def generate(self): """未运算, 返回model结果的tensor""" weight_path = os.path.expanduser(self.weight_path) assert weight_path.endswith( '.h5'), 'Keras model or weights must be a .h5 file.' # Load model, or construct model and load weights. num_anchors = len(self.anchors) num_classes = len(self.class_names) h, w = self.model_image_size assert os.path.exists(self.weight_path), 'weight文件不存在' self.yolo_model = yolo_body(Input(shape=(h, w, 3)), num_anchors // 3, num_classes) self.yolo_model.load_weights( self.weight_path) # make sure model, anchors and classes match print('{} model, anchors, and classes loaded.'.format(weight_path)) # Generate output tensor targets for filtered bounding boxes. # placeholder: 实例化一个占位符张量并返回它 # input_image_shape 只输入wh self.input_image_shape = K.placeholder(shape=(2, )) if self.gpu_num >= 2: self.yolo_model = multi_gpu_model(self.yolo_model, gpus=self.gpu_num) boxes, scores, classes = yolo_eval(self.yolo_model.output, self.anchors, len(self.class_names), self.input_image_shape, score_threshold=self.score) # boxes: xywh return boxes, scores, classes
def create_model(input_shape, anchors, num_class, weights_path, freeze_body=0, load_pretrained=False): """ 创建一个model :param freeze_body: 冻结部分参数 :param input_shape: 输入尺寸, hw :param anchors: 所有的anchors :param num_class: class数量 :param weights_path: 已训练的权重的数量 :param load_pretrained: 是否加载权重 :return: """ K.clear_session() image_input = Input(shape=(416, 416, 3)) h, w = input_shape num_anchors = len(anchors) out_dict = {0: 32, 1: 16, 2: 8} # y_true的输出 y_true = [ Input(shape=(h // out_dict[m], w // out_dict[m], num_anchors // 3, num_class + 5)) for m in range(3) ] model_body = yolo_body(image_input, num_anchors // 3, num_class) # 加载已训练的weight if load_pretrained: import os assert os.path.exists(weights_path), 'weight文件不存在' 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))) loss_argument = { 'anchors': anchors, 'num_classes': num_class, 'ignore_thresh': 0.5 } # yolo_loss封装为Layer对象(用来间接到yolo_body上, 使model的输出即为loss) # 因为这个model只用来训练 model_loss = Lambda(yolo_loss, output_shape=(1, ), name='yolo_loss', arguments=loss_argument)([*model_body.output, *y_true]) model = Model([model_body.input, *y_true], model_loss) return model
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.' # Load model, or construct model and load weights. num_anchors = len(self.anchors) num_classes = len(self.class_names) is_tiny_version = num_anchors == 6 # default setting try: self.yolo_model = load_model(model_path, compile=False) print('Model loaded') except: self.yolo_model = tiny_yolo_body(Input(shape=(None,None,3)), num_anchors//2, num_classes) \ if is_tiny_version else yolo_body(Input(shape=(None,None,3)), num_anchors//3, num_classes) self.yolo_model.load_weights( self.model_path) # make sure model, anchors and classes match print('自己写模型') 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)) # Generate colors for drawing bounding boxes. 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)) np.random.seed(10101) # Fixed seed for consistent colors across runs. np.random.shuffle( self.colors) # Shuffle colors to decorrelate adjacent classes. np.random.seed(None) # Reset seed to default. # Generate output tensor targets for filtered bounding boxes. self.input_image_shape = K.placeholder(shape=(2, )) if self.gpu_num >= 2: self.yolo_model = multi_gpu_model(self.yolo_model, gpus=self.gpu_num) boxes, scores, classes = yolo_eval(self.yolo_model.output, self.anchors, len(self.class_names), self.input_image_shape, score_threshold=self.score, iou_threshold=self.iou) return boxes, scores, classes
def _main(): # TODO: 定义路径 model_path = "logs/yolov3-model-1.h5" assert model_path.endswith('.h5'), 'Keras model must be a .h5 file.' anchors_path = "model/yolo_anchors.txt" classes_path = "model/voc_classes.txt" test_path = "images/test1.jpg" output_path = "images/test1_out.jpg" anchors = get_anchors(anchors_path) class_names = get_classes(classes_path) num_classes = len(class_names) num_anchors = len(anchors) # 构建模型 image_input = Input(shape=(None, None, 3)) model = yolo_body(image_input, num_anchors // 3, num_classes) model.load_weights(model_path) model.summary() # 给每一个类定义一个颜色 hsv_tuples = [(x / num_classes, 1., 1.) for x in range(num_classes)] colors = list(map(lambda x: colorsys.hsv_to_rgb(*x), hsv_tuples)) colors = list( map(lambda x: (int(x[0] * 255), int(x[1] * 255), int(x[2] * 255)), colors)) random.seed(10101) # Fixed seed for consistent colors across runs. random.shuffle(colors) # Shuffle colors to decorrelate adjacent classes. random.seed(None) # Reset seed to default. # TODO: 加载图片 image = Image.open(test_path) print(image.size) # 按照原尺寸缩放图像,空余的地方留灰 boxed_image = letterbox_image(image, (416, 416)) image_data = np.array(boxed_image, dtype='float32') image_data /= 255. image_data = np.expand_dims(image_data, 0) # Add batch dimension. # 推理 y = model.predict(image_data, batch_size=1) boxes_, scores_, classes_ = yolo_eval(y, anchors, num_classes, (image.size[1], image.size[0])) image = cv2.imread(test_path) for i, box in enumerate(boxes_): cv2.rectangle(image, (int(box[0]), int(box[1])), (int(box[2]), int(box[3])), colors[classes_[i]]) cv2.putText(image, class_names[classes_[i]], (int(box[0]), int(box[1])), 1, 1, colors[classes_[i]], 1) cv2.imshow('image', image) cv2.imwrite(output_path, image) cv2.waitKey(0)
def create_model(input_shape, anchors, num_classes, load_pretrained=True, freeze_body=2, weights_path='model/yolo_weights.h5'): """ create the training model :param input_shape: 输入图片尺寸 :param anchors: anchor 列表 :param num_classes: classes 数量 :param load_pretrained: 是否加载预训练模型 :param freeze_body: 是否冻结部分层次 :param weights_path: 预训练模型路径 :return: """ K.clear_session() image_input = Input(shape=(None, None, 3)) h, w = input_shape num_anchors = len(anchors) # [<tf.Tensor 'input_2:0' shape=(None, 13, 13, 3, 25) dtype=float32>, # <tf.Tensor 'input_3:0' shape=(None, 26, 26, 3, 25) dtype=float32>, # <tf.Tensor 'input_4:0' shape=(None, 52, 52, 3, 25) dtype=float32>] 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)) # 加载域训练权重 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))) # todo 自定义loss 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