当前位置: 首页>>代码示例>>Python>>正文


Python model.yolo_loss方法代码示例

本文整理汇总了Python中yolo3.model.yolo_loss方法的典型用法代码示例。如果您正苦于以下问题:Python model.yolo_loss方法的具体用法?Python model.yolo_loss怎么用?Python model.yolo_loss使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在yolo3.model的用法示例。


在下文中一共展示了model.yolo_loss方法的11个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。

示例1: train

# 需要导入模块: from yolo3 import model [as 别名]
# 或者: from yolo3.model import yolo_loss [as 别名]
def train(model, image_data, y_true, log_dir='logs/'):
    '''retrain/fine-tune the model'''
    model.compile(optimizer='adam', loss={
        # use custom yolo_loss Lambda layer.
        '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)
    early_stopping = EarlyStopping(monitor='val_loss', min_delta=0, patience=5, verbose=1, mode='auto')

    model.fit([image_data, *y_true],
              np.zeros(len(image_data)),
              validation_split=.1,
              batch_size=32,
              epochs=30,
              callbacks=[logging, checkpoint, early_stopping])
    model.save_weights(log_dir + 'trained_weights.h5')
    # Further training. 
开发者ID:scutan90,项目名称:YOLO-3D-Box,代码行数:21,代码来源:train.py

示例2: create_model

# 需要导入模块: from yolo3 import model [as 别名]
# 或者: from yolo3.model import yolo_loss [as 别名]
def create_model(input_shape, anchors, num_classes, load_pretrained=True, freeze_body=2,
            weights_path='model_data/yolo_weights.h5'):
    '''create the training model'''
    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=(416//{0:32, 1:16, 2:8}[l], 416//{0:32, 1:16, 2:8}[l], 9//3, 80+5)) for l in range(3)]
    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 in [1, 2]:
            # Freeze darknet53 body or freeze all but 3 output layers.
            num = (185, len(model_body.layers)-3)[freeze_body-1]
            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)
    print('model_body.input: ', model_body.input)
    print('model.input: ', model.input)

    return model 
开发者ID:bing0037,项目名称:keras-yolo3,代码行数:33,代码来源:train.py

示例3: create_tiny_model

# 需要导入模块: from yolo3 import model [as 别名]
# 或者: from yolo3.model import yolo_loss [as 别名]
def create_tiny_model(input_shape, anchors, num_classes, load_pretrained=True, freeze_body=2,
            weights_path='model_data/tiny_yolo_weights.h5'):
    '''create the training model, for Tiny YOLOv3'''
    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}[l], w//{0:32, 1:16}[l], \
        num_anchors//2, num_classes+5)) for l in range(2)]

    model_body = tiny_yolo_body(image_input, num_anchors//2, num_classes)
    print('Create Tiny 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 in [1, 2]:
            # Freeze the darknet body or freeze all but 2 output layers.
            num = (20, len(model_body.layers)-2)[freeze_body-1]
            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': 0.7})(
        [*model_body.output, *y_true])
    model = Model([model_body.input, *y_true], model_loss)

    return model 
开发者ID:bing0037,项目名称:keras-yolo3,代码行数:31,代码来源:train.py

示例4: create_model

# 需要导入模块: from yolo3 import model [as 别名]
# 或者: from yolo3.model import yolo_loss [as 别名]
def create_model(input_shape, anchors, num_classes, load_pretrained=True, freeze_body=True):
    '''create the training model'''
    image_input = Input(shape=(None, None, 3))
    h, w = input_shape
    num_anchors = len(anchors)//3
    y_true = [Input(shape=(h//32, w//32, num_anchors, num_classes+5)),
              Input(shape=(h//16, w//16, num_anchors, num_classes+5)),
              Input(shape=(h//8, w//8, num_anchors, num_classes+5))]

    model_body = yolo_body(image_input, num_anchors, num_classes)

    if load_pretrained:
        weights_path = os.path.join('model_data', 'yolo_weights.h5')
        if not os.path.exists(weights_path):
            print("CREATING WEIGHTS FILE" + weights_path)
            yolo_path = os.path.join('model_data', 'yolo.h5')
            orig_model = load_model(yolo_path, compile=False)
            orig_model.save_weights(weights_path)
        model_body.load_weights(weights_path, by_name=True, skip_mismatch=True)
        if freeze_body:
            # Do not freeze 3 output layers.
            for i in range(len(model_body.layers)-3):
                model_body.layers[i].trainable = False

    model_loss = Lambda(yolo_loss, output_shape=(1,), name='yolo_loss',
        arguments={'anchors': anchors, 'num_classes': num_classes})(
        [*model_body.output, *y_true])
    model = Model([model_body.input, *y_true], model_loss)

    return model_body, model 
开发者ID:scutan90,项目名称:YOLO-3D-Box,代码行数:32,代码来源:train.py

示例5: train

# 需要导入模块: from yolo3 import model [as 别名]
# 或者: from yolo3.model import yolo_loss [as 别名]
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 = 15
    val_split = 0.1
    with open(annotation_path, encoding='UTF-8') 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))


    try :
        #########2、修改epochs为30 ###########
        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 = 30, initial_epoch = 0)
    except :
        print("error")
    finally:
        model.save_weights(log_dir + 'trained_weights_except.h5')
    model.save_weights(log_dir + 'trained_weights.h5') 
开发者ID:lijialinneu,项目名称:keras-yolo3-master,代码行数:29,代码来源:train.py

