5.3 使用tensorflow搭建GoogLeNet網路 筆記
model
from tensorflow.keras import layers, models, Model, Sequential
def GoogLeNet(im_height=224, im_width=224, class_num=1000, aux_logits=False):
# tensorflow中的tensor通道排序是NHWC
input_image = layers.Input(shape=(im_height, im_width, 3), dtype="float32")
# (None, 224, 224, 3)
x = layers.Conv2D(64, kernel_size=7, strides=2, padding="SAME", activation="relu", name="conv2d_1")(input_image)
# (None, 112, 112, 64)
x = layers.MaxPool2D(pool_size=3, strides=2, padding="SAME", name="maxpool_1")(x)
# (None, 56, 56, 64)
x = layers.Conv2D(64, kernel_size=1, activation="relu", name="conv2d_2")(x)
# (None, 56, 56, 64)
x = layers.Conv2D(192, kernel_size=3, padding="SAME", activation="relu", name="conv2d_3")(x)
# (None, 56, 56, 192)
x = layers.MaxPool2D(pool_size=3, strides=2, padding="SAME", name="maxpool_2")(x)#池化核大小為3，步距為2
# (None, 28, 28, 192)
x = Inception(64, 96, 128, 16, 32, 32, name="inception_3a")(x)
# (None, 28, 28, 256)
x = Inception(128, 128, 192, 32, 96, 64, name="inception_3b")(x)
# (None, 28, 28, 480)
x = layers.MaxPool2D(pool_size=3, strides=2, padding="SAME", name="maxpool_3")(x)
# (None, 14, 14, 480)
x = Inception(192, 96, 208, 16, 48, 64, name="inception_4a")(x)
if aux_logits:
aux1 = InceptionAux(class_num, name="aux_1")(x)
# (None, 14, 14, 512)
x = Inception(160, 112, 224, 24, 64, 64, name="inception_4b")(x)
# (None, 14, 14, 512)
x = Inception(128, 128, 256, 24, 64, 64, name="inception_4c")(x)
# (None, 14, 14, 512)
x = Inception(112, 144, 288, 32, 64, 64, name="inception_4d")(x)
if aux_logits:
aux2 = InceptionAux(class_num, name="aux_2")(x)
# (None, 14, 14, 528)
x = Inception(256, 160, 320, 32, 128, 128, name="inception_4e")(x)
# (None, 14, 14, 532)
x = layers.MaxPool2D(pool_size=3, strides=2, padding="SAME", name="maxpool_4")(x)
# (None, 7, 7, 832)
x = Inception(256, 160, 320, 32, 128, 128, name="inception_5a")(x)
# (None, 7, 7, 832)
x = Inception(384, 192, 384, 48, 128, 128, name="inception_5b")(x)
# (None, 7, 7, 1024)
x = layers.AvgPool2D(pool_size=7, strides=1, name="avgpool_1")(x)
# (None, 1, 1, 1024)
x = layers.Flatten(name="output_flatten")(x)
# (None, 1024)
x = layers.Dropout(rate=0.4, name="output_dropout")(x)
x = layers.Dense(class_num, name="output_dense")(x)
# (None, class_num)
aux3 = layers.Softmax(name="aux_3")(x)
if aux_logits:
model = models.Model(inputs=input_image, outputs=[aux1, aux2, aux3])#無法遮蔽，要用就得帶，不用就不能弄
else:
model = models.Model(inputs=input_image, outputs=aux3)
return model
class Inception(layers.Layer):
def __init__(self, ch1x1, ch3x3red, ch3x3, ch5x5red, ch5x5, pool_proj, **kwargs):#最後一個是可變長度字典變數，傳層名稱
super(Inception, self).__init__(**kwargs)
#定義四個分支
self.branch1 = layers.Conv2D(ch1x1, kernel_size=1, activation="relu")#relu啟用
self.branch2 = Sequential([
layers.Conv2D(ch3x3red, kernel_size=1, activation="relu"),
layers.Conv2D(ch3x3, kernel_size=3, padding="SAME", activation="relu")]) # output_size= input_size
self.branch3 = Sequential([
layers.Conv2D(ch5x5red, kernel_size=1, activation="relu"),
layers.Conv2D(ch5x5, kernel_size=5, padding="SAME", activation="relu")]) # output_size= input_size
self.branch4 = Sequential([
layers.MaxPool2D(pool_size=3, strides=1, padding="SAME"), # caution: default strides==pool_size
layers.Conv2D(pool_proj, kernel_size=1, activation="relu")]) # output_size= input_size
def call(self, inputs, **kwargs):
branch1 = self.branch1(inputs)
branch2 = self.branch2(inputs)
branch3 = self.branch3(inputs)
