model
from typing import Union
from functools import partial
from tensorflow.keras import layers, Model
def _make_divisible(ch, divisor=8, min_ch=None):
"""
This function is taken from the original tf repo.
It ensures that all layers have a channel number that is divisible by 8
It can be seen here:
https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet.py
"""
if min_ch is None:
min_ch = divisor
new_ch = max(min_ch, int(ch + divisor / 2) // divisor * divisor)
# Make sure that round down does not go down by more than 10%.
if new_ch < 0.9 * ch:
new_ch += divisor
return new_ch
def correct_pad(input_size: Union[int, tuple], kernel_size: int):
"""Returns a tuple for zero-padding for 2D convolution with downsampling.
Arguments:
input_size: Input tensor size.
kernel_size: An integer or tuple/list of 2 integers.
Returns:
A tuple.
"""
if isinstance(input_size, int):
input_size = (input_size, input_size)
kernel_size = (kernel_size, kernel_size)
adjust = (1 - input_size[0] % 2, 1 - input_size[1] % 2)
correct = (kernel_size[0] // 2, kernel_size[1] // 2)
return ((correct[0] - adjust[0], correct[0]),
(correct[1] - adjust[1], correct[1]))
class HardSigmoid(layers.Layer):
def __init__(self, **kwargs):
super(HardSigmoid, self).__init__(**kwargs)
self.relu6 = layers.ReLU(6.)
def call(self, inputs, **kwargs):
x = self.relu6(inputs + 3) * (1. / 6)
return x
class HardSwish(layers.Layer):
def __init__(self, **kwargs):
super(HardSwish, self).__init__(**kwargs)
self.hard_sigmoid = HardSigmoid()
def call(self, inputs, **kwargs):
x = self.hard_sigmoid(inputs) * inputs
return x
def _se_block(inputs, filters, prefix, se_ratio=1 / 4.):
# [batch, height, width, channel] -> [batch, channel]
x = layers.GlobalAveragePooling2D(name=prefix + 'squeeze_excite/AvgPool')(inputs)
# Target shape. Tuple of integers, does not include the samples dimension (batch size).
# [batch, channel] -> [batch, 1, 1, channel]
x = layers.Reshape((1, 1, filters))(x)
# fc1
x = layers.Conv2D(filters=_make_divisible(filters * se_ratio),
kernel_size=1,
padding='same',
name=prefix + 'squeeze_excite/Conv')(x)
x = layers.ReLU(name=prefix + 'squeeze_excite/Relu')(x)
# fc2
x = layers.Conv2D(filters=filters,
kernel_size=1,
padding='same',
name=prefix + 'squeeze_excite/Conv_1')(x)
x = HardSigmoid(name=prefix + 'squeeze_excite/HardSigmoid')(x)
x = layers.Multiply(name=prefix + 'squeeze_excite/Mul')([inputs, x])
return x
def _inverted_res_block(x,
input_c: int, # input channel
kernel_size: int, # kennel size
exp_c: int, # expanded channel
out_c: int, # out channel
use_se: bool, # whether using SE
activation: str, # RE or HS
stride: int,
block_id: int,
alpha: float = 1.0):
bn = partial(layers.BatchNormalization, epsilon=0.001, momentum=0.99)
input_c = _make_divisible(input_c * alpha)
exp_c = _make_divisible(exp_c * alpha)
out_c = _make_divisible(out_c * alpha)
act = layers.ReLU if activation == "RE" else HardSwish
shortcut = x
prefix = 'expanded_conv/'
if block_id:
# expand channel
prefix = 'expanded_conv_{}/'.format(block_id)
x = layers.Conv2D(filters=exp_c,
kernel_size=1,
padding='same',
use_bias=False,
name=prefix + 'expand')(x)
x = bn(name=prefix + 'expand/BatchNorm')(x)
x = act(name=prefix + 'expand/' + act.__name__)(x)
if stride == 2:
input_size = (x.shape[1], x.shape[2]) # height, width
x = layers.ZeroPadding2D(padding=correct_pad(input_size, kernel_size),
