Я пытаюсь реализовать простую сеть Unet с использованием Keras на бэкэнде Tensorflow 2.0.
Я использую собственный генератор изображений без расширенных данных. Мои шаблоны и маски имеют размер 1536x1536 RGB-изображений (маски черно-белые).
import numpy as np
import os
import cv2
import random
from tensorflow.python.keras.models import Model
from tensorflow.python.keras.layers import Input, BatchNormalization, Activation, Dense, Dropout
from tensorflow.python.keras.layers.core import Lambda, RepeatVector, Reshape
from tensorflow.python.keras.layers.convolutional import Conv2D, Conv2DTranspose
from tensorflow.python.keras.layers.pooling import MaxPooling2D, GlobalMaxPool2D
from tensorflow.python.keras.layers.merge import concatenate, add
from tensorflow.python.keras.callbacks import EarlyStopping, ModelCheckpoint, ReduceLROnPlateau
from tensorflow.keras.optimizers import Adam
from tensorflow.python.keras.preprocessing.image import ImageDataGenerator, array_to_img, img_to_array, load_img
import tensorflow as tf
config = tf.compat.v1.ConfigProto()
config.gpu_options.allow_growth = True
session = tf.compat.v1.Session(config=config)
def data_gen(templates_folder, masks_folder, image_width, batch_size): # Custom image generator
counter = 0
images_list = os.listdir(templates_folder)
random.shuffle(images_list)
while True:
templates_pack = np.zeros((batch_size, image_width, image_width, 3)).astype('float')
masks_pack = np.zeros((batch_size, image_width, image_width, 1)).astype('float')
for i in range(counter, counter + batch_size):
template = cv2.imread(templates_folder + '/' + images_list[i]) / 255.
templates_pack[i - counter] = template
mask = cv2.imread(masks_folder + '/' + images_list[i], cv2.IMREAD_GRAYSCALE) / 255.
mask = mask.reshape(image_width, image_width, 1) # Add extra dimension for parity with template size [1536 * 1536 * 3]
masks_pack[i - counter] = mask
counter += batch_size
if counter + batch_size >= len(images_list):
counter = 0
random.shuffle(images_list)
yield templates_pack, masks_pack
def conv2d_block(input_tensor, n_filters, kernel_size=3, batchnorm=True):
x = Conv2D(filters=n_filters, kernel_size=(kernel_size, kernel_size), kernel_initializer="he_normal", padding="same")(input_tensor)
if batchnorm:
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = Conv2D(filters=n_filters, kernel_size=(kernel_size, kernel_size), kernel_initializer="he_normal", padding="same")(x)
if batchnorm:
x = BatchNormalization()(x)
x = Activation("relu")(x)
return x
def get_unet(input_img, n_filters=16, dropout=0.5, batchnorm=True):
c1 = conv2d_block(input_img, n_filters=n_filters * 1, kernel_size=3, batchnorm=batchnorm)
p1 = MaxPooling2D((2, 2))(c1)
p1 = Dropout(dropout * 0.5)(p1)
c2 = conv2d_block(p1, n_filters=n_filters * 2, kernel_size=3, batchnorm=batchnorm)
p2 = MaxPooling2D((2, 2))(c2)
p2 = Dropout(dropout)(p2)
c3 = conv2d_block(p2, n_filters=n_filters * 4, kernel_size=3, batchnorm=batchnorm)
p3 = MaxPooling2D((2, 2))(c3)
p3 = Dropout(dropout)(p3)
c4 = conv2d_block(p3, n_filters=n_filters * 8, kernel_size=3, batchnorm=batchnorm)
p4 = MaxPooling2D(pool_size=(2, 2))(c4)
p4 = Dropout(dropout)(p4)
c5 = conv2d_block(p4, n_filters=n_filters * 16, kernel_size=3, batchnorm=batchnorm)
u6 = Conv2DTranspose(n_filters * 8, (3, 3), strides=(2, 2), padding='same')(c5)
u6 = concatenate([u6, c4])
u6 = Dropout(dropout)(u6)
c6 = conv2d_block(u6, n_filters=n_filters * 8, kernel_size=3, batchnorm=batchnorm)
u7 = Conv2DTranspose(n_filters * 4, (3, 3), strides=(2, 2), padding='same')(c6)
u7 = concatenate([u7, c3])