branch4 = self.branch4(inputs)
outputs = layers.concatenate([branch1, branch2, branch3, branch4])
return outputs
class InceptionAux(layers.Layer):
def __init__(self, num_classes, **kwargs):
super(InceptionAux, self).__init__(**kwargs)
self.averagePool = layers.AvgPool2D(pool_size=5, strides=3)
self.conv = layers.Conv2D(128, kernel_size=1, activation="relu")
self.fc1 = layers.Dense(1024, activation="relu")
self.fc2 = layers.Dense(num_classes)
self.softmax = layers.Softmax()
def call(self, inputs, **kwargs):
# aux1: N x 512 x 14 x 14, aux2: N x 528 x 14 x 14
x = self.averagePool(inputs)
# aux1: N x 512 x 4 x 4, aux2: N x 528 x 4 x 4
x = self.conv(x)
# N x 128 x 4 x 4
x = layers.Flatten()(x)
x = layers.Dropout(rate=0.5)(x)
# N x 2048
x = self.fc1(x)
x = layers.Dropout(rate=0.5)(x)#原論文70%隨即失活，但發現50%更好
# N x 1024
x = self.fc2(x)
# N x num_classes
x = self.softmax(x)
return x
model_add_bn
from tensorflow.keras import layers, models, Model, Sequential
def InceptionV1(im_height=224, im_width=224, class_num=1000, aux_logits=False):
# tensorflow中的tensor通道排序是NHWC
input_image = layers.Input(shape=(im_height, im_width, 3), dtype="float32")
# (None, 224, 224, 3)
x = layers.Conv2D(64, kernel_size=7, strides=2, padding="SAME", use_bias=False, name="conv1/conv")(input_image)
x = layers.BatchNormalization(momentum=0.9, epsilon=1e-5, name="conv1/bn")(x)
x = layers.ReLU()(x)
# (None, 112, 112, 64)
x = layers.MaxPool2D(pool_size=3, strides=2, padding="SAME", name="maxpool_1")(x)
# (None, 56, 56, 64)
x = layers.Conv2D(64, kernel_size=1, use_bias=False, name="conv2/conv")(x)
x = layers.BatchNormalization(momentum=0.9, epsilon=1e-5, name="conv2/bn")(x)
x = layers.ReLU()(x)
# (None, 56, 56, 64)
x = layers.Conv2D(192, kernel_size=3, padding="SAME", use_bias=False, name="conv3/conv")(x)
x = layers.BatchNormalization(momentum=0.9, epsilon=1e-5, name="conv3/bn")(x)
x = layers.ReLU()(x)
# (None, 56, 56, 192)
x = layers.MaxPool2D(pool_size=3, strides=2, padding="SAME", name="maxpool_2")(x)
# (None, 28, 28, 192)
x = Inception(64, 96, 128, 16, 32, 32, name="inception3a")(x)
# (None, 28, 28, 256)
x = Inception(128, 128, 192, 32, 96, 64, name="inception3b")(x)
# (None, 28, 28, 480)
x = layers.MaxPool2D(pool_size=3, strides=2, padding="SAME", name="maxpool_3")(x)
# (None, 14, 14, 480)
x = Inception(192, 96, 208, 16, 48, 64, name="inception4a")(x)
if aux_logits:
aux1 = InceptionAux(class_num, name="aux1")(x)
# (None, 14, 14, 512)
x = Inception(160, 112, 224, 24, 64, 64, name="inception4b")(x)
# (None, 14, 14, 512)
x = Inception(128, 128, 256, 24, 64, 64, name="inception4c")(x)
# (None, 14, 14, 512)
x = Inception(112, 144, 288, 32, 64, 64, name="inception4d")(x)
if aux_logits:
aux2 = InceptionAux(class_num, name="aux2")(x)
# (None, 14, 14, 528)
x = Inception(256, 160, 320, 32, 128, 128, name="inception4e")(x)
# (None, 14, 14, 532)
x = layers.MaxPool2D(pool_size=2, strides=2, padding="SAME", name="maxpool_4")(x)
# (None, 7, 7, 832)
x = Inception(256, 160, 320, 32, 128, 128, name="inception5a")(x)
# (None, 7, 7, 832)
x = Inception(384, 192, 384, 48, 128, 128, name="inception5b")(x)
# (None, 7, 7, 1024)
x = layers.AvgPool2D(pool_size=7, strides=1, name="avgpool_1")(x)
# (None, 1, 1, 1024)
x = layers.Flatten(name="output_flatten")(x)
# (None, 1024)
x = layers.Dropout(rate=0.4, name="output_dropout")(x)
x = layers.Dense(class_num, name="fc")(x)
# (None, class_num)
aux3 = layers.Softmax()(x)
if aux_logits:
