def generate(self):
model_path = os.path.expanduser(self.model_path)
assert model_path.endswith('.h5'), 'Keras model or weights must be a .h5 file.'
# 计算anchor数量
num_anchors = len(self.anchors)
num_classes = len(self.class_names)
# 载入模型，如果原来的模型里已经包括了模型结构则直接载入。
# 否则先构建模型再载入
try:
self.yolo_model = load_model(model_path, compile=False)
except:
self.yolo_model = yolo_body(Input(shape=(None,None,3)), num_anchors//3, num_classes)
self.yolo_model.load_weights(self.model_path)
else:
assert self.yolo_model.layers[-1].output_shape[-1] == \
num_anchors/len(self.yolo_model.output) * (num_classes + 5), \
'Mismatch between model and given anchor and class sizes'
print('{} model, anchors, and classes loaded.'.format(model_path))
# 画框设置不同的颜色
hsv_tuples = [(x / len(self.class_names), 1., 1.)
for x in range(len(self.class_names))]
self.colors = list(map(lambda x: colorsys.hsv_to_rgb(*x), hsv_tuples))
self.colors = list(
map(lambda x: (int(x[0] * 255), int(x[1] * 255), int(x[2] * 255)),
self.colors))
# 打乱颜色
np.random.seed(10101)
np.random.shuffle(self.colors)
np.random.seed(None)
self.input_image_shape = K.placeholder(shape=(2, ))
boxes, scores, classes = yolo_eval(self.yolo_model.output, self.anchors,
num_classes, self.input_image_shape,
score_threshold=self.score, iou_threshold=self.iou)
return boxes, scores, classes
anchor_wh.append(anchors_wh_13)
anchors_wh_26 = np.array(anchors[3:6])
anchors_wh_26 = np.tile(np.reshape(anchors_wh_26, (1, 1, 3, 2)), reps=(26, 26, 1, 1))
anchors_wh_26 = tf.constant(anchors_wh_26, dtype=tf.float32)
anchor_wh.append(anchors_wh_26)
anchors_wh_52 = np.array(anchors[:3])
anchors_wh_52 = np.tile(np.reshape(anchors_wh_52, (1, 1, 3, 2)), reps=(52, 52, 1, 1))
anchors_wh_52 = tf.constant(anchors_wh_52, dtype=tf.float32)
anchor_wh.append(anchors_wh_52)
# yoloV3
inputs_keras = keras.Input(shape=(416, 416, 3))
yolo3 = yolo_body(inputs=inputs_keras,
num_anchors=num_anchors,
num_classes=num_classes)
yolo3.load_weights(weight_path)
def save_model(inputs,
image_shape,
input_shape,
num_anchors,
num_classes,
score_thres,
iou_thres):
"""package model with forward propagation and post processing
# The output of my model is boxes, scores and classes, so it is
# 训练后的模型保存的位置
log_dir = 'logs/'
# 输入的shape大小
input_shape = (416, 416)
# 清除session
K.clear_session()
# 输入的图像为
image_input = Input(shape=(None, None, 3))
h, w = input_shape
# 创建yolo模型
print('Create YOLOv3 model with {} anchors and {} classes.'.format(
num_anchors, num_classes))
model_body = yolo_body(image_input, num_anchors // 3, num_classes)
# 载入预训练权重
print('Load weights {}.'.format(weights_path))
model_body.load_weights(weights_path, by_name=True, skip_mismatch=True)
# y_true为13,13,3,85
# 26,26,3,85
# 52,52,3,85
y_true = [Input(shape=(h // {0: 32, 1: 16, 2: 8}[l], w // {0: 32, 1: 16, 2: 8}[l], \
num_anchors // 3, num_classes + 5)) for l in range(3)]
# 输入为*model_body.input, *y_true
# 输出为model_loss
loss_input = [*model_body.output, *y_true]
model_loss = Lambda(yolo_loss,
#--------------------------------------------#
# 该部分代码只用于看网络结构，并非测试代码
# map测试请看get_dr_txt.py、get_gt_txt.py
# 和get_map.py
#--------------------------------------------#
from keras.layers import Input
from nets.yolo3 import yolo_body
if __name__ == "__main__":
inputs = Input([None, None, 3])
model = yolo_body(inputs, 3, 80)
model.summary()
# for i,layer in enumerate(model.layers):
# print(i,layer.name)
num_anchors = len(anchors)
# 训练后的模型保存的位置
log_dir = 'logs/'
# 输入的shape大小
input_shape = (416,416)
# 清除session
K.clear_session()
# 输入的图像为
image_input = Input(shape=(None, None, 3))
h, w = input_shape
