We Keep Coding

How process image on Convolutional Neural network [duplicate]

In ImageDataGenerator of Keras the flow method has argument x which takes data with rank 4. Why?
I have a test image which has RGB (150, 150, 3).
Data has been trained on the images of type (150,150,3) where 150,150 are width and height, and 3 is for RGB. But I am getting error
ValueError: ('Input data in NumpyArrayIterator should have rank 4. You passed an array with shape', (3, 150, 150))
how can an image have shape with rank 4?
and how to make test input image type with rank 4?
For the reference, my code is as per follow:
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D
from keras.layers import Activation, Dropout, Flatten, Dense
from keras import backend as K
# dimensions of our images.
img_width, img_height = 150, 150
train_data_dir = 'C:/Users/imageNetToyDataset/train'
validation_data_dir = 'C:/Users/imageNetToyDataset/validation'
epochs = 5
nb_train_samples = 2000
nb_validation_samples = 50
batch_size = 16
input_shape = (img_width, img_height, 3)
model = Sequential()
model.add(Conv2D(32, (3, 3), input_shape=input_shape))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('sigmoid'))
model.compile(loss='binary_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
train_datagen = ImageDataGenerator(
rescale=1. / 255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
# this is the augmentation configuration we will use for testing:
# only rescaling
test_datagen = ImageDataGenerator(rescale=1. / 255)
train_generator = train_datagen.flow_from_directory(
train_data_dir,
target_size=(img_width, img_height),
batch_size=batch_size,
class_mode='binary')
validation_generator = test_datagen.flow_from_directory(
validation_data_dir,
target_size=(img_width, img_height),
batch_size=batch_size,
class_mode='binary')
model.fit_generator(
train_generator,
steps_per_epoch=nb_train_samples // batch_size,
epochs=epochs,
validation_data=validation_generator,
validation_steps=nb_validation_samples // batch_size)
import numpy as np
import cv2
import csv
import os
from keras.preprocessing.image import ImageDataGenerator, array_to_img,
img_to_array, load_img
from scipy.misc import imresize
import scipy
def predict_labels(model):
"""writes test image labels and predictions to csv"""
test_data_dir = "C:/Users/imageNetToyDataset/test"
test_datagen = ImageDataGenerator(rescale=1./255)
test_generator = test_datagen.flow_from_directory(
test_data_dir,
target_size=(img_width, img_height),
batch_size=32,
shuffle=False,
class_mode="binary")
with open("prediction.csv", "w") as f:
p_writer = csv.writer(f, delimiter=',', lineterminator='\n')
for _, _, imgs in os.walk(test_data_dir):
print ("number of images: {}".format(len(imgs)))
for im in imgs:
print ("image:\n{}".format(im))
pic_id = im.split(".")[0]
imgPath = os.path.join(test_data_dir,im)
print (imgPath)
img = load_img(imgPath)
img = imresize(img, size=(img_width, img_height))
print ("img shape = {}".format(img.shape))
test_x = img_to_array(img).reshape(3, img_width, img_height)
print ("test_x shape = {}".format(test_x.shape))
test_generator = test_datagen.flow(test_x,
batch_size=1,
shuffle=False)
prediction = model.predict_generator(test_generator,1,epochs)
p_writer.writerow([pic_id, prediction])
prediction=predict_labels(model)

The forth dimension is the number of samples in a batch.
Look at https://keras.io/preprocessing/image/ at the data_format explanation