model = models.Model(inputs=input_image, outputs=[aux1, aux2, aux3])
else:
model = models.Model(inputs=input_image, outputs=aux3)
return model
class Inception(layers.Layer):
def __init__(self, ch1x1, ch3x3red, ch3x3, ch5x5red, ch5x5, pool_proj, **kwargs):
super(Inception, self).__init__(**kwargs)
self.branch1 = Sequential([
layers.Conv2D(ch1x1, kernel_size=1, use_bias=False, name="conv"),
layers.BatchNormalization(momentum=0.9, epsilon=1e-5, name="bn"),
layers.ReLU()], name="branch1")
self.branch2 = Sequential([
layers.Conv2D(ch3x3red, kernel_size=1, use_bias=False, name="0/conv"),
layers.BatchNormalization(momentum=0.9, epsilon=1e-5, name="0/bn"),
layers.ReLU(),
layers.Conv2D(ch3x3, kernel_size=3, padding="SAME", use_bias=False, name="1/conv"),
layers.BatchNormalization(momentum=0.9, epsilon=1e-5, name="1/bn"),
layers.ReLU()], name="branch2") # output_size= input_size
self.branch3 = Sequential([
layers.Conv2D(ch5x5red, kernel_size=1, use_bias=False, name="0/conv"),
layers.BatchNormalization(momentum=0.9, epsilon=1e-5, name="0/bn"),
layers.ReLU(),
layers.Conv2D(ch5x5, kernel_size=3, padding="SAME", use_bias=False, name="1/conv"),
layers.BatchNormalization(momentum=0.9, epsilon=1e-5, name="1/bn"),
layers.ReLU()], name="branch3") # output_size= input_size
self.branch4 = Sequential([
layers.MaxPool2D(pool_size=3, strides=1, padding="SAME"), # caution: default strides==pool_size
layers.Conv2D(pool_proj, kernel_size=1, use_bias=False, name="1/conv"),
layers.BatchNormalization(momentum=0.9, epsilon=1e-5, name="1/bn"),
layers.ReLU()], name="branch4") # output_size= input_size
def call(self, inputs, **kwargs):
branch1 = self.branch1(inputs)
branch2 = self.branch2(inputs)
branch3 = self.branch3(inputs)
branch4 = self.branch4(inputs)
outputs = layers.concatenate([branch1, branch2, branch3, branch4])
return outputs
class InceptionAux(layers.Layer):
def __init__(self, num_classes, **kwargs):
super(InceptionAux, self).__init__(**kwargs)
self.averagePool = layers.AvgPool2D(pool_size=5, strides=3)
self.conv = layers.Conv2D(128, kernel_size=1, use_bias=False, name="conv/conv")
self.bn1 = layers.BatchNormalization(momentum=0.9, epsilon=1e-5, name="conv/bn")
self.rule1 = layers.ReLU()
self.fc1 = layers.Dense(1024, activation="relu", name="fc1")
self.fc2 = layers.Dense(num_classes, name="fc2")
self.softmax = layers.Softmax()
def call(self, inputs, **kwargs):
# aux1: N x 512 x 14 x 14, aux2: N x 528 x 14 x 14
x = self.averagePool(inputs)
# aux1: N x 512 x 4 x 4, aux2: N x 528 x 4 x 4
x = self.conv(x)
x = self.bn1(x)
x = self.rule1(x)
# N x 128 x 4 x 4
x = layers.Flatten()(x)
x = layers.Dropout(rate=0.5)(x)
# N x 2048
x = self.fc1(x)
x = layers.Dropout(rate=0.5)(x)
# N x 1024
x = self.fc2(x)
# N x num_classes
x = self.softmax(x)
return x
train
from tensorflow.keras.preprocessing.image import ImageDataGenerator
import matplotlib.pyplot as plt
from model import GoogLeNet
import tensorflow as tf
import json
import os
data_root = os.path.abspath(os.path.join(os.getcwd(), "../..")) # get data root path
image_path = data_root + "/data_set/flower_data/" # flower data set path
train_dir = image_path + "train"
validation_dir = image_path + "val"
# create direction for saving weights
if not os.path.exists("save_weights"):
os.makedirs("save_weights")
im_height = 224
im_width = 224
batch_size = 32
epochs = 30
def pre_function(img):
# img = im.open('test.jpg')
# img = np.array(img).astype(np.float32)
img = img / 255.