# 创建yolo模型
print('Create YOLOv3 model with {} anchors and {} classes.'.format(num_anchors, num_classes))
model_body = yolo_body(image_input, num_anchors//3, num_classes) # model_body = [y1,y2,y3]，得到框、分数、类别概率、修正框、筛选框
'''
image_input.shape[?,?,?,3],num_classes=20,num_anchors//3=3
'''
# 载入预训练权重
print('Load weights {}.'.format(weights_path))
model_body.load_weights(weights_path, by_name=True, skip_mismatch=True) # 加载模型所需的参数
# y_true为13,13,3,25
# 26,26,3,25
# 52,52,3,25
y_true = [Input(shape=(h//{0:32, 1:16, 2:8}[l], w//{0:32, 1:16, 2:8}[l], \
num_anchors//3, num_classes+5)) for l in range(3)]
# 输入为*model_body.input, *y_true
# 输出为model_loss
# 13,13,3,85
# 26,26,3,85
# 13,26是grid,3是每个尺度的anchor个数,num_classes+5是框的4个坐标信息,objectness score一位,类别1位和类别数
y_true = [
Input(shape=(h // {
0: 32,
1: 16
}[l], w // {
0: 32,
1: 16
}[l], num_anchors // 2, num_classes + 5)) for l in range(2)
]
else:
print('Create YOLOv3 model with {} anchors and {} classes.'.format(
num_anchors, num_classes))
model_body = yolo_body(image_input, num_anchors // 3,
num_classes) #调用yolo3.py的yolo_body生成yolo计算图
# y_true为[(13, 13, 3, num_classes+5), (26, 26, 3, num_classes+5), (52, 52, 3, num_classes+5)]三种大小，
# 13,13,3,85
# 26,26,3,85
# 52,52,3,85
# 13,26,52是grid,3是每个尺度的anchor个数,num_classes+5是框的4个坐标信息,objectness score一位,类别1位和类别数
y_true = [
Input(shape=(h // {
0: 32,
1: 16,
2: 8
}[l], w // {
0: 32,
1: 16,
2: 8
}[l], num_anchors // 3, num_classes + 5)) for l in range(3)
#--------------------------------------------# # 该部分代码只用于看网络结构，并非测试代码 # map测试请看get_dr_txt.py、get_gt_txt.py # 和get_map.py #--------------------------------------------# from nets.yolo3 import yolo_body from keras.layers import Input inputs = Input([416, 416, 3]) model = yolo_body(inputs, 3, 80, phi=3) model.summary() # for i,layer in enumerate(model.layers): # print(i,layer.name)
# ------------------------------------------------- # @Time : 2020/7/2 0:39 # @Author : RunRun # @File : net # @Software: PyCharm # # ------------------------------------------------- # 功能 # # 查看整个网络的架构 # # # 结果 # # # # # from nets.yolo3 import yolo_body from keras.layers import Input Inputs = Input([416,416,3]) model = yolo_body(Inputs,3,10) model.summary()
def train_process(config_dic):
# ----------------------------------------------------#
# 获得图片路径和标签
# ----------------------------------------------------#
annotation_path = str(config_dic["annotation_path"])
# ------------------------------------------------------#
# 训练后的模型保存的位置，保存在logs文件夹里面
# ------------------------------------------------------#
log_dir = 'logs/'
# ----------------------------------------------------#
# classes和anchor的路径，非常重要
# 训练前一定要修改classes_path，使其对应自己的数据集
# ----------------------------------------------------#
classes_path = str(config_dic["classes_path"])
anchors_path = str(config_dic["anchors_path"])
# ------------------------------------------------------#
# 权值文件请看README，百度网盘下载
# 训练自己的数据集时提示维度不匹配正常
# 预测的东西都不一样了自然维度不匹配
# ------------------------------------------------------#
weights_path = str(config_dic["pretained_model"])
# ------------------------------------------------------#
# 输入的shape大小
# ------------------------------------------------------#
input_shape = (int(config_dic["model_image_size"]),
int(config_dic["model_image_size"]))
print("input shape:", input_shape)
# ------------------------------------------------------#
# 是否对损失进行归一化
# ------------------------------------------------------#
normalize = True
# ----------------------------------------------------#
# 获取classes和anchor
# ----------------------------------------------------#
class_names = get_classes(classes_path)