u7 = Dropout(dropout)(u7)
c7 = conv2d_block(u7, n_filters=n_filters * 4, kernel_size=3, batchnorm=batchnorm)
u8 = Conv2DTranspose(n_filters * 2, (3, 3), strides=(2, 2), padding='same')(c7)
u8 = concatenate([u8, c2])
u8 = Dropout(dropout)(u8)
c8 = conv2d_block(u8, n_filters=n_filters * 2, kernel_size=3, batchnorm=batchnorm)
u9 = Conv2DTranspose(n_filters * 1, (3, 3), strides=(2, 2), padding='same')(c8)
u9 = concatenate([u9, c1], axis=3)
u9 = Dropout(dropout)(u9)
c9 = conv2d_block(u9, n_filters=n_filters * 1, kernel_size=3, batchnorm=batchnorm)
outputs = Conv2D(1, (1, 1), activation='sigmoid')(c9)
model = Model(inputs=[input_img], outputs=[outputs])
return model
callbacks = [
EarlyStopping(patience=10, verbose=1),
ReduceLROnPlateau(factor=0.1, patience=3, min_lr=0.00001, verbose=1),
ModelCheckpoint("model-prototype.h5", verbose=1, save_best_only=True,
save_weights_only=True)
]
train_templates_path = "E:/train/templates"
train_masks_path = "E:/train/masks"
valid_templates_path = "E:/valid/templates"
valid_masks_path = "E:/valid/masks"
TRAIN_SET_SIZE = len(os.listdir(train_templates_path))
VALID_SET_SIZE = len(os.listdir(valid_templates_path))
BATCH_SIZE = 1
EPOCHS = 100
STEPS_PER_EPOCH = TRAIN_SET_SIZE / BATCH_SIZE
VALIDATION_STEPS = VALID_SET_SIZE / BATCH_SIZE
IMAGE_WIDTH = 1536
train_generator = data_gen(train_templates_path, train_masks_path, IMAGE_WIDTH, batch_size = BATCH_SIZE)
val_generator = data_gen(valid_templates_path, valid_masks_path, IMAGE_WIDTH, batch_size = BATCH_SIZE)
model = get_unet(input_img, n_filters=16, dropout=0.05, batchnorm=True)
model.compile(optimizer=Adam(lr=0.001), loss="binary_crossentropy", metrics=["accuracy"])
results = model.fit_generator(train_generator, epochs=EPOCHS, steps_per_epoch=STEPS_PER_EPOCH, validation_data=val_generator, validation_steps=VALIDATION_STEPS, callbacks=callbacks)
По какой-то причине я получаю следующую ошибку:
Epoch 1/100
Traceback (most recent call last):
File "E:/Explorium/python/unet_trainer.py", line 83, in <module>
results = model.fit_generator(train_generator, epochs=EPOCHS, steps_per_epoch=STEPS_PER_EPOCH, validation_data=val_generator, validation_steps=VALIDATION_STEPS, callbacks=callbacks)
File "C:\Users\E-soft\Anaconda3\envs\Explorium\lib\site-packages\tensorflow_core\python\keras\engine\training.py", line 1297, in fit_generator
steps_name='steps_per_epoch')
File "C:\Users\E-soft\Anaconda3\envs\Explorium\lib\site-packages\tensorflow_core\python\keras\engine\training_generator.py", line 265, in model_iteration
batch_outs = batch_function(*batch_data)
File "C:\Users\E-soft\Anaconda3\envs\Explorium\lib\site-packages\tensorflow_core\python\keras\engine\training.py", line 973, in train_on_batch
class_weight=class_weight, reset_metrics=reset_metrics)
File "C:\Users\E-soft\Anaconda3\envs\Explorium\lib\site-packages\tensorflow_core\python\keras\engine\training_v2_utils.py", line 253, in train_on_batch
extract_tensors_from_dataset=True)
File "C:\Users\E-soft\Anaconda3\envs\Explorium\lib\site-packages\tensorflow_core\python\keras\engine\training.py", line 2472, in _standardize_user_data
exception_prefix='input')
File "C:\Users\E-soft\Anaconda3\envs\Explorium\lib\site-packages\tensorflow_core\python\keras\engine\training_utils.py", line 574, in standardize_input_data
str(data_shape))
ValueError: Error when checking input: expected img to have shape (1536, 1536, 1) but got array with shape (1536, 1536, 3)
Кажется, что Keras не может нормализуйте данные, используя standardize_input_data(), но я понятия не имею, почему это происходит.