img = (img - 0.5) * 2.0#做了一個縮放,截圖中的寫法一樣
return img
# data generator with data augmentation
train_image_generator = ImageDataGenerator(preprocessing_function=pre_function,
horizontal_flip=True)
validation_image_generator = ImageDataGenerator(preprocessing_function=pre_function)
train_data_gen = train_image_generator.flow_from_directory(directory=train_dir,
batch_size=batch_size,
shuffle=True,
target_size=(im_height, im_width),
class_mode='categorical')
total_train = train_data_gen.n
# get class dict
class_indices = train_data_gen.class_indices
# transform value and key of dict
inverse_dict = dict((val, key) for key, val in class_indices.items())
# write dict into json file
json_str = json.dumps(inverse_dict, indent=4)
with open('class_indices.json', 'w') as json_file:
json_file.write(json_str)
val_data_gen = train_image_generator.flow_from_directory(directory=validation_dir,
batch_size=batch_size,
shuffle=True,
target_size=(im_height, im_width),
class_mode='categorical')
total_val = val_data_gen.n
model = GoogLeNet(im_height=im_height, im_width=im_width, class_num=5, aux_logits=True)
# model.build((batch_size, 224, 224, 3)) # when using subclass model
model.summary()#列印每一層
# using keras low level api for training 一個比較底層的方法（因為有兩個輔助分類器，引數不匹配）
loss_object = tf.keras.losses.CategoricalCrossentropy(from_logits=False)
optimizer = tf.keras.optimizers.Adam(learning_rate=0.0003)
train_loss = tf.keras.metrics.Mean(name='train_loss')
train_accuracy = tf.keras.metrics.CategoricalAccuracy(name='train_accuracy')
test_loss = tf.keras.metrics.Mean(name='test_loss')
test_accuracy = tf.keras.metrics.CategoricalAccuracy(name='test_accuracy')
@tf.function
def train_step(images, labels):
with tf.GradientTape() as tape:
aux1, aux2, output = model(images, training=True)
loss1 = loss_object(labels, aux1)
loss2 = loss_object(labels, aux2)
loss3 = loss_object(labels, output)
loss = loss1*0.3 + loss2*0.3 + loss3
gradients = tape.gradient(loss, model.trainable_variables)
optimizer.apply_gradients(zip(gradients, model.trainable_variables))
train_loss(loss)
train_accuracy(labels, output)
@tf.function
def test_step(images, labels):
_, _, output = model(images, training=False)#有兩個值不要
t_loss = loss_object(labels, output)
test_loss(t_loss)
test_accuracy(labels, output)
best_test_loss = float('inf')
for epoch in range(1, epochs+1):
train_loss.reset_states() # clear history info
train_accuracy.reset_states() # clear history info
test_loss.reset_states() # clear history info
test_accuracy.reset_states() # clear history info
for step in range(total_train // batch_size):
images, labels = next(train_data_gen)
train_step(images, labels)
for step in range(total_val // batch_size):
test_images, test_labels = next(val_data_gen)
test_step(test_images, test_labels)
template = 'Epoch {}, Loss: {}, Accuracy: {}, Test Loss: {}, Test Accuracy: {}'
print(template.format(epoch,
train_loss.result(),
train_accuracy.result() * 100,
test_loss.result(),
test_accuracy.result() * 100))
if test_loss.result() < best_test_loss:
best_test_loss = test_loss.result()
model.save_weights("./save_weights/myGoogLeNet.h5")
train_add_bn
from tensorflow.keras.preprocessing.image import ImageDataGenerator
import matplotlib.pyplot as plt
from model_add_bn import InceptionV1
import tensorflow as tf
import json
import os
import numpy as np
data_root = os.path.abspath(os.path.join(os.getcwd(), "../..")) # get data root path
image_path = data_root + "/data_set/flower_data/" # flower data set path
train_dir = image_path + "train"
validation_dir = image_path + "val"
# create direction for saving weights
if not os.path.exists("save_weights"):
os.makedirs("save_weights")
im_height = 224
im_width = 224
batch_size = 16
epochs = 30
def pre_function(img: np.ndarray):
# img = im.open('test.jpg')
# img = np.array(img).astype(np.float32)
img = img / 255.
