I am starting to learn Python and trying create a neural network, which detects and localizes anomalious parts of images. I am using a pretrained CNN from TensorFlow. The code works so far as it learns my images and classifies them. But when I give him the same amount (around 100) of images for each class. the accuracy is around 50% which is random for two classes. So I am looking for a solution for it right now. The localization Problem I solving by slicing my images in to multiple parts. The anomaly is being split from non-anomalous region while every image has an reference of its location in its name. So when the image is classified as a certain class one also finds out about its location by its name.
first option: I have to find for a way to extent the amount of my images to look if it improves my accuracy.I didn't work on that yet. second option: trying to tune the hyper parameters of the CNN, maybe put my images in some earlier layers. I watched a couple tutorials and tried to implement them, but they all failed mostly due to the shape of the arrays or inconsistent numbers.
# Use scikit-learn to grid search the batch size and epochs import numpy from sklearn.model_selection import GridSearchCV from keras.models import Sequential from keras.layers import Dense from keras.wrappers.scikit_learn import KerasClassifier # Function to create model, required for KerasClassifier def create_model(): # create model model = Sequential() model.add(Dense(12, input_dim=8, activation='relu')) model.add(Dense(1, activation='sigmoid')) # Compile model model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy']) return model # fix random seed for reproducibility seed = 7 numpy.random.seed(seed) # load dataset # create model model = KerasClassifier(build_fn=create_model, verbose=0) # define the grid search parameters batch_size = [10, 20, 40, 60, 80, 100] epochs = [10, 50, 100] param_grid = dict(batch_size=batch_size, epochs=epochs) grid = GridSearchCV(estimator=model, param_grid=param_grid, n_jobs=-1) grid_result = grid.fit(x_train, label_batch) # summarize results print("Best: %f using %s" % (grid_result.best_score_, grid_result.best_params_)) means = grid_result.cv_results_['mean_test_score'] stds = grid_result.cv_results_['std_test_score'] params = grid_result.cv_results_['params'] for mean, stdev, param in zip(means, stds, params): print("%f (%f) with: %r" % (mean, stdev, param)) init = tf.global_variables_initializer() sess.run(init) result = model.predict(image_batch) result.shape model.compile( optimizer=tf.train.AdamOptimizer(), loss='categorical_crossentropy', metrics=['accuracy']) class CollectBatchStats(tf.keras.callbacks.Callback): def __init__(self): self.batch_losses = [] self.batch_acc = [] def on_batch_end(self, batch, logs=None): self.batch_losses.append(logs['loss']) self.batch_acc.append(logs['acc']) steps_per_epoch = image_data.samples//image_data.batch_size batch_stats = CollectBatchStats() model.fit((item for item in image_data), epochs=1, steps_per_epoch=steps_per_epoch, callbacks = [batch_stats]) 