name=prefix + 'depthwise/pad')(x)
x = layers.DepthwiseConv2D(kernel_size=kernel_size,
strides=stride,
padding='same' if stride == 1 else 'valid',
use_bias=False,
name=prefix + 'depthwise')(x)
x = bn(name=prefix + 'depthwise/BatchNorm')(x)
x = act(name=prefix + 'depthwise/' + act.__name__)(x)
if use_se:
x = _se_block(x, filters=exp_c, prefix=prefix)
x = layers.Conv2D(filters=out_c,
kernel_size=1,
padding='same',
use_bias=False,
name=prefix + 'project')(x)
x = bn(name=prefix + 'project/BatchNorm')(x)
if stride == 1 and input_c == out_c:
x = layers.Add(name=prefix + 'Add')([shortcut, x])
return x
def mobilenet_v3_large(input_shape=(224, 224, 3),
num_classes=1000,
alpha=1.0,
include_top=True):
"""
download weights url:
链接: https://pan.baidu.com/s/13uJznKeqHkjUp72G_gxe8Q 密码: 8quu
"""
bn = partial(layers.BatchNormalization, epsilon=0.001, momentum=0.99)
img_input = layers.Input(shape=input_shape)
x = layers.Conv2D(filters=16,
kernel_size=3,
strides=(2, 2),
padding='same',
use_bias=False,
name="Conv")(img_input)
x = bn(name="Conv/BatchNorm")(x)
x = HardSwish(name="Conv/HardSwish")(x)
inverted_cnf = partial(_inverted_res_block, alpha=alpha)
# input, input_c, k_size, expand_c, use_se, activation, stride, block_id
x = inverted_cnf(x, 16, 3, 16, 16, False, "RE", 1, 0)
x = inverted_cnf(x, 16, 3, 64, 24, False, "RE", 2, 1)
x = inverted_cnf(x, 24, 3, 72, 24, False, "RE", 1, 2)
x = inverted_cnf(x, 24, 5, 72, 40, True, "RE", 2, 3)
x = inverted_cnf(x, 40, 5, 120, 40, True, "RE", 1, 4)
x = inverted_cnf(x, 40, 5, 120, 40, True, "RE", 1, 5)
x = inverted_cnf(x, 40, 3, 240, 80, False, "HS", 2, 6)
x = inverted_cnf(x, 80, 3, 200, 80, False, "HS", 1, 7)
x = inverted_cnf(x, 80, 3, 184, 80, False, "HS", 1, 8)
x = inverted_cnf(x, 80, 3, 184, 80, False, "HS", 1, 9)
x = inverted_cnf(x, 80, 3, 480, 112, True, "HS", 1, 10)
x = inverted_cnf(x, 112, 3, 672, 112, True, "HS", 1, 11)
x = inverted_cnf(x, 112, 5, 672, 160, True, "HS", 2, 12)
x = inverted_cnf(x, 160, 5, 960, 160, True, "HS", 1, 13)
x = inverted_cnf(x, 160, 5, 960, 160, True, "HS", 1, 14)
last_c = _make_divisible(160 * 6 * alpha)
last_point_c = _make_divisible(1280 * alpha)
x = layers.Conv2D(filters=last_c,
kernel_size=1,
padding='same',
use_bias=False,
name="Conv_1")(x)
x = bn(name="Conv_1/BatchNorm")(x)
x = HardSwish(name="Conv_1/HardSwish")(x)
if include_top is True:
x = layers.GlobalAveragePooling2D()(x)
x = layers.Reshape((1, 1, last_c))(x)
# fc1
x = layers.Conv2D(filters=last_point_c,
kernel_size=1,
padding='same',
name="Conv_2")(x)
x = HardSwish(name="Conv_2/HardSwish")(x)
# fc2
x = layers.Conv2D(filters=num_classes,
kernel_size=1,
padding='same',
name='Logits/Conv2d_1c_1x1')(x)
x = layers.Flatten()(x)
x = layers.Softmax(name="Predictions")(x)
model = Model(img_input, x, name="MobilenetV3large")
return model
def mobilenet_v3_small(input_shape=(224, 224, 3),
num_classes=1000,
alpha=1.0,
include_top=True):
"""
download weights url:
链接: https://pan.baidu.com/s/1vrQ_6HdDTHL1UUAN6nSEcw 密码: rrf0
"""
bn = partial(layers.BatchNormalization, epsilon=0.001, momentum=0.99)
img_input = layers.Input(shape=input_shape)
x = layers.Conv2D(filters=16,
kernel_size=3,
strides=(2, 2),
padding='same',
use_bias=False,
name="Conv")(img_input)
x = bn(name="Conv/BatchNorm")(x)
x = HardSwish(name="Conv/HardSwish")(x)
inverted_cnf = partial(_inverted_res_block, alpha=alpha)