img = img - [0.485, 0.456, 0.406]
img = img / [0.229, 0.224, 0.225]
return img
# data generator with data augmentation
train_image_generator = ImageDataGenerator(preprocessing_function=pre_function,
horizontal_flip=True)
validation_image_generator = ImageDataGenerator(preprocessing_function=pre_function)
train_data_gen = train_image_generator.flow_from_directory(directory=train_dir,
batch_size=batch_size,
shuffle=True,
target_size=(im_height, im_width),
class_mode='categorical')
total_train = train_data_gen.n
# get class dict
class_indices = train_data_gen.class_indices
# transform value and key of dict
inverse_dict = dict((val, key) for key, val in class_indices.items())
# write dict into json file
json_str = json.dumps(inverse_dict, indent=4)
with open('class_indices.json', 'w') as json_file:
json_file.write(json_str)
val_data_gen = train_image_generator.flow_from_directory(directory=validation_dir,
batch_size=batch_size,
shuffle=True,
target_size=(im_height, im_width),
class_mode='categorical')
total_val = val_data_gen.n
model = InceptionV1(im_height=im_height, im_width=im_width, class_num=5, aux_logits=True)
# model.build((batch_size, 224, 224, 3)) # when using subclass model
model.load_weights("pretrain_weights.ckpt")
model.summary()
# using keras low level api for training
loss_object = tf.keras.losses.CategoricalCrossentropy(from_logits=False)
optimizer = tf.keras.optimizers.Adam(learning_rate=0.0005)
train_loss = tf.keras.metrics.Mean(name='train_loss')
train_accuracy = tf.keras.metrics.CategoricalAccuracy(name='train_accuracy')
test_loss = tf.keras.metrics.Mean(name='test_loss')
test_accuracy = tf.keras.metrics.CategoricalAccuracy(name='test_accuracy')
@tf.function
def train_step(images, labels):
with tf.GradientTape() as tape:
aux1, aux2, output = model(images, training=True)
loss1 = loss_object(labels, aux1)
loss2 = loss_object(labels, aux2)
loss3 = loss_object(labels, output)
loss = loss1*0.3 + loss2*0.3 + loss3
gradients = tape.gradient(loss, model.trainable_variables)
optimizer.apply_gradients(zip(gradients, model.trainable_variables))
train_loss(loss)
train_accuracy(labels, output)
@tf.function
def test_step(images, labels):
_, _, output = model(images, training=False)
t_loss = loss_object(labels, output)
test_loss(t_loss)
test_accuracy(labels, output)
best_test_loss = float('inf')
for epoch in range(1, epochs+1):
train_loss.reset_states() # clear history info
train_accuracy.reset_states() # clear history info
test_loss.reset_states() # clear history info
test_accuracy.reset_states() # clear history info
for step in range(total_train // batch_size):
images, labels = next(train_data_gen)
train_step(images, labels)
for step in range(total_val // batch_size):
test_images, test_labels = next(val_data_gen)
test_step(test_images, test_labels)
template = 'Epoch {}, Loss: {}, Accuracy: {}, Test Loss: {}, Test Accuracy: {}'
print(template.format(epoch,
train_loss.result(),
train_accuracy.result() * 100,
test_loss.result(),
test_accuracy.result() * 100))
if test_loss.result() < best_test_loss:
best_test_loss = test_loss.result()
model.save_weights("./save_weights/myInceptionV1.h5")
trainGPU
import matplotlib.pyplot as plt
from model import GoogLeNet
import tensorflow as tf
import json
import os
import time
import glob
import random
os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
gpus = tf.config.experimental.list_physical_devices("GPU")
