keras-yolov3可視化

1.輸出mAp

參考：
YoloV3_Keras模型MAP測試

2.輸出loss、acc曲線

修改train函數

# -*- 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)  # 設置網格形式
        plt.xlabel('epoch')
        plt.ylabel('acc-loss')  # 給x，y軸加註釋
        plt.legend(loc="upper right")  # 設置圖例顯示位置
        plt.savefig('epoch_data.jpg')

    def batch_data(self):
        iters = range(len(self.losses['batch']))
        # 創建一個圖
        plt.figure('batch_data')
        # acc
        plt.plot(iters, self.val_acc['batch'], 'r', label='val acc')  # plt.plot(x,y)，這個將數據畫成曲線
        # 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)，這個將數據畫成曲線
        # loss
        plt.plot(iters, self.losses['batch'], 'k', label='train loss')
        plt.grid(True)  # 設置網格形式
        plt.xlabel('batch')
        plt.ylabel('acc-loss')  # 給x，y軸加註釋
        plt.legend(loc="upper right")  # 設置圖例顯示位置
        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()

參考文獻：
Keras —— 繪製模型的acc-loss曲線