marsmarcin / yolo_save_subimages Goto Github PK

Hi,Could I ask you one question:
I just see that the title is Yolo,but the weight is yolov2,so I want ask you that this project use yolo or yolov2?

你好我将你的代码生成后，使用.\darknet_no_gpu.exe detector test .\data\coco.data .\cfg\yolo.cfg .\yolov2.weights -i 0 -thresh 0.25 dog.jpg 命令成功复现。但是将权重文件更改为我自己基于yolov3训练的文件后报错：
82 Type not recognized: [yolo]
Unused field: 'mask = 6,7,8'
Unused field: 'anchors = 10,13,16,30,33,23,30,61,62,45,59,119,116,90,156,198,373,326'
Unused field: 'classes = 20'
Unused field: 'num = 9'
Unused field: 'jitter = .3'
Unused field: 'ignore_thresh = .5'
Unused field: 'truth_thresh = 1'
Unused field: 'random = 1'
83 route 79
84 conv 256 1 x 1 / 1 13 x 13 x 512 -> 13 x 13 x 256
85 Type not recognized: [upsample]
Unused field: 'stride = 2'
86 route 85 61
87 Layer before convolutional layer must output image.: No error
这个是我是用的命令： .\darknet_no_gpu.exe detector test .\data\voc_CardText.data .\cfg\yolov3-voc.cfg .\yolov3-voc-CardText_last_5800loss0.090.weights -i 0 -thresh 0.25 2.jpg
请问这个错误要如何解决呢？感谢