Unable to Compile Model CNN-LSTM Image Classification

I am planning to use CNN+LSTM for image classification into 4 categories.
I am not really familiar on how to combining CNN and LSTM.
I faced an error: You must compile your model before using it. when I am trying to compile CNN+LSTM.
The data sets are a series of medical images. I am able to get roughly 70% accuracy by using CNN alone (small sample size of around 300 samples only), so I decided to combine LSTM to see if there will be a boost in accuracy.
from keras.optimizers import RMSprop
from keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras import Sequential
from tensorflow.keras.layers import (LSTM, Dense, Embedding, Dropout, Conv2D, BatchNormalization, Activation,
MaxPooling2D, Flatten, TimeDistributed, SpatialDropout1D)
train_datagen = ImageDataGenerator(rescale=1. / 255, shear_range=0.2, zoom_range=0.2, rotation_range=45,
horizontal_flip=True, vertical_flip=True, validation_split=.2)
validation_datagen = ImageDataGenerator(rescale=1. / 255, validation_split=.2)
test_datagen = ImageDataGenerator(rescale=1. / 255)
train_generator = train_datagen.flow_from_directory(directory=r'', target_size=(224, 224), color_mode="rgb",
batch_size=32, class_mode='categorical', shuffle=True, seed=42)
validation_generator = validation_datagen.flow_from_directory(directory=r'', target_size=(224, 224), color_mode="rgb",
batch_size=32, class_mode='categorical', shuffle=True,
seed=42)
test_generator = test_datagen.flow_from_directory(directory=r'', target_size=(224, 224), color_mode="rgb",
batch_size=1, class_mode=None, shuffle=False, seed=42)
num_classes = 4
input_shape = (224, 224, 3)
# input image dimensions
img_rows, img_cols = 224, 224
model = Sequential()
# define CNN model
model.add(TimeDistributed(Conv2D(32, (3, 3), padding='same', input_shape=input_shape)))
model.add(TimeDistributed(BatchNormalization()))
model.add(TimeDistributed(Activation('relu')))
model.add(TimeDistributed(MaxPooling2D(pool_size=(2, 2))))
model.add(TimeDistributed(Conv2D(64, (3, 3))))
model.add(TimeDistributed(BatchNormalization()))
model.add(TimeDistributed(Activation('relu')))
model.add(TimeDistributed(MaxPooling2D(pool_size=(2, 2))))
model.add(TimeDistributed(Dropout(0.25)))
model.add(TimeDistributed(Flatten()))
model.add(TimeDistributed(Dense(256)))
model.add(TimeDistributed(BatchNormalization()))
model.add(TimeDistributed(Activation('relu')))
model.add(TimeDistributed(Dropout(0.25)))
# define LSTM model
model.add(LSTM(100, input_shape=(5, 1), return_sequences=True))
model.add(LSTM(Embedding(8192, 256)))
model.add(LSTM(SpatialDropout1D(0.3)))
model.add(LSTM(256, dropout=0.3, recurrent_dropout=0.3))
model.add(Dense(256, activation='relu'))
model.add(Dropout(0.3))
model.add(Dense(5, activation='softmax'))
model.compile(loss=keras.losss.categorical_crossentropy, optimizer=RMSprop(lr=0.001, rho=0.9, epsilon=1e-08, decay=0.0),
metrics=['accuracy'])
STEP_SIZE_TRAIN = train_generator.n // train_generator.batch_size
STEP_SIZE_VALID = validation_generator.n // validation_generator.batch_size
model.fit_generator(generator=train_generator, steps_per_epoch=50, validation_data=validation_generator,
validation_steps=STEP_SIZE_VALID, epochs=30)

You can simply move the input_shape=input_shape out from Conv2D and put it in TimeDistributed. i.e.
model.add(TimeDistributed(Conv2D(32, (3, 3), padding='same'), input_shape=input_shape))

