I'm using pre-trained ResNet50 model to classify malaria dataset. I added two dense layer after it with 1024, 2048 units respectively and one classification layer using softmax function (results are worse with sigmoid). I used StratifiedKFold to validate this model but accuracy is always 0.5 after first fold.
After first fold all the epochs are the same like this:
22047/22047 [==============================] - 37s 3ms/step - loss: 8.0596 - acc: 0.5000
This is my model:
height = 100 #dimensions of image
width = 100
channel = 3 #RGB
classes = 2
batch_size = 64 #vary depending on the GPU
epochs = 10
folds = 5
optimizer = "Adam"
metrics = ["accuracy"]
loss = 'categorical_crossentropy'
random_state = 1377
chanDim = -1
model = ResNet50(include_top=False, weights="imagenet", input_shape=(height, width, channel))
# Get the ResNet50 layers up to res5c_branch2c
model = Model(input=model.input, output=model.get_layer('res5c_branch2c').output)
for layer in model.layers:
layer.trainable = False
Flatten1 = Flatten()(model.output)
F1 = Dense(1024, activation='relu')(Flatten1)
D1 = Dropout(0.5)(F1)
F2 = Dense(2048, activation='relu')(D1)
D2 = Dropout(0.2)(F2)
F3 = Dense(classes, activation='softmax')(D2)
model = Model(inputs = model.input, outputs = F3)
# Compile the model
model.compile(loss = loss, optimizer = optimizer, metrics = metrics)
This is validation part:
# Create a model compatible with sklearn
model = KerasClassifier(build_fn=customResnetBuild, epochs=epochs, batch_size=batch_size)
kfold = StratifiedKFold(n_splits=folds, shuffle=False, random_state=random_state)
# Make a custom score for classification report method to get results for mean of the all folds
def classification_report_with_accuracy_score(y_true, y_pred):
originalclass.extend(y_true)
predictedclass.extend(y_pred)
return accuracy_score(y_true, y_pred) # return accuracy score
scores = cross_val_score(model, data, labels, cv=kfold, error_score="raise", scoring=make_scorer(classification_report_with_accuracy_score) )
print(classification_report(originalclass, predictedclass))
Result
Mean of results: 0.6404469896025613
precision recall f1-score support
0 0.86 0.34 0.48 13781
1 0.59 0.94 0.72 13779
micro avg 0.64 0.64 0.64 27560
macro avg 0.72 0.64 0.60 27560
weighted avg 0.72 0.64 0.60 27560