# input, input_c, k_size, expand_c, use_se, activation, stride, block_id
x = inverted_cnf(x, 16, 3, 16, 16, True, "RE", 2, 0)
x = inverted_cnf(x, 16, 3, 72, 24, False, "RE", 2, 1)
x = inverted_cnf(x, 24, 3, 88, 24, False, "RE", 1, 2)
x = inverted_cnf(x, 24, 5, 96, 40, True, "HS", 2, 3)
x = inverted_cnf(x, 40, 5, 240, 40, True, "HS", 1, 4)
x = inverted_cnf(x, 40, 5, 240, 40, True, "HS", 1, 5)
x = inverted_cnf(x, 40, 5, 120, 48, True, "HS", 1, 6)
x = inverted_cnf(x, 48, 5, 144, 48, True, "HS", 1, 7)
x = inverted_cnf(x, 48, 5, 288, 96, True, "HS", 2, 8)
x = inverted_cnf(x, 96, 5, 576, 96, True, "HS", 1, 9)
x = inverted_cnf(x, 96, 5, 576, 96, True, "HS", 1, 10)
last_c = _make_divisible(96 * 6 * alpha)
last_point_c = _make_divisible(1024 * alpha)
x = layers.Conv2D(filters=last_c,
kernel_size=1,
padding='same',
use_bias=False,
name="Conv_1")(x)
x = bn(name="Conv_1/BatchNorm")(x)
x = HardSwish(name="Conv_1/HardSwish")(x)
if include_top is True:
x = layers.GlobalAveragePooling2D()(x)
x = layers.Reshape((1, 1, last_c))(x)
# fc1
x = layers.Conv2D(filters=last_point_c,
kernel_size=1,
padding='same',
name="Conv_2")(x)
x = HardSwish(name="Conv_2/HardSwish")(x)
# fc2
x = layers.Conv2D(filters=num_classes,
kernel_size=1,
padding='same',
name='Logits/Conv2d_1c_1x1')(x)
x = layers.Flatten()(x)
x = layers.Softmax(name="Predictions")(x)
model = Model(img_input, x, name="MobilenetV3large")
return model
main
import os
import sys
import tensorflow as tf
from tqdm import tqdm
from model_v3 import mobilenet_v3_large
from utils import generate_ds
assert tf.version.VERSION >= "2.4.0", "version of tf must greater/equal than 2.4.0"
import numpy as np
from random import shuffle
import cv2 as cv
from tensorflow.keras import datasets, layers, optimizers, Sequential, metrics, losses
name_dict = {"BF":0,"BK":1,"BL":2,"BR":3,"CF":4,"CL":5,"CV":6,"CXK":7,"S":8,"XF":9}
data_root_path = "C:/my_all_data_download/ZCB/color_part_data_processing/"
test_file_path = "C:/my_all_data_download/ZCB/TXT_doc/test.txt" #测试集数据集文件
trainer_file_path = "C:/my_all_data_download/ZCB/TXT_doc/trainer.txt" #训练集数据集文件
name_data_list = {} #记录每类图片有多少训练图片、测试图片
trainer_list = []
test_list = []
#将图片完整路径存入字典
def save_train_test_file(path,name):
if name not in name_data_list:
img_list =[]
img_list.append(path)
name_data_list[name] = img_list
else:
name_data_list[name].append(path)
#遍历数据集目录,提取出图片路径,分训练集、测试集
dirs = os.listdir(data_root_path)
for d in dirs:
full_path = data_root_path + d
if os.path.isdir(full_path):
imgs = os.listdir(full_path) #列出子目录中所有图片
for img in imgs:
save_train_test_file(full_path+ "/" + img, d)
#将字典中的内容写入测试集、训练集文件
with open(test_file_path, "w") as f: #清空测试集文件
pass
with open(trainer_file_path, "w") as f: #清空训练集文件
pass
#遍历字典,分数据
for name,img_list in name_data_list.items():
i = 0
num = len(img_list)
print(f"{name}:{num}张")
for img in img_list:
if i % 10 == 0:
test_list.append(f"{img}\t{name_dict[name]}\n")
else:
trainer_list.append(f"{img}\t{name_dict[name]}\n")
i += 1
with open(trainer_file_path,"w") as f:
shuffle(trainer_list)
f.writelines(trainer_list)
with open(test_file_path,"w") as f:
f.writelines(test_list)
print("---------------------------------------------------之前的代码主要是生成.txt文件便于找到图片和对应的标签-------------------------------------------------")
def generateds(train_list):
x, y_ = [], [] # x图片数据,y_为标签
with open(train_list,'r') as f:
#读取所有行