anchors = get_anchors(anchors_path)
# ------------------------------------------------------#
# 一共有多少类和多少先验框
# ------------------------------------------------------#
num_classes = len(class_names)
num_anchors = len(anchors)
K.clear_session()
# ------------------------------------------------------#
# 创建yolo模型
# ------------------------------------------------------#
image_input = Input(shape=(None, None, 3))
h, w = input_shape
print('Create YOLOv3 model with {} anchors and {} classes.'.format(
num_anchors, num_classes))
model_body = yolo_body(image_input, num_anchors // 3, num_classes)
# ------------------------------------------------------#
# 载入预训练权重
# ------------------------------------------------------#
print('Load weights {}.'.format(weights_path))
model_body.load_weights(weights_path, by_name=True, skip_mismatch=True)
# ------------------------------------------------------#
# 在这个地方设置损失，将网络的输出结果传入loss函数
# 把整个模型的输出作为loss
# ------------------------------------------------------#
y_true = [Input(shape=(h // {0: 32, 1: 16, 2: 8}[l], w // {0: 32, 1: 16, 2: 8}[l], \
num_anchors // 3, num_classes + 5)) for l in range(3)]
loss_input = [*model_body.output, *y_true]
model_loss = Lambda(yolo_loss,
output_shape=(1, ),
name='yolo_loss',
arguments={
'anchors': anchors,
'num_classes': num_classes,
'ignore_thresh': 0.5,
'normalize': normalize
})(loss_input)
model = Model([model_body.input, *y_true], model_loss)
# ------------------------------------------------------#
# 主干特征提取网络特征通用，冻结训练可以加快训练速度
# 也可以在训练初期防止权值被破坏。
# 提示OOM或者显存不足请调小Batch_size
# ------------------------------------------------------#
freeze_layers = 184
for i in range(freeze_layers):
model_body.layers[i].trainable = False
print('Freeze the first {} layers of total {} layers.'.format(
freeze_layers, len(model_body.layers)))
# -------------------------------------------------------------------------------#
# 训练参数的设置
# logging表示tensorboard的保存地址
# checkpoint用于设置权值保存的细节，period用于修改多少epoch保存一次
# reduce_lr用于设置学习率下降的方式
# early_stopping用于设定早停，val_loss多次不下降自动结束训练，表示模型基本收敛
# -------------------------------------------------------------------------------#
logging = TensorBoard(log_dir=log_dir)
checkpoint = ModelCheckpoint(
log_dir + 'ep{epoch:03d}-loss{loss:.3f}-val_loss{val_loss:.3f}.h5',
monitor='val_loss',
save_weights_only=False,
save_best_only=True,
period=20)
reduce_lr = ReduceLROnPlateau(monitor='val_loss',
factor=0.5,
patience=3,
verbose=1)
early_stopping = EarlyStopping(monitor='val_loss',
min_delta=0,
patience=10,
verbose=1)
# ----------------------------------------------------------------------#
# 验证集的划分在train.py代码里面进行
# 2007_test.txt和2007_val.txt里面没有内容是正常的。训练不会使用到。
# 当前划分方式下，验证集和训练集的比例为1:9
# ----------------------------------------------------------------------#
val_split = 0.1
with open(annotation_path) as f:
lines = f.readlines()
np.random.seed(10101)
np.random.shuffle(lines)
np.random.seed(None)
num_val = int(len(lines) * val_split)
num_train = len(lines) - num_val
# ------------------------------------------------------#
# 主干特征提取网络特征通用，冻结训练可以加快训练速度
# 也可以在训练初期防止权值被破坏。
# Init_Epoch为起始世代
# Freeze_Epoch为冻结训练的世代
# Epoch总训练世代
# 提示OOM或者显存不足请调小Batch_size
# ------------------------------------------------------#
if True:
Init_epoch = 0
Freeze_epoch = int(config_dic["Freeze_epoch"])
batch_size = 8
learning_rate_base = 1e-3
model.compile(optimizer=Adam(lr=learning_rate_base),
loss={
'yolo_loss': lambda y_true, y_pred: y_pred
})
print('Train on {} samples, val on {} samples, with batch size {}.'.
