbers (SVHN) to train my program. I don't know what I have to modify to load the SVHN dataset ( file .mat) in my code
from __future__ import print_function
import keras
from keras.datasets import mnist
from keras import backend as K
import tensorflow as tf
import matplotlib.pyplot as plt
from keras.models import Sequential
from keras.layers import Dense, Conv2D, Dropout, Flatten, MaxPooling2D
img_rows, img_cols = 28, 28
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()
image_index = 7777
print(y_train[image_index])
plt.imshow(x_train[image_index], cmap='Greys')
x_train.shape
x_train = x_train.reshape(x_train.shape[0], 28, 28, 1)
x_test = x_test.reshape(x_test.shape[0], 28, 28, 1)
input_shape = (28, 28, 1)
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
print('x_train shape:', x_train.shape)
print('Number of images in x_train', x_train.shape[0])
print('Number of images in x_test', x_test.shape[0])
model = Sequential()
model.add(Conv2D(28, kernel_size=(3,3), input_shape=input_shape))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(128, activation=tf.nn.relu))
model.add(Dropout(0.2))
model.add(Dense(10,activation=tf.nn.softmax))
model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
model.fit(x=x_train,y=y_train, epochs=2)
model.evaluate(x_test, y_test)
image_index = 9999
plt.imshow(x_test[image_index].reshape(28, 28),cmap='Greys')
pred = model.predict(x_test[image_index].reshape(1, img_rows, img_cols, 1))
print(pred.argmax())
You can read .mat files using scipy.io.loadmat which returns a dict with values as numpy arrays. See documentations here. You may need to reshape the data according to your requirement.
Notice that they mention
You will need an HDF5 python library to read MATLAB 7.3 format mat files.
I trained the CNN on MNIST dataset with training and validation accuracy of ~0.99.
I followed the exact steps from the example given at the Keras documentation of implementing CNN with MNIST dataset:
import cv2
import numpy as np
import tensorflow.keras as keras
import math
from __future__ import print_function
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras import backend as K
batch_size = 128
num_classes = 10
epochs = 12
# input image dimensions
img_rows, img_cols = 28, 28
# the data, split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()
if K.image_data_format() == 'channels_first':
x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
input_shape = (1, img_rows, img_cols)
else:
x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
input_shape = (img_rows, img_cols, 1)
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')
# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
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(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))
model.compile(loss=keras.losses.categorical_crossentropy,
optimizer=keras.optimizers.Adadelta(),
metrics=['accuracy'])
model.fit(x_train, y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_data=(x_test, y_test))
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])
When I tested the following image:
using the following test code:
img = cv2.imread("m9.png", 0)
img = cv2.resize(img, (28,28))
img = img / 255.
prob = model.predict_proba(img.reshape((1,28, 28, 1)))
print(prob)
model.predict_classes(img.reshape((1,28, 28, 1)))
The class it prints out is array([1]) , denoting number 1. I could not understand the reason for it. Did I try to predict in an incorrect way?
Exactly same class array([1]) was predicted for number 8 as shown below:
It looks like I have made an error during prediction? I tried to understand what could be happening but could not understand.
There is no error, its just that your images don't look at all like the ones in the MNIST dataset. This dataset is not meant to train a general digit recognition algorithm, it will only work with similar images.
In your case the digits will be very small in a 28x28 image, so the predictions are kind of random.
You are resizing the input image to 28 X 28. Instead you should first crop the image around the digit to make it look like the data-set in MNIST. Otherwise in resized image, the digit will occupy very small portion and results will be arbitrary.
I use the following code (courtesy to here) which runs CNN for training MNIST images:
from __future__ import print_function
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras import backend as K
batch_size = 128
num_classes = 10
epochs = 1
# input image dimensions
img_rows, img_cols = 28, 28
# the data, split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()
if K.image_data_format() == 'channels_first':
x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
input_shape = (1, img_rows, img_cols)
else:
x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
input_shape = (img_rows, img_cols, 1)
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')
# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
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(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))
model.compile(loss=keras.losses.categorical_crossentropy,
optimizer=keras.optimizers.Adadelta(),
metrics=['accuracy'])
model.fit(x_train, y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_data=(x_test, y_test))
print(model.save_weights('file.txt')) # <<<<<----
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])
My goal is to use CNN model to extract MNIST features into a dataset that I can use as an input for another classifier. In this example, I don't care about the classification operation since all I need is the features of the trained images. The only method I found is save_weights as:
print(model.save_weights('file.txt'))
How can I extract features into a dataset from keras model?
After training or loading the existing trained model, you can create another model:
extract = Model(model.inputs, model.layers[-3].output) # Dense(128,...)
features = extract.predict(data)
and use the .predict method to return the vectors from a specific layer, in this case every image will become (128,), the output of the Dense(128, ...) layer.
You can also train these networks jointly with 2 outputs using the functional API. Follow the guide and you'll see that you can chain models together and have multiple outputs each possibly with a separate loss. This will allow your model to learn shared features that is useful for both classifying the MNIST image and your task at the same time.
I am trying out the mnist tutorial using keras at https://github.com/fchollet/keras/blob/master/examples/mnist_cnn.py but am getting really low accuracy. I got a test accuracy of 83% on my 1st trial after 12 epochs and 75% on my 2nd trial. The page claims that it is able to get 99.25% test accuracy after 12 epochs. I am not sure why this is happening because I literally copy pasted the code into PyCharm.
I am using Keras version 2.0.0 with Tensorflow version 0.12.1 as its backend. Training is done via CPU.
Could the reason be due to the version? Should I upgrade to the latest versions of Keras and Tensorflow? I hope someone can run the exact code and let me know of their results after 12 epochs with the Keras and Tensorflow version.
Or could the reason be due to the variability in deep learning and that I might eventually get a ~99% test accuracy after 12 epochs if I run enough simulations. This is the code in case anyone doesn't wanna get into the link
'''Trains a simple convnet on the MNIST dataset.
Gets to 99.25% test accuracy after 12 epochs
(there is still a lot of margin for parameter tuning).
16 seconds per epoch on a GRID K520 GPU.
'''
from __future__ import print_function
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras import backend as K
batch_size = 128
num_classes = 10
epochs = 12
# input image dimensions
img_rows, img_cols = 28, 28
# the data, shuffled and split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()
if K.image_data_format() == 'channels_first':
x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
input_shape = (1, img_rows, img_cols)
else:
x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
input_shape = (img_rows, img_cols, 1)
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')
# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
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(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))
model.compile(loss=keras.losses.categorical_crossentropy,
optimizer=keras.optimizers.Adadelta(),
metrics=['accuracy'])
model.fit(x_train, y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_data=(x_test, y_test))
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])