I'm trying to train a VGG16 model following a video guide on YouTube.
I copied the code given by the instructor. After doing this I tried to train a model using some of the images available in my system. I have uploaded some images only to demonstrate for the reader here.
Summary:
I tried to change the dataset for the VGG16 and train for my dataset. VGG16 uses IMAGE_SIZE = [224, 224] and I don't know the size of the images that I have! Could this be the problem?
I have uploaded the some images at OneDrive, but when I change the dataset I came across multiple errors, one of which was kernel died, which came frequently. After that was solved I hade some errors related the images I provided for training and testing. I need help to train the model.
# -*- coding: utf-8 -*-
"""
@author: Krish.Naik
"""
import tensorflow as tf
from keras.models import load_model
from keras.layers import Input, Lambda, Dense, Flatten
from keras.models import Model
from keras.applications.vgg16 import VGG16
from keras.applications.vgg16 import preprocess_input
from keras.preprocessing import image
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
import numpy as np
from glob import glob
import matplotlib.pyplot as plt
# re-size all the images to this
IMAGE_SIZE = [224, 224]
train_path = 'Datasets/Train'
valid_path = 'Datasets/Test'
# add preprocessing layer to the front of VGG
vgg = VGG16(input_shape=IMAGE_SIZE + [3], weights='imagenet', include_top=False)
# don't train existing weights
for layer in vgg.layers:
layer.trainable = False
# useful for getting number of classes
folders = glob('Datasets/Train/*')
# our layers - you can add more if you want
x = Flatten()(vgg.output)
# x = Dense(1000, activation='relu')(x)
prediction = Dense(len(folders), activation='softmax')(x)
# create a model object
model = Model(inputs=vgg.input, outputs=prediction)
# view the structure of the model
model.summary()
# tell the model what cost and optimization method to use
model.compile(loss='categorical_crossentropy',optimizer='adam',metrics=['accuracy'])
from keras.preprocessing.image import ImageDataGenerator
train_datagen = ImageDataGenerator(rescale = 1./255,
shear_range = 0.2,
zoom_range = 0.2,
horizontal_flip = True)
test_datagen = ImageDataGenerator(rescale = 1./255)
training_set = train_datagen.flow_from_directory('Datasets/Train',
target_size = (224, 224),
batch_size = 32,
class_mode = 'categorical')
test_set = test_datagen.flow_from_directory('Datasets/Test',
target_size = (224, 224),
batch_size = 32,
class_mode = 'categorical')
'''r=model.fit_generator(training_set,
samples_per_epoch = 8000,
nb_epoch = 5,
validation_data = test_set,
nb_val_samples = 2000)'''
# fit the model
r = model.fit_generator(
training_set,
validation_data=test_set,
epochs=5,
steps_per_epoch=len(training_set),
validation_steps=len(test_set)
)
# loss
plt.plot(r.history['loss'], label='train loss')
plt.plot(r.history['val_loss'], label='val loss')
plt.legend()
plt.show()
plt.savefig('LossVal_loss')
# accuracies
plt.plot(r.history['accuracy'], label='train acc')
plt.plot(r.history['val_accuracy'], label='val acc')
plt.legend()
plt.show()
plt.savefig('AccVal_acc')
model.save('facefeatures_new_model.h5')
when training the model got this error
Error when checking target: expected dense_3 to have shape (2,) but got array with shape (1,)
what should i do to resolve it??
how can i change the shape of the array to match the shape ofdense_3 ??
if someone could do the changes and show how whould it be done!!! ill be greatfull.