image classifer with multiple categories

hiya i followed a guide on how to make an image classifier from here https://blog.keras.io/building-powerful-image-classification-models-using-very-little-data.html and this categorizes it into only 2 categories these code gives me the F1 score and confusion matrix is there a way to make a multiple category image classifier using these codes my data sets right now are types of mushroom
import numpy
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D
from keras.layers import Activation, Dropout, Flatten, Dense
from keras import backend as K
import matplotlib.pyplot as plt
# dimensions of our images.
img_width, img_height = 150, 150
train_data_dir = r'C:\Users\Acer\imagerec\Mushrooms\TRAIN'
validation_data_dir = r'C:\Users\Acer\imagerec\Mushrooms\VAL'
nb_train_samples = 7025
nb_validation_samples = 6262
epochs = 50
batch_size = 16
if K.image_data_format() == 'channels_first':
input_shape = (3, img_width, img_height)
else:
input_shape = (img_width, img_height, 3)
model = Sequential()
model.add(Conv2D(32, (3, 3), input_shape=input_shape))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('sigmoid'))
model.compile(loss='binary_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
# this is the augmentation configuration we will use for training
train_datagen = ImageDataGenerator(
rescale=1. / 255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
# this is the augmentation configuration we will use for testing:
# only rescaling
test_datagen = ImageDataGenerator(rescale=1. / 255)
train_generator = train_datagen.flow_from_directory(
train_data_dir,
target_size=(img_width, img_height),
batch_size=batch_size,
class_mode='binary')
validation_generator = test_datagen.flow_from_directory(
validation_data_dir,
target_size=(img_width, img_height),
batch_size=batch_size,
class_mode='binary')
model.fit_generator(
train_generator,
steps_per_epoch=nb_train_samples // batch_size,
epochs=epochs,
validation_data=validation_generator,
validation_steps=nb_validation_samples // batch_size)
model.save_weights('first_try.h5')
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
import seaborn as sns
test_steps_per_epoch = numpy.math.ceil(validation_generator.samples / validation_generator.batch_size)
predictions = model.predict_generator(validation_generator, steps=test_steps_per_epoch)
# Get most likely class
predicted_classes = numpy.argmax(predictions, axis=1)
true_classes = validation_generator.classes
class_labels = list(validation_generator.class_indices.keys())
report = classification_report(true_classes, predicted_classes, target_names=class_labels)
print(report)
cm=confusion_matrix(true_classes,predicted_classes)
sns.heatmap(cm, annot=True)
print(cm)
plt.show()

You clearly defined a binary classification in your code. To turn it to a multi-class task, let's say to N class, you need to change your last layer from 1 Dense to N Dense, and for the activation, you should change it from sigmoid to softmax.
Last but not least, you should change your loss function from binary_crossentropy to categorical_crossentropy if your classes are already hot-encoded. Otherwise, you might want to go with sparse_categorical_crossentropy
That part of your code should seems something like this after applying the changes:
model.add(Dense(N))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
Where N is the number of different classes you have.
Edit: you also need to go from "binary" to "categorical" for class_mode in your generators. You should also check how to generate the labels (one-hot-encoded)

How to predict input probability of image using trained model in Keras?

I'm beginning ML and have come to a huge road bump, looked at this thing for hours. I want to get the predict() probability as output but the predictions are only outputting [[1.]] for every test image. Using larger numbers of training data and more epochs, the acc and validation acc are up to about 90% each. This is only binary classification but I don't want predict_classes. I have no idea why it's printing [[1.]]
Here is the code I'm using:
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D
from keras.layers import Activation, Dropout, Flatten, Dense
from keras import backend as K
img_width, img_height = 150, 150
train_data_dir = 'D:\Machine_Learning\\train'
validation_data_dir = 'D:\Machine_Learning\\test'
nb_train_samples = 20000
nb_validation_samples = 7000
epochs = 50
batch_size = 40
if K.image_data_format() == 'channels_first':
input_shape = (3, img_width, img_height)
else:
input_shape = (img_width, img_height, 3)
# Build model structure
model = Sequential()
model.add(Conv2D(32, (3, 3), input_shape=input_shape))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('sigmoid'))
model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy'])
# Image augmentation
train_datagen = ImageDataGenerator(
rescale=1. / 255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
test_datagen = ImageDataGenerator(rescale=1. / 255)
train_generator = train_datagen.flow_from_directory(
train_data_dir,
target_size=(img_width, img_height),
batch_size=batch_size,
class_mode='binary')
validation_generator = test_datagen.flow_from_directory(
validation_data_dir,
target_size=(img_width, img_height),
batch_size=batch_size,
class_mode='binary')
model.fit_generator(
train_generator,
steps_per_epoch=nb_train_samples // batch_size,
epochs=epochs,
validation_data=validation_generator,
validation_steps=nb_validation_samples // batch_size)
model.save('first_try.h5')
model.save_weights('my_weights.model')
And for predictions:
from keras.models import load_model
from keras.preprocessing import image
model = load_model('first_try.h5')
def prepare(image):
imageSize = 150
#imageArray = cv2.imread(filePath)
newImageArray = cv2.resize(image, (imageSize, imageSize))
return newImageArray.reshape(-1, imageSize, imageSize, 3)
for i in range(len(test_images)):
print(test_images[i])
im = prepare(test_images[i])
prediction = model.predict([im])
print(prediction)

