print('shape mismatch in %s. shape_1=%s, while shape_2=%s.' %
(k, shape_1, shape_2))
_state_dict.update(new_state_dict)
model.load_state_dict(_state_dict)
if __name__ == '__main__':
cfg = None
if config_file == 0:
cfg = PPYOLO_2x_Config()
elif config_file == 1:
cfg = PPYOLO_2x_Config()
elif config_file == 2:
cfg = PPYOLO_r18vd_Config()
class_names = get_classes(cfg.classes_path)
num_classes = len(class_names)
# 步id，无需设置，会自动读。
iter_id = 0
# 创建模型
Backbone = select_backbone(cfg.backbone_type)
backbone = Backbone(**cfg.backbone)
IouLoss = select_loss(cfg.iou_loss_type)
iou_loss = IouLoss(**cfg.iou_loss)
iou_aware_loss = None
if cfg.head['iou_aware']:
IouAwareLoss = select_loss(cfg.iou_aware_loss_type)
iou_aware_loss = IouAwareLoss(**cfg.iou_aware_loss)
Loss = select_loss(cfg.yolo_loss_type)
config.gpu_options.per_process_gpu_memory_fraction = 1.0
set_session(tf.Session(config=config))
if __name__ == '__main__':
classes_path = 'data/coco_classes.txt'
# model_path可以是'yolov4.h5'、'./weights/step00001000.h5'这些。
# model_path = 'yolov4.h5'
model_path = './weights/step00001000.h5'
# input_shape越大，精度会上升，但速度会下降。
# input_shape = (320, 320)
input_shape = (416, 416)
# input_shape = (608, 608)
num_anchors = 3
all_classes = get_classes(classes_path)
num_classes = len(all_classes)
inputs = layers.Input(shape=(None, None, 3))
yolo = YOLOv4(inputs, num_classes, num_anchors)
yolo.load_weights(model_path, by_name=True)
_decode = Decode(0.05, 0.45, input_shape, yolo, all_classes)
# detect images in test floder.
for (root, dirs, files) in os.walk('images/test'):
if files:
start = time.time()
for f in files:
path = os.path.join(root, f)
image = cv2.imread(path)
image, boxes, scores, classes = _decode.detect_image(
# 验证集图片的相对路径
eval_pre_path = cfg.val_pre_path
anno_file = cfg.val_path
from pycocotools.coco import COCO
val_dataset = COCO(anno_file)
val_img_ids = val_dataset.getImgIds()
images = [] # 只跑有gt的图片，跟随PaddleDetection
for img_id in val_img_ids:
ins_anno_ids = val_dataset.getAnnIds(
imgIds=img_id, iscrowd=False) # 读取这张图片所有标注anno的id
if len(ins_anno_ids) == 0:
continue
img_anno = val_dataset.loadImgs(img_id)[0]
images.append(img_anno)
all_classes = get_classes(cfg.classes_path)
num_classes = len(all_classes)
# 创建模型
Backbone = select_backbone(cfg.backbone_type)
backbone = Backbone(**cfg.backbone)
Fpn = select_fpn(cfg.fpn_type)
fpn = Fpn(**cfg.fpn)
Head = select_head(cfg.head_type)
head = Head(fcos_loss=None, nms_cfg=cfg.nms_cfg, **cfg.head)
fcos = FCOS(backbone, fpn, head)
if use_gpu:
fcos = fcos.cuda()
fcos.load_state_dict(torch.load(model_path))
fcos.eval(
) # 必须调用model.eval()来设置dropout和batch normalization layers在运行推理前，切换到评估模式。
