[code-quality] Keras question

[Abdul Abdul]

Hello,

Happy new year! I wish you a happy, productive, and fruitful new year.

I just have a Keras question and through you might have an idea on it,
especially that I have been trying to solve the issue for a while now but
couldn't yet solve the issue.

The following code always predicts the same class. I tried balancing the
training dataset and used different data (i.e. melanoma vs. nevus, cats vs.
dogs), but always having only "1" class predicted.

from keras import layers
>     from keras import models
>     from keras import optimizers
>     from keras.preprocessing.image import ImageDataGenerator
>     from sklearn.metrics import roc_curve
>     from sklearn.metrics import auc
>     import cv2
>     import numpy as np
>     import os
>
>     train_directory = '/train'
>     validation_directory = '/valid'
>     test_directory = '/test'
>     results_directory = '/results'
>     correct_classification = 0
>     number_of_test_images = 0
>     labels = []
>     prediction_probabilities = []
>
>     model = models.Sequential()
>
>
> model.add(layers.Conv2D(32,(3,3),activation='relu',input_shape=(512,512,3)))
>     model.add(layers.MaxPooling2D(2,2))
>     model.add(layers.Conv2D(64,(3,3),activation='relu'))
>     model.add(layers.MaxPooling2D(2,2))
>     model.add(layers.Conv2D(128,(3,3),activation='relu'))
>     model.add(layers.MaxPooling2D(2,2))
>     model.add(layers.Conv2D(256,(3,3),activation='relu'))
>     model.add(layers.MaxPooling2D(2,2))
>     model.add(layers.Conv2D(512,(3,3),activation='relu'))
>     model.add(layers.MaxPooling2D(2,2))
>
>     model.add(layers.Flatten())
>     model.add(layers.Dense(1024,activation='relu'))
>     model.add(layers.Dense(1,activation='sigmoid'))
>
>
> model.compile(loss='binary_crossentropy',optimizer='rmsprop',metrics=['acc'])
>
>     train_data = ImageDataGenerator(rescale=1.0/255)
>     validation_data = ImageDataGenerator(rescale=1.0/255)
>
>     train_generator =
> train_data.flow_from_directory(train_directory,target_size=(512,512),batch_size=20,class_mode='binary')
>     validation_generator =
> validation_data.flow_from_directory(validation_directory,target_size=(512,512),batch_size=20,class_mode='binary')
>
>     history = model.fit_generator(train_generator,
>     steps_per_epoch=10,
>     epochs=10,
>     validation_data=validation_generator,
>     validation_steps=5)
>
>     model.save('my_model.h5')
>
>     for root, dirs, files in os.walk(test_directory):
>     for file in files:
>     img = cv2.imread(root + '/' + file)
>     img = cv2.resize(img,(512,512),interpolation=cv2.INTER_AREA)
>     img = np.expand_dims(img, axis=0)
>     img = img/255.0
>     if os.path.basename(root) == 'nevus':
>     label = 1
>     elif os.path.basename(root) == 'melanoma':
>     label = 0
>     labels.append(label)
>     img_class = model.predict_classes(img)
>     img_class_probability = model.predict(img)
>     prediction_probability = img_class_probability[0]
>     prediction_probabilities.append(prediction_probability)
>     prediction = img_class[0]
>     if prediction == label:
>     correct_classification = correct_classification + 1


Any ideas on how the issue could be solved?

Thanks a lot, and appreciate you kind support.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.python.org/pipermail/code-quality/attachments/20190107/de9d8868/attachment.html>