Class lables absent from Keras Predictions

I am trying to solve the Cats vs Dogs problem using Keras. Here is the model I am using.
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D
from keras.layers import Activation, Dropout, Flatten, Dense
from keras import backend as K
from keras import regularizers
from keras.utils import plot_model
img_width, img_height = 150, 150
train_data_dir = 'kateVSdoge/train'
validation_data_dir = 'kateVSdoge/validation'
nb_train_samples = 2000
nb_validation_samples = 800
epochs = 50
batch_size = 16
if K.image_data_format() == 'channels_first':
input_shape = (3, img_width, img_height)
else:
input_shape = (img_width, img_height, 3)
model = Sequential()
model.add(Conv2D(32, (3, 3), input_shape=input_shape))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(1,kernel_regularizer=regularizers.l2(0.01),
activity_regularizer=regularizers.l1(0.01)))
model.add(Activation('sigmoid'))
model.compile(loss='binary_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
train_datagen = ImageDataGenerator(
rescale=1. / 255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
test_datagen = ImageDataGenerator(rescale=1. / 255)
train_generator = train_datagen.flow_from_directory(
train_data_dir,
target_size=(img_width, img_height),
batch_size=batch_size,
class_mode='binary')
validation_generator = test_datagen.flow_from_directory(
validation_data_dir,
target_size=(img_width, img_height),
batch_size=batch_size,
class_mode='binary',
)
xm=model.fit_generator(
train_generator,
steps_per_epoch=nb_train_samples // batch_size,
epochs=epochs,
validation_data=validation_generator,
validation_steps=nb_validation_samples // batch_size)
model.save_weights('first_try3.h5')
model_json=model.to_json()
with open("model3.json","w+") as json_file:
json_file.write(model_json)
plot_model(model,to_file="model.jpeg")
The model trains well accuracy at the end is 0.79-0.80. But when I try to load the model in a predictor script and predict using the model.predict_generator() I seem to be doing something wrong as I cant get the class names in the prediction. I have tried .predict() and .predict_proba() without any success.
Here is the predictor script:
from keras.models import Sequential, model_from_json
from keras.preprocessing import image
from keras.preprocessing.image import ImageDataGenerator
import numpy as np
p_model = Sequential();
jsonfile = open('model3.json','r')
model_json = jsonfile.read()
p_model = model_from_json(model_json)
p_model.load_weights('first_try3.h5')
p_model.compile(loss='binary_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
img = image.load_img('do.jpg', target_size=(150,150))
x=image.img_to_array(img)
x=x.reshape((1,)+x.shape)
test_datagen = ImageDataGenerator(rescale=1. /255)
m=test_datagen.flow(x,batch_size=1)
preds = p_model.predict_generator(m,1,verbose=1)
print preds
Also I observed an Interesting thing , The image doesn't seem to rescale.
I printed out x and m.x , both the matrices seem to be equal and the values don't transform to be between 0 and 1.
Here is the output for a cat and a dog's picture respectively.
(myenv)link#zero-VirtualBox:~/myenv/keras_app$ python predictor.py
Using Theano backend.
1/1 [==============================] - 0s
[[ 0.29857877]]
(myenv)link#zero-VirtualBox:~/myenv/keras_app$ python predictor.py
Using Theano backend.
1/1 [==============================] - 0s
[[ 0.77536112]]
I have used the advice given here https://stackoverflow.com/a/41833076/4159447 to introduce regularizers and rescale.
What am I doing wrong? All I want is to get the cat and dog labels against their scores.

The only wrong thing is to expect class names from a classifier. The classifier doesn't know the class names, that is a post-processing step, something like:
preds = p_model.predict_generator(m,1,verbose=1)[0]
if preds > 0.5:
output = "cat"
else:
output = "dog"
Note that 0.5 might not be the best threshold, you can also take the class with biggest probability (p vs 1 - p).