1.输出mAp
2.输出loss、acc曲线
修改train函数
# -*- coding: utf-8 -*-
import numpy as np
import keras.backend as K
from keras.layers import Input, Lambda
from keras.models import Model
from keras.callbacks import TensorBoard, ModelCheckpoint, EarlyStopping
from yolo3.model import preprocess_true_boxes, yolo_body, tiny_yolo_body, yolo_loss
from yolo3.utils import get_random_data
import time
import keras
from keras.models import Sequential
from keras.layers import Dense
import matplotlib.pyplot as plt
class LossHistory(keras.callbacks.Callback):
def on_train_begin(self, logs={}):
self.losses = {'batch': [], 'epoch': []}
self.accuracy = {'batch': [], 'epoch': []}
self.val_loss = {'batch': [], 'epoch': []}
self.val_acc = {'batch': [], 'epoch': []}
def on_batch_end(self, batch, logs={}):
self.losses['batch'].append(logs.get('loss'))
self.accuracy['batch'].append(logs.get('acc'))
self.val_loss['batch'].append(logs.get('val_loss'))
self.val_acc['batch'].append(logs.get('val_acc'))
def on_epoch_end(self, batch, logs={}):
self.losses['epoch'].append(logs.get('loss'))
self.accuracy['epoch'].append(logs.get('acc'))
self.val_loss['epoch'].append(logs.get('val_loss'))
self.val_acc['epoch'].append(logs.get('val_acc'))
def loss_plot(self):
self.batch_data()
# if loss_type == 'ture':
self.epoch_plot()
# plt.show()
def epoch_plot(self):
iters = range(len(self.losses['epoch']))
plt.figure('epoch_data')
# val_acc
plt.plot(iters, self.val_acc['epoch'], 'r', label='val acc')
# val_loss
plt.plot(iters, self.val_loss['epoch'], 'g', label='val loss')
plt.plot(iters, self.accuracy['epoch'], 'b', label='train acc')
plt.plot(iters, self.losses['epoch'], 'k', label='train loss')
plt.grid(True) # 设置网格形式
plt.xlabel('epoch')
plt.ylabel('acc-loss') # 给x,y轴加注释
plt.legend(loc="upper right") # 设置图例显示位置
plt.savefig('epoch_data.jpg')
def batch_data(self):
iters = range(len(self.losses['batch']))
# 创建一个图
plt.figure('batch_data')
# acc
plt.plot(iters, self.val_acc['batch'], 'r', label='val acc') # plt.plot(x,y),这个将数据画成曲线
# loss
plt.plot(iters, self.val_loss['batch'], 'g', label='val loss')
# acc
plt.plot(iters, self.accuracy['batch'], 'b', label='train acc') # plt.plot(x,y),这个将数据画成曲线
# loss
plt.plot(iters, self.losses['batch'], 'k', label='train loss')
plt.grid(True) # 设置网格形式
plt.xlabel('batch')
plt.ylabel('acc-loss') # 给x,y轴加注释
plt.legend(loc="upper right") # 设置图例显示位置
plt.savefig('batch_data.jpg')
logs_loss = LossHistory()
def _main():
annotation_path = '2007_train.txt'
log_dir = 'logs/000/'
classes_path = 'model_data/voc_classes.txt'
anchors_path = 'model_data/yolo_anchors.txt'
class_names = get_classes(classes_path)
anchors = get_anchors(anchors_path)
input_shape = (416, 416) # multiple of 32, hw
model = create_model(input_shape, anchors, len(class_names))
train(model, annotation_path, input_shape, anchors, len(class_names), log_dir=log_dir)
def train(model, annotation_path, input_shape, anchors, num_classes, log_dir='logs/'):
model.compile(optimizer='adam', loss={
'yolo_loss': lambda y_true, y_pred: y_pred})
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=True, save_best_only=True, period=1)
batch_size = 4
val_split = 0.1
with open(annotation_path) as f:
lines = f.readlines()
np.random.shuffle(lines)
num_val = int(len(lines) * val_split)
num_train = len(lines) - num_val
print('Train on {} samples, val on {} samples, with batch size {}.'.format(num_train, num_val, batch_size))
model.fit_generator(data_generator_wrap(lines[:num_train], batch_size, input_shape, anchors, num_classes),
steps_per_epoch=max(1, num_train // batch_size),
validation_data=data_generator_wrap(lines[num_train:], batch_size, input_shape, anchors,
num_classes),
validation_steps=max(1, num_val // batch_size),
# epochs=500,
epochs=1,
initial_epoch=0,
callbacks=[logs_loss])
model.save_weights(log_dir + 'trained_weights.h5')
def get_classes(classes_path):
with open(classes_path) as f:
class_names = f.readlines()
class_names = [c.strip() for c in class_names]
return class_names
def get_anchors(anchors_path):
with open(anchors_path) as f:
anchors = f.readline()
anchors = [float(x) for x in anchors.split(',')]
return np.array(anchors).reshape(-1, 2)
def create_model(input_shape, anchors, num_classes, load_pretrained=False, freeze_body=False,
weights_path='model_data/yolo_weights.h5'):
K.clear_session() # get a new session
image_input = Input(shape=(None, None, 3))
h, w = input_shape
num_anchors = len(anchors)
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)]
model_body = yolo_body(image_input, num_anchors // 3, num_classes)
print('Create YOLOv3 model with {} anchors and {} classes.'.format(num_anchors, num_classes))
if load_pretrained:
model_body.load_weights(weights_path, by_name=True, skip_mismatch=True)
print('Load weights {}.'.format(weights_path))
if freeze_body:
# Do not freeze 3 output layers.
num = len(model_body.layers) - 7
for i in range(num): model_body.layers[i].trainable = False
print('Freeze the first {} layers of total {} layers.'.format(num, len(model_body.layers)))
model_loss = Lambda(yolo_loss, output_shape=(1,), name='yolo_loss',
arguments={'anchors': anchors, 'num_classes': num_classes, 'ignore_thresh': 0.5})(
[*model_body.output, *y_true])
model = Model([model_body.input, *y_true], model_loss)
return model
def data_generator(annotation_lines, batch_size, input_shape, anchors, num_classes):
n = len(annotation_lines)
np.random.shuffle(annotation_lines)
i = 0
while True:
image_data = []
box_data = []
for b in range(batch_size):
i %= n
image, box = get_random_data(annotation_lines[i], input_shape, random=True)
image_data.append(image)
box_data.append(box)
i += 1
image_data = np.array(image_data)
box_data = np.array(box_data)
y_true = preprocess_true_boxes(box_data, input_shape, anchors, num_classes)
yield [image_data, *y_true], np.zeros(batch_size)
def data_generator_wrap(annotation_lines, batch_size, input_shape, anchors, num_classes):
n = len(annotation_lines)
if n == 0 or batch_size <= 0: return None
return data_generator(annotation_lines, batch_size, input_shape, anchors, num_classes)
if __name__ == '__main__':
_main()
logs_loss.loss_plot()
参考文献:
Keras —— 绘制模型的acc-loss曲线