format(num_train, num_val, batch_size))
model.fit_generator(
data_generator(lines[:num_train],
batch_size,
input_shape,
anchors,
num_classes,
random=True),
steps_per_epoch=max(1, num_train // batch_size),
validation_data=data_generator(lines[num_train:],
batch_size,
input_shape,
anchors,
num_classes,
random=False),
validation_steps=max(1, num_val // batch_size),
epochs=Freeze_epoch,
initial_epoch=Init_epoch,
callbacks=[logging, checkpoint, reduce_lr, early_stopping])
model.save_weights(log_dir + 'trained_weights_stage_1.h5')
# model.save(log_dir+"stage1.h5")
for i in range(freeze_layers):
model_body.layers[i].trainable = True
# 解冻后训练
if True:
Freeze_epoch = int(config_dic["Freeze_epoch"])
Epoch = int(config_dic["Epoch"])
batch_size = 4
learning_rate_base = 1e-4
model.compile(optimizer=Adam(lr=learning_rate_base),
loss={
'yolo_loss': lambda y_true, y_pred: y_pred
})
print('Train on {} samples, val on {} samples, with batch size {}.'.
format(num_train, num_val, batch_size))
model.fit_generator(
data_generator(lines[:num_train],
batch_size,
input_shape,
anchors,
num_classes,
random=True),
steps_per_epoch=max(1, num_train // batch_size),
validation_data=data_generator(lines[num_train:],
batch_size,
input_shape,
anchors,
num_classes,
random=False),
validation_steps=max(1, num_val // batch_size),
epochs=Epoch,
initial_epoch=Freeze_epoch,
callbacks=[logging, checkpoint, reduce_lr, early_stopping])
# model.save_weights(log_dir + config_dic["save_rknn_name"] + ".h5")
model.save(log_dir + config_dic["save_rknn_name"] + ".h5")
model_body.save(log_dir + config_dic["save_rknn_name"] + "_body.h5")
K.clear_session()
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time : 2020/2/12 20:58
# @Author : codingchaozhang
from nets.yolo3 import yolo_body
from keras.layers import Input
Inputs = Input([416,416,3])
model = yolo_body(Inputs,3,20)
model.save("yolov3.h5")
model.summary()
def generate(self):
'''
Parameters
----------
Returns
-------
boxes:
scores:
classes:
'''
model_path = os.path.expanduser(self.model_path)
assert model_path.endswith(
'.h5'), 'Keras model or weights must be a .h5 file.'
# 计算anchor数量
num_anchors = len(self.anchors)
num_classes = len(self.class_names)
# 载入模型，如果原来的模型里已经包括了模型结构则直接载入。
# 否则先构建模型再载入
try:
self.yolo_model = load_model(model_path, compile=False)
except:
self.yolo_model = yolo_body(Input(shape=(None, None, 3)),
num_anchors // 3, num_classes)
self.yolo_model.load_weights(self.model_path)
else:
assert self.yolo_model.layers[-1].output_shape[-1] == \
num_anchors/len(self.yolo_model.output) * (num_classes + 5), \
'Mismatch between model and given anchor and class sizes'
print('{} model, anchors, and classes loaded.'.format(model_path))
# 画框设置不同的颜色,每个类设置一种颜色
# colors:array, shape=(20, 3), eg:[(0,178,255), (255,153,0), ..., (255,0,0)]
hsv_tuples = [(x / len(self.class_names), 1., 1.)
for x in range(len(self.class_names))]
self.colors = list(map(lambda x: colorsys.hsv_to_rgb(*x), hsv_tuples))
self.colors = list(
map(lambda x: (int(x[0] * 255), int(x[1] * 255), int(x[2] * 255)),
self.colors))
# 打乱颜色
np.random.seed(10101)
np.random.shuffle(self.colors)
np.random.seed(None)
# 根据检测参数，过滤框
# <tf.Tensor 'Placeholder_366:0' shape=(2,) dtype=float32>
self.input_image_shape = K.placeholder(shape=(2, ))
# 图片预测
boxes, scores, classes = yolo_eval(self.yolo_model.output,
self.anchors,
num_classes,
self.input_image_shape,
score_threshold=self.score,
iou_threshold=self.iou)
return boxes, scores, classes
