damengdameng
damengdameng
> Could someone give the pytorch versions witch it works? Hi, have you got the answer?
In the case of python3, I just change the ` with open(args.model) as f:` to `with open(args.model,'rb') as f:` then the model can be loaded successfully.
> Hi, > > I find that as the training goes (beyond 20 epochs), the loss will gradually become negative. May I ask if this is harmful to downstream tasks?...
> 你好，把识别模型.h5转pb，加载pb模型识别都是乱码 您好 请问你的问题解决了嘛？
改parse_args.py 呀... 或者python mian.py --num_imgs=你要的数字 > 默认是20
> I find out the reason: the groundingDINO object detector cannot work in case of loading Text2Box_cuda on other cuda card. > I change to load on 0, it works....
> hi, same confusions! Have you reimplemented this work successfully?
> I met the same problem! Have you solved it? This can be solved by changing ` feature_maps=self.texture_enhance(feature_maps,(0.2,0.2)) ` to ` feature_maps, _ =self.texture_enhance(feature_maps,(0.2,0.2)) `
@GHmaryam hi.i used your method, solved the original error, then there was a new error .. OutOfRangeError (see above for traceback): RandomShuffleQueue '_3_shuffle_batch/random_shuffle_queue' is closed and has insufficient elements (requested...
> > Yes, `youtube-dl https://www.youtube.com/watch?v=VXP7-x_w2eg`. If you launch from a folder then `./youtube-dl https://www.youtube.com/watch?v=VXP7-x_w2eg`. > > Thank you for your help, i can download the video using youtube-dl by opening...