I've just noticed that I get different results everytime I run a Keras model. I've tried the solutions from this issue on GitHub, basically:
- Setting up the seeds before importing anything else
- Setting
shuffle=Falseonfit_generator()
Even though I did this, I still can't seem to reproduce the same results.
I've posted this same question on the issue I've just linked, but I've decided to post here as well because of the visibility, hoping anyone can help me figure out what's wrong.
import numpy as np
import tensorflow as tf
import random as rn
import os
os.environ['PYTHONHASHSEED'] = '0'
np.random.seed(42)
rn.seed(12345)
session_conf = tf.ConfigProto(intra_op_parallelism_threads=1, inter_op_parallelism_threads=1)
from keras import backend as K
tf.set_random_seed(1234)
sess = tf.Session(graph=tf.get_default_graph(), config=session_conf)
K.set_session(sess)
from keras.layers import Input, Dropout, Flatten, Conv2D, MaxPooling2D, Dense, Activation, Lambda,GlobalAveragePooling2D
from keras.optimizers import RMSprop , SGD, Adam,Nadam
from keras.callbacks import ModelCheckpoint, Callback, EarlyStopping, History
from keras.preprocessing.image import ImageDataGenerator
from keras.applications import VGG16, VGG19, ResNet50, Xception
from keras.models import Model
batch_size = 32
num_channels = 3
img_size = 512
img_full_size = (img_size, img_size, num_channels)
num_classes = 2
seed = 1 # for image transformations
train_path = 'keras_folders/train/'
validation_path = 'keras_folders/val/'
test_path = 'keras_folders/test/'
train_datagen = ImageDataGenerator(
rescale=1./255,
horizontal_flip=True)
validation_datagen = ImageDataGenerator(
rescale=1./255)
test_datagen = ImageDataGenerator(
rescale=1./255)
train_generator = train_datagen.flow_from_directory(
train_path,
target_size=(img_size, img_size),
batch_size=batch_size,
class_mode='categorical',
seed=seed)
validation_generator = validation_datagen.flow_from_directory(
validation_path,
target_size=(img_size, img_size),
batch_size=batch_size,
shuffle=False,
class_mode='categorical',
seed=seed)
from collections import Counter
counter = Counter(train_generator.classes)
max_val = float(max(counter.values()))
class_weights = {class_id : max_val/num_images for class_id, num_images in counter.items()}
conv_base = VGG16(weights='imagenet', include_top=False, input_shape=img_full_size)
conv_base.trainable=True
for layer in conv_base.layers[:4]:
layer.trainable = False
x = Flatten()(conv_base.output)
x = Dense(256, activation='relu')(x)
x = Dropout(0.218)(x)
predictions = Dense(num_classes, activation='softmax')(x)
model = Model(inputs = conv_base.input , outputs=predictions)
adam = Adam(lr=0.0001)
model.compile(loss='categorical_crossentropy', optimizer=adam, metrics=['accuracy'])
train_samples = train_generator.samples
validation_samples = validation_generator.samples
model.fit_generator(
train_generator,
class_weight=class_weights,
steps_per_epoch= train_samples // batch_size,
epochs=1,
validation_data= validation_generator,
validation_steps= validation_samples // batch_size,
shuffle=False)