示例6: create_model

# 需要导入模块: from yolo3 import model [as 别名]
# 或者: from yolo3.model import yolo_loss [as 别名]
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 
开发者ID:lijialinneu,项目名称:keras-yolo3-master,代码行数:28,代码来源:train.py

示例7: create_model

# 需要导入模块: from yolo3 import model [as 别名]
# 或者: from yolo3.model import yolo_loss [as 别名]
def create_model(input_shape, anchors, num_classes, load_pretrained=True, freeze_body=2,
            weights_path='model_data/yolo_weights.h5'):
    '''create the training model'''
    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 in [1, 2]:
            # Freeze darknet53 body or freeze all but 3 output layers.
            num = (185, len(model_body.layers)-3)[freeze_body-1]
            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 
开发者ID:Akhtar303,项目名称:Vehicle-Detection-and-Tracking-Usig-YOLO-and-Deep-Sort-with-Keras-and-Tensorflow,代码行数:31,代码来源:train.py

示例8: train

# 需要导入模块: from yolo3 import model [as 别名]
# 或者: from yolo3.model import yolo_loss [as 别名]
def train(model, annotation_path, input_shape, anchors, num_classes, log_dir='logs/'):
    model.compile(optimizer=Adam(lr=1e-3), loss={
        'yolo_loss': lambda y_true, y_pred: y_pred})
    # 该回调函数将日志信息写入TensorBorad,使得你可以动态的观察训练和测试指标的图像以及不同层的激活值直方图。
    logging = TensorBoard(log_dir=log_dir)
    # 该回调函数将在每个epoch后保存模型到filepath
    checkpoint = ModelCheckpoint(log_dir + "best_weights.h5",
                                 verbose=1,
                                 save_weights_only=True, save_best_only=True, mode='auto', period=1)
    # 当评价指标不在提升时,减少学习率
    reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.1, patience=10, verbose=1)
    # 当监测值不再改善时,该回调函数将中止训练
    early_stopping = EarlyStopping(monitor='val_loss', min_delta=0, patience=10, verbose=1)

    callbacks = [checkpoint, logging, reduce_lr]
    batch_size = 12
    val_split = 0.1
    with open(annotation_path) as f:
        lines = f.readlines()
    np.random.shuffle(lines)  # 打乱排序
    num_val = int(len(lines) * val_split)
    num_train = len(lines) - num_val  # 拿出0.1做val集
    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,
                        initial_epoch=0, callbacks=callbacks)
    model.save_weights(log_dir + 'trained_weights.h5')
    model.save(log_dir + 'model.h5') 
开发者ID:ZzzzzZXxxX,项目名称:yolo3_keras_Flag_Detection,代码行数:35,代码来源:train.py

示例9: create_model

# 需要导入模块: from yolo3 import model [as 别名]
# 或者: from yolo3.model import yolo_loss [as 别名]
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 
开发者ID:ZzzzzZXxxX,项目名称:yolo3_keras_Flag_Detection,代码行数:28,代码来源:train.py

示例10: train

# 需要导入模块: from yolo3 import model [as 别名]
# 或者: from yolo3.model import yolo_loss [as 别名]
def train(model, annotation_path, input_shape, anchors, num_classes, log_dir='logs/'):
    for index in range(1,11):
        e = index*50
        ie = e-50
        if True:
            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 = 6
            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=e,
                    initial_epoch=ie,
                    callbacks=[logging, checkpoint])
            model.save_weights(log_dir + str(index)+'trained_weights.h5') 
开发者ID:lyk19940625,项目名称:WorkControl,代码行数:29,代码来源:train.py

示例11: create_model

# 需要导入模块: from yolo3 import model [as 别名]
# 或者: from yolo3.model import yolo_loss [as 别名]
def create_model(input_shape, anchors, num_classes, load_pretrained=True, freeze_body=2,
            weights_path='model_data/yolo_weights.h5'):
    '''create the training model'''
    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 in [1, 2]:
            # Freeze darknet53 body or freeze all but 3 output layers.
            num = (185, len(model_body.layers)-3)[freeze_body-1]
            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)))

    # get output of second last layers and create bottleneck model of it
    out1=model_body.layers[246].output
    out2=model_body.layers[247].output
    out3=model_body.layers[248].output
    bottleneck_model = Model([model_body.input, *y_true], [out1, out2, out3])

    # create last layer model of last layers from yolo model
    in0 = Input(shape=bottleneck_model.output[0].shape[1:].as_list()) 
    in1 = Input(shape=bottleneck_model.output[1].shape[1:].as_list())
    in2 = Input(shape=bottleneck_model.output[2].shape[1:].as_list())
    last_out0=model_body.layers[249](in0)
    last_out1=model_body.layers[250](in1)
    last_out2=model_body.layers[251](in2)
    model_last=Model(inputs=[in0, in1, in2], outputs=[last_out0, last_out1, last_out2])
    model_loss_last =Lambda(yolo_loss, output_shape=(1,), name='yolo_loss',
        arguments={'anchors': anchors, 'num_classes': num_classes, 'ignore_thresh': 0.5})(
        [*model_last.output, *y_true])
    last_layer_model = Model([in0,in1,in2, *y_true], model_loss_last)

    
    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, bottleneck_model, last_layer_model 
开发者ID:bing0037,项目名称:keras-yolo3,代码行数:51,代码来源:train_bottleneck.py


注:本文中的yolo3.model.yolo_loss方法示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。