Why am I getting GPU ran out of memory error here?

Question

I am very new to deep learning and am trying to make a cat / dog classifier using keras. The model was taking too much time for training on my laptop, so I decided to train it on my desktop with a GTX 750Ti (2GB). I am using keras with tensorflow-gpu backend but it gives me OOM error everytime. Even if I reduce the batch size to 1. How can I control the amount of data given to the gpu here?

CODE

from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Dense, Activation, Conv2D, MaxPooling2D, Flatten, Dropout
images = ImageDataGenerator()
train = images.flow_from_directory('./dataset', class_mode='binary', target_size=(200, 200), batch_size=64)

model = Sequential()

model.add(Conv2D(32, (3, 3), padding='same', input_shape=(200,200,3), activation='relu'))
model.add(Conv2D(32, (3, 3), padding='same', activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(64, (3, 3), padding='same', activation='relu'))
model.add(Conv2D(64, (3, 3), padding='same', activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(128, (3, 3), padding='same', activation='relu'))
model.add(Conv2D(128, (3, 3), padding='same', activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(256, (3, 3), padding='same', activation='relu'))
model.add(Conv2D(256, (3, 3), padding='same', activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Flatten())
model.add(Dense(256, activation='relu'))
model.add(Dropout(0.5))

model.add(Dense(256, activation='relu'))
model.add(Dropout(0.5))

model.add(Dense(1))
model.add(Activation('sigmoid'))

model.compile(loss='binary_crossentropy',
            optimizer='adam',
            metrics=['accuracy'])

model.fit_generator(train, steps_per_epoch=len(train.filenames)//32, epochs=100)

model.save_weights('model.h5')

Here is the model summary :

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_1 (Conv2D)            (None, 200, 200, 32)      896       
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 200, 200, 32)      9248      
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 100, 100, 32)      0         
_________________________________________________________________
conv2d_3 (Conv2D)            (None, 100, 100, 64)      18496     
_________________________________________________________________
conv2d_4 (Conv2D)            (None, 100, 100, 64)      36928     
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 50, 50, 64)        0         
_________________________________________________________________
conv2d_5 (Conv2D)            (None, 50, 50, 128)       73856     
_________________________________________________________________
conv2d_6 (Conv2D)            (None, 50, 50, 128)       147584    
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 25, 25, 128)       0         
_________________________________________________________________
conv2d_7 (Conv2D)            (None, 25, 25, 256)       295168    
_________________________________________________________________
conv2d_8 (Conv2D)            (None, 25, 25, 256)       590080    
_________________________________________________________________
max_pooling2d_4 (MaxPooling2 (None, 12, 12, 256)       0         
_________________________________________________________________
flatten_1 (Flatten)          (None, 36864)             0         
_________________________________________________________________
dense_1 (Dense)              (None, 256)               9437440   
_________________________________________________________________
dropout_1 (Dropout)          (None, 256)               0         
_________________________________________________________________
dense_2 (Dense)              (None, 256)               65792     
_________________________________________________________________
dropout_2 (Dropout)          (None, 256)               0         
_________________________________________________________________
dense_3 (Dense)              (None, 1)                 257       
_________________________________________________________________
activation_1 (Activation)    (None, 1)                 0         
=================================================================
Total params: 10,675,745
Trainable params: 10,675,745
Non-trainable params: 0
_________________________________________________________________

Answer 1

Usually, when OOM errors take place, it is because the batch_size is too big or your VRAM is too small.

In your case, the GPU simply runs out of memory, because your VRAM is too small. 2GB is very few video memory for a 10.000.000 parameters neural network.

For Computer Vision tasks, most of the neural networks require at least 6GB of VRAM.

The solution is definitely to use a video card with more memory.