物体检测YOLOv3实践（2）

from keras.optimizers import Adam
from yolo3.utils import get_random_data 

# 设置所有的层可训练
for i in range(len(model.layers)):
    model.layers[i].trainable = True
    
# 选择Adam优化器，设置学习率
learning_rate = 1e-4
model.compile(optimizer=Adam(lr=learning_rate), loss={'yolo_loss': lambda y_true, y_pred: y_pred}) 

# 设置批大小和训练轮数
batch_size = 16
max_epochs = 2
print('Train on {} samples, val on {} samples, with batch size {}.'.format(num_train, num_val, batch_size))
# 开始训练
model.fit_generator(data_generator_wrapper(lines[:num_train], batch_size, input_shape, data_path,anchors, num_classes),
    steps_per_epoch=max(1, num_train//batch_size),
    validation_data=data_generator_wrapper(lines[num_train:], batch_size, input_shape, data_path,anchors, num_classes),
    validation_steps=max(1, num_val//batch_size),
    epochs=max_epochs,
    initial_epoch=0,
    callbacks=[reduce_lr, early_stopping])

import os
os.makedirs(save_path)
# 保存模型
model.save_weights(os.path.join(save_path, 'trained_weights_final.h5'))

from PIL import Image
import numpy as np
# 测试文件路径
test_file_path = './test.jpg'
# 打开测试文件
image = Image.open(test_file_path)
image_ori = np.array(image)
image_ori.shape

from yolo3.utils import letterbox_image

new_image_size = (image.width - (image.width % 32), image.height - (image.height % 32))
boxed_image = letterbox_image(image, new_image_size)
image_data = np.array(boxed_image, dtype='float32')
image_data /= 255.
image_data = np.expand_dims(image_data, 0)
image_data.shape

import keras.backend as K
sess = K.get_session()

from yolo3.model import yolo_body
from keras.layers import Input
# coco数据anchor值文件存储位置
anchor_path = "./model_data/yolo_anchors.txt"
with open(anchor_path) as f:
    anchors = f.readline()
anchors = [float(x) for x in anchors.split(',')]
anchors = np.array(anchors).reshape(-1, 2)
yolo_model = yolo_body(Input(shape=(None,None,3)), len(anchors)//3, num_classes)

# 模型权重存储路径
weights_path = "./model_data/yolo.h5"
yolo_model.load_weights(weights_path)

iou = 0.45
score = 0.8

from yolo3.model import yolo_eval
input_image_shape = K.placeholder(shape=(2, ))
boxes, scores, classes = yolo_eval(
    yolo_model.output, 
    anchors,
    num_classes,
    input_image_shape,
    score_threshold=score, 
    iou_threshold=iou)

out_boxes, out_scores, out_classes = sess.run(
    [boxes, scores, classes],
    feed_dict={
        yolo_model.input: image_data,
        input_image_shape: [image.size[1], image.size[0]],
        K.learning_phase(): 0
    })

class_coco = get_classes(classes_path)
out_coco = []
for i in out_classes:
    out_coco.append(class_coco[i])

print(out_boxes)
print(out_scores)
print(out_coco)

from PIL import Image, ImageFont, ImageDraw

font = ImageFont.truetype(font='font/FiraMono-Medium.otf',
                    size=np.floor(3e-2 * image.size[1] + 0.5).astype('int32'))

thickness = (image.size[0] + image.size[1]) // 300

for i, c in reversed(list(enumerate(out_coco))):
    predicted_class = c
    box = out_boxes[i]
    score = out_scores[i]

    label = '{} {:.2f}'.format(predicted_class, score)
    draw = ImageDraw.Draw(image)
    label_size = draw.textsize(label, font)

    top, left, bottom, right = box
    top = max(0, np.floor(top + 0.5).astype('int32'))
    left = max(0, np.floor(left + 0.5).astype('int32'))
    bottom = min(image.size[1], np.floor(bottom + 0.5).astype('int32'))
    right = min(image.size[0], np.floor(right + 0.5).astype('int32'))
    print(label, (left, top), (right, bottom))

    if top - label_size[1] >= 0:
        text_origin = np.array([left, top - label_size[1]])
    else:
        text_origin = np.array([left, top + 1])

    for i in range(thickness):
        draw.rectangle(
            [left + i, top + i, right - i, bottom - i],
            outline=225)
    draw.rectangle(
        [tuple(text_origin), tuple(text_origin + label_size)],
        fill=225)
    draw.text(text_origin, label, fill=(0, 0, 0), font=font)
    del draw

image