if gpus:
try:
for gpu in gpus:
tf.config.experimental.set_memory_growth(gpu, True)
except RuntimeError as e:
print(e)
exit(-1)
data_root = os.path.abspath(os.path.join(os.getcwd(), "../..")) # get data root path
image_path = data_root + "/data_set/flower_data/" # flower data set path
train_dir = image_path + "train"
validation_dir = image_path + "val"
# create direction for saving weights
if not os.path.exists("save_weights"):
os.makedirs("save_weights")
im_height = 224
im_width = 224
batch_size = 32
epochs = 30
# class dict
data_class = [cla for cla in os.listdir(train_dir) if ".txt" not in cla]
class_num = len(data_class)
class_dict = dict((value, index) for index, value in enumerate(data_class))
# reverse value and key of dict
inverse_dict = dict((val, key) for key, val in class_dict.items())
# write dict into json file
json_str = json.dumps(inverse_dict, indent=4)
with open('class_indices.json', 'w') as json_file:
json_file.write(json_str)
# load train images list
train_image_list = glob.glob(train_dir+"/*/*.jpg")
random.shuffle(train_image_list)
train_num = len(train_image_list)
train_label_list = [class_dict[path.split(os.path.sep)[-2]] for path in train_image_list]
# load validation images list
val_image_list = glob.glob(validation_dir+"/*/*.jpg")
random.shuffle(val_image_list)
val_num = len(val_image_list)
val_label_list = [class_dict[path.split(os.path.sep)[-2]] for path in val_image_list]
def process_train_img(img_path, label):
label = tf.one_hot(label, depth=class_num)
image = tf.io.read_file(img_path)
image = tf.image.decode_jpeg(image)
image = tf.image.convert_image_dtype(image, tf.float32)
image = tf.image.resize(image, [im_height, im_width])
image = tf.image.random_flip_left_right(image)
image = (image - 0.5) / 0.5
return image, label
def process_val_img(img_path, label):
label = tf.one_hot(label, depth=class_num)
image = tf.io.read_file(img_path)
image = tf.image.decode_jpeg(image)
image = tf.image.convert_image_dtype(image, tf.float32)
image = tf.image.resize(image, [im_height, im_width])
image = (image - 0.5) / 0.5
return image, label
AUTOTUNE = tf.data.experimental.AUTOTUNE
# load train dataset
train_dataset = tf.data.Dataset.from_tensor_slices((train_image_list, train_label_list))#用tfdata讀取，真正多執行緒讀取，加速訓練
train_dataset = train_dataset.shuffle(buffer_size=train_num)\
.map(process_train_img, num_parallel_calls=AUTOTUNE)\
.repeat().batch(batch_size).prefetch(AUTOTUNE)
# load train dataset
val_dataset = tf.data.Dataset.from_tensor_slices((val_image_list, val_label_list))
val_dataset = val_dataset.map(process_val_img, num_parallel_calls=tf.data.experimental.AUTOTUNE)\
.repeat().batch(batch_size)
# 例項化模型
model = GoogLeNet(im_height=224, im_width=224, class_num=5, aux_logits=True)
model.summary()
# using keras low level api for training
loss_object = tf.keras.losses.CategoricalCrossentropy(from_logits=False)
optimizer = tf.keras.optimizers.Adam(learning_rate=0.0003)
train_loss = tf.keras.metrics.Mean(name='train_loss')
train_accuracy = tf.keras.metrics.CategoricalAccuracy(name='train_accuracy')
test_loss = tf.keras.metrics.Mean(name='test_loss')
test_accuracy = tf.keras.metrics.CategoricalAccuracy(name='test_accuracy')
@tf.function
def train_step(images, labels):
with tf.GradientTape() as tape:
aux1, aux2, output = model(images, training=True)
loss1 = loss_object(labels, aux1)
loss2 = loss_object(labels, aux2)
