kaikaizhu

@KaiOtter 我把所有的

@sourav164 Have you figured it out? I am having the same issue too.

主要原因是project_dir后面不应该有‘upload’, get_local_path函数会在project_dir后面补一个upload modify label_studio_ml/model.py as following: ```python def get_local_path(self, url, project_dir=None): #return get_local_path(url, project_dir=project_dir, hostname=self.hostname, access_token=self.access_token) => return get_local_path(url, project_dir=project_dir.replace('/upload', '/'), hostname=self.hostname, access_token=self.access_token) ```

@Chilicyy 我遇到了同样的问题： 测试coco数据集上每个类别的map时，在命令中加入--verbose，就会出现 'Model' object has no attribute 'names' 和 'Model' object has no attribute 'nc' 的报错。 执行命令是：python tools/eval.py --data data/coco.yaml --batch 2 --weights weights/yolov6n.pt --task val --reproduce_640_eval --verbose

我知道应该怎么修改了。 把 model.nc 改为 self.data['nc'] 把 model.names 改为 self.data['names']

@yeyewen 你解决了么？能不能发我一份？感谢！

@yeyewen 邮箱[email protected]

I also want to use a custom resolution of 128x128 to train the model. Did you succeed? Does anyone know what to do?

+1 How to solve it?

trainer.output_info[key].update(metric_dict[key].numpy()[0] 改为 trainer.output_info[key].update(metric_dict[key].numpy() 即可