lines = [line.strip()for line in f] #对数据进行掐头去尾放入列表
for line in lines:
img_path, lab = line.strip().split("\t")
img = cv.imread(img_path) #读入图片
img = cv.resize(img,(224,224)) ####对图片进行放缩**********************************
# img = np.array(img.convert('L')) #将图片变为8位宽灰度值的np.array格式
img = img / 255 #数据归一化(实现预处理)
x.append(img) #归一化后的数据,贴到列表x
y_.append(lab)
x = np.array(x)
y_ = np.array(y_)
y_ = y_.astype(np.int64)
return x, y_
x_train , y_train = generateds(trainer_file_path)
x_test, y_test = generateds(test_file_path)
x_train = tf.convert_to_tensor(x_train,dtype=tf.float32)
y_train = tf.convert_to_tensor(y_train,dtype=tf.int32)
x_test = tf.convert_to_tensor(x_test,dtype=tf.float32)
y_test = tf.convert_to_tensor(y_test,dtype=tf.int32)
train_dataset = tf.data.Dataset.from_tensor_slices((x_train,y_train)) #构建数据集对象
train_dataset = train_dataset.batch(32) #设置批量训练的batch为32,要将训练集重复训练10遍
test_dataset = tf.data.Dataset.from_tensor_slices((x_test,y_test))
test_dataset = test_dataset.batch(32)
data_root = "/data/flower_photos" # get data root path
# if not os.path.exists("./save_weights"):
# os.makedirs("./save_weights")
im_height = 224
im_width = 224
batch_size = 32
epochs = 1000
num_classes = 10
freeze_layer = False
# data generator with data augmentation
# train_ds, val_ds = generate_ds(data_root, im_height, im_width, batch_size)
# create model
model = mobilenet_v3_large(input_shape=(im_height, im_width, 3),
num_classes=num_classes,
include_top=True)
model.summary()
# using keras low level api for training
loss_object = tf.keras.losses.SparseCategoricalCrossentropy(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.SparseCategoricalAccuracy(name='train_accuracy')
val_loss = tf.keras.metrics.Mean(name='val_loss')
val_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='val_accuracy')
@tf.function
def train_step(train_images, train_labels):
with tf.GradientTape() as tape:
output = model(train_images, training=True)
loss = loss_object(train_labels, output)
gradients = tape.gradient(loss, model.trainable_variables)
optimizer.apply_gradients(zip(gradients, model.trainable_variables))
train_loss(loss)
train_accuracy(train_labels, output)
@tf.function
def val_step(val_images, val_labels):
output = model(val_images, training=False)
loss = loss_object(val_labels, output)
val_loss(loss)
val_accuracy(val_labels, output)
best_val_acc = 0.
for epoch in range(epochs):
train_loss.reset_states() # clear history info
train_accuracy.reset_states() # clear history info
val_loss.reset_states() # clear history info
val_accuracy.reset_states() # clear history info
# train
for step, (images, labels) in enumerate(train_dataset):
train_step(images, labels)
# print train process
# validate
for step, (imags_val, labels_val) in enumerate(test_dataset):
val_step(imags_val, labels_val)
# print val process
template = 'Epoch {}, Loss: {}, Accuracy: {}, Test Loss: {}, Test Accuracy: {}'
print(template.format(epoch,
train_loss.result(),
train_accuracy.result() * 100,
val_loss.result(),
val_accuracy.result() * 100))
# only save best weights
if val_accuracy.result() > best_val_acc:
best_val_acc = val_accuracy.result()
print(best_val_acc)
print('----------------------------------------------------------------------------------------------------:' , best_val_acc)
# model.save_weights("./save_weights/resMobileNetV3.ckpt", save_format="tf")
测试集准确率为78.260871%