loss3 = loss_object(labels, output)
loss = loss1 * 0.3 + loss2 * 0.3 + loss3
gradients = tape.gradient(loss, model.trainable_variables)
optimizer.apply_gradients(zip(gradients, model.trainable_variables))
train_loss(loss)
train_accuracy(labels, output)
@tf.function
def test_step(images, labels):
_, _, output = model(images, training=False)
t_loss = loss_object(labels, output)
test_loss(t_loss)
test_accuracy(labels, output)
best_test_loss = float('inf')
train_step_num = train_num // batch_size
val_step_num = val_num // batch_size
for epoch in range(1, epochs+1):
train_loss.reset_states() # clear history info
train_accuracy.reset_states() # clear history info
test_loss.reset_states() # clear history info
test_accuracy.reset_states() # clear history info
t1 = time.perf_counter()
for index, (images, labels) in enumerate(train_dataset):
train_step(images, labels)
if index+1 == train_step_num:
break
print(time.perf_counter()-t1)
for index, (images, labels) in enumerate(val_dataset):
test_step(images, labels)
if index+1 == val_step_num:
break
template = 'Epoch {}, Loss: {}, Accuracy: {}, Test Loss: {}, Test Accuracy: {}'
print(template.format(epoch,
train_loss.result(),
train_accuracy.result() * 100,
test_loss.result(),
test_accuracy.result() * 100))
if test_loss.result() < best_test_loss:
model.save_weights("./save_weights/myGoogLeNet.ckpt".format(epoch), save_format='tf')#ckpt官方模式
predict
from model import GoogLeNet
from PIL import Image
import numpy as np
import json
import matplotlib.pyplot as plt
im_height = 224
im_width = 224
# load image
img = Image.open("../tulip.jpg")
# resize image to 224x224
img = img.resize((im_width, im_height))
plt.imshow(img)
# scaling pixel value and normalize
img = ((np.array(img) / 255.) - 0.5) / 0.5
# Add the image to a batch where it's the only member.
img = (np.expand_dims(img, 0))
# read class_indict
try:
json_file = open('./class_indices.json', 'r')
class_indict = json.load(json_file)
except Exception as e:
print(e)
exit(-1)
model = GoogLeNet(class_num=5, aux_logits=False)
model.summary()
# model.load_weights("./save_weights/myGoogLenet.h5", by_name=True) # h5 format，因為沒有輔助分類器，by_name這樣就按照相應的載入，不然報錯
model.load_weights("./save_weights/myGoogLeNet.ckpt") # ckpt format官方，ckpt就不用了，寫by_name反倒報錯
result = model.predict(img)
predict_class = np.argmax(result)
print(class_indict[str(predict_class)])
plt.show()
相關文章
- 深度學習筆記8：利用Tensorflow搭建神經網路深度學習筆記神經網路
- GoogleNet閱讀筆記Go筆記
- TensorFlow筆記-05-反向傳播,搭建神經網路的八股筆記反向傳播神經網路
- 【機器學習】搭建神經網路筆記機器學習神經網路筆記
- Lua5.3學習筆記筆記
- TensorFlow搭建神經網路最佳實踐樣例神經網路
- 5.3_前端筆記-js變數前端筆記JS變數
- ibm aix 5.3學習筆記IBMAI筆記
- Tensorflow Error筆記1Error筆記
- TensorFlow 學習筆記筆記
- TensorFlow筆記-07-神經網路優化-學習率,滑動平均筆記神經網路優化
- TensorFlow筆記-02-Windows下搭建TensorFlow環境（win版非虛擬機器）筆記Windows虛擬機
- 網路層筆記（1）筆記
- 【筆記】Android 網路筆記Android
- 5.3 閃電網路的設計
- TensorFlow筆記-04-神經網路的實現過程,前向傳播筆記神經網路
- 以太坊學習筆記————12、搭建測試網路和私有鏈筆記
- 使用Leanote搭建私有云筆記筆記
- 使用Vmware搭建虛擬網路
- TensorFlow學習筆記（二）筆記
- tensorflow學習筆記3筆記
- Tensorflow學習筆記一筆記
- Tensorflow學習筆記二筆記
- Elasticsearch 5.3 叢集搭建Elasticsearch
- tensorflow學習筆記1（程式碼轉自官網）筆記
- 前端面試筆記 – 網路前端面試筆記
- 網路流練習筆記筆記
- 【學習筆記】網路流筆記
- [網路]NIO學習筆記筆記
- 【筆記/模板】網路流初步筆記
- 網路流學習筆記筆記
- TensorFlow學習筆記（8）：基於MNIST資料的迴圈神經網路RNN筆記神經網路RNN
- 騰訊雲使用筆記一: 環境搭建筆記
- substrate學習筆記5：使用substrate構建私有網路筆記
- TensorFlow Java API 學習筆記JavaAPI筆記
- tensorflow學習筆記——DenseNet筆記SENet
- Tensorflow學習筆記No.10筆記
- Tensorflow學習筆記No.11筆記