I'm trying to use InceptionV4 for some classfication problem. Before using it on the problem I'm trying to experiment with it.
I replaced the last dense layer (sized 1001) with a new dense layer, compiled the model and tried to fit it
from keras import backend as K
import inception_v4
import numpy as np
import cv2
import os
from keras import optimizers
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Convolution2D, MaxPooling2D, ZeroPadding2D
from keras.layers import Activation, Dropout, Flatten, Dense, Input
from keras.models import Model
os.environ['CUDA_VISIBLE_DEVICES'] = ''
my_batch_size=32
train_data_dir ='//shared_directory/projects/try_CDFxx/data/train/'
validation_data_dir ='//shared_directory/projects/try_CDFxx/data/validation/'
img_width, img_height = 299, 299
num_classes=3
nb_epoch=50
nbr_train_samples = 24
nbr_validation_samples = 12
def train_top_model (num_classes):
v4 = inception_v4.create_model(weights='imagenet')
predictions = Dense(output_dim=num_classes, activation='softmax', name="newDense")(v4.layers[-2].output) # replacing the 1001 categories dense layer with my own
main_input= v4.layers[1].input
main_output=predictions
t_model = Model(input=[main_input], output=[main_output])
train_datagen = ImageDataGenerator(
rescale=1./255,
shear_range=0.1,
zoom_range=0.1,
rotation_range=10.,
width_shift_range=0.1,
height_shift_range=0.1,
horizontal_flip=True)
val_datagen = ImageDataGenerator(rescale=1./255)
train_generator = train_datagen.flow_from_directory(
train_data_dir,
target_size = (img_width, img_height),
batch_size = my_batch_size,
shuffle = True,
class_mode = 'categorical')
validation_generator = val_datagen.flow_from_directory(
validation_data_dir,
target_size=(img_width, img_height),
batch_size=my_batch_size,
shuffle = True,
class_mode = 'categorical')
#
t_model.compile(optimizer='rmsprop', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
#
t_model.fit_generator(
train_generator,
samples_per_epoch = nbr_train_samples,
nb_epoch = nb_epoch,
validation_data = validation_generator,
nb_val_samples = nbr_validation_samples)
train_top_model(num_classes)
But I am getting the following error
Traceback (most recent call last):
File "re_try.py", line 76, in <module>
train_top_model(num_classes)
File "re_try.py", line 72, in train_top_model
nb_val_samples = nbr_validation_samples)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 1508, in fit_generator
class_weight=class_weight)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 1261, in train_on_batch
check_batch_dim=True)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 985, in _standardize_user_data
exception_prefix='model target')
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 113, in standardize_input_data
str(array.shape))
ValueError: Error when checking model target: expected newDense to have shape (None, 1) but got array with shape (24, 3)
Exception in thread Thread-1:
Traceback (most recent call last):
File "/usr/lib/python2.7/threading.py", line 801, in __bootstrap_inner
self.run()
File "/usr/lib/python2.7/threading.py", line 754, in run
self.__target(*self.__args, **self.__kwargs)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 409, in data_generator_task
generator_output = next(generator)
File "/usr/local/lib/python2.7/dist-packages/keras/preprocessing/image.py", line 693, in next
x = self.image_data_generator.random_transform(x)
File "/usr/local/lib/python2.7/dist-packages/keras/preprocessing/image.py", line 403, in random_transform
fill_mode=self.fill_mode, cval=self.cval)
File "/usr/local/lib/python2.7/dist-packages/keras/preprocessing/image.py", line 109, in apply_transform
final_offset, order=0, mode=fill_mode, cval=cval) for x_channel in x]
AttributeError: 'NoneType' object has no attribute 'interpolation'
What am I doing wrong?
And why is the newDense layer expected to have a (None,1) shape after I defined it as having the size of 3?
Many thanks
PS I am adding the end of summary of the model
merge_25 (Merge) (None, 8, 8, 1536) 0 activation_140[0][0]
merge_23[0][0]
merge_24[0][0]
activation_149[0][0]
____________________________________________________________________________________________________
averagepooling2d_15 (AveragePool (None, 1, 1, 1536) 0 merge_25[0][0]
____________________________________________________________________________________________________
dropout_1 (Dropout) (None, 1, 1, 1536) 0 averagepooling2d_15[0][0]
____________________________________________________________________________________________________
flatten_1 (Flatten) (None, 1536) 0 dropout_1[0][0]
____________________________________________________________________________________________________
newDense (Dense) (None, 3) 4611 flatten_1[0][0]
====================================================================================================
Total params: 41,210,595
Trainable params: 41,147,427
Non-trainable params: 63,168
Ok, problem lied in
validation_generator = val_datagen.flow_from_directory(...
class_mode = 'categorical')
Categorical makes your generator to return a one-hot encoded vector. In your case a 3-d one. But you set your loss to sparse_categorical_crossentropy which accepts int as a label. You should either change class_mode="sparse" or loss="categorical_crossentropy".