Improving Validation Loss and Accuracy for CNN

Question

I am new to CNNs and need some direction as I can't get any improvement in my validation results.

I am trying to do binary image classification on pictures of groups of small plastic pieces to detect defects. Unfortunately, I am unable to share pictures, but each picture is a group of round white pieces on a black background. One class includes pictures with all normal pieces, the other class includes pictures where two pieces in the picture are stuck together - and therefore defective.

I have a small data set: 250 pictures per class for training, 50 per class for validation, 30 per class for testing. The pictures are 256 x 256 pixels, although I can have a different resolution if needed.

Here is my CNN architecture:

classifier = Sequential()
classifier.add(Conv2D(32, (7, 7), padding="same", input_shape=(256, 256, 3), activation='relu'))
classifier.add(MaxPooling2D(pool_size=(2, 2)))
classifier.add(Dropout(0.5))

classifier.add(Conv2D(64, (5, 5), padding="same", input_shape=(256, 256, 3), activation='relu'))
classifier.add(MaxPooling2D(pool_size=(2, 2)))
classifier.add(Dropout(0.5))

classifier.add(Flatten())

classifier.add(Dense(units=128, activation='relu'))
classifier.add(Dense(units=1, activation='sigmoid'))

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

# Treatment done to images:
train_datagen = ImageDataGenerator(rescale=1./255,
                                   shear_range=0.2,
                                   zoom_range=0.2,
                                   horizontal_flip=True)
validation_datagen = ImageDataGenerator(rescale=1./255)

train_batch_size = 10
val_batch_size = 10
num_epochs = 100
train_images = 250
val_images = 50

classifier.fit_generator(training_set,
                             steps_per_epoch=train_images // train_batch_size
                             epochs=num_epochs,
                             validation_data=validation_set,
                             validation_steps=val_images // val_batch_size) 

Here are the results:

It's overfitting and the validation loss increases over time. The validation accuracy is not better than a coin toss, so clearly my model is not learning anything.

I have tried different values of dropout and L1/L2 for both the convolutional and FC layers, but validation accuracy is never better than a coin toss.

I understand that my data set is very small, but even getting a small increase in validation would be acceptable as long as my model seems correct, which it doesn't at this point.

Update: Switching from binary to multiclass classification helped raise the validation accuracy and reduced the validation loss, but it still grows consistenly:

Any advice would be very appreciated. Thanks in advance!

Answer 1

Your data set is very small, so you definitely should try your luck at transfer learning, if it is an option.

Other than that, you probably should have a dropout layer after the dense-128 layer. Also, it is probably a good idea to remove dropouts after pooling layers. Instead, you can try using SpatialDropout after convolutional layers.

Answer 2

I suggest you:

• Lower the size of the kernel filters. The best filter is (3, 3). I think that a (7, 7) is leaving too much information out.
• If the size of the images is too big, consider the possiblity of rescaling them before training the CNN.
• If possible, remove one Max-Pool layer.
• Lower dropout, that looks too high IMHO (but other people might disagree with me on this). I usually set it between 0.1-0.25.
• The number of output nodes should equal the number of classes.

Answer 3

As @Leevo suggested I would try kernel size (3, 3) and try to use different activation functions for Conv2D and Dense layers. E.g. relu for all Conv2D and elu for Dense.