-
I want to do only training (lora is fine) for the head of the network, how do I do that? I get this error:
```bash
(beyond_scale_2_unsloth) brando9@ampere1~/beyond-scale-2-alignment-coeff $ python /…
-
### 功能改进
能否将已经重命名过后的qBittorent任务加上一个TAG，方便其他程序或脚本来过滤已经被Auto Bangumi处理过的任务，这样未处理过的任务就会等待处理，毕竟重命名也是需要一个等待时间的。当然这个TAG如果可以根据环境变量来自定义就更好了，谢谢
-
Hello, I have so problem with running the demo even after porting to py3...
Could you add package version to requirements.txt to be able to run the demo, Thx
-
Following the instructions provided, I was able to train my own dataset (by modifying the VOC2007) with the ff. command:
`python ./faster_rcnn/train_net.py --gpu 0 --imdb voc_2007_trainval --iters 10…
-
i have recently created a new movies and tv shows library using the new scanner and agent.
the new movies library, using the PLEX MOVIE scanner and agent are scrobbling properly. i am able to verif…
-
Computing bounding-box regression targets...
Traceback (most recent call last):
File "./faster_rcnn/train_net.py", line 109, in
restore=bool(int(args.restore)))
File "./faster_rcnn/../lib…
-
We should document the steps required to deploy the entire solution, from 0 to production, using only local commands (no pipeline approach). Here is what i did for reference:
Note: missing tm globa…
-
[목표]
textVQA fine-tuning 시켜서 training 하기
[기한 목표]
~11.20 : textVQA 다시 학습 & pretrained model학습
~11.21 : 모델 팀 회의후, 결론 내기
- web team이 model 쓸 수 있도록 인터페이스 만들기
- 다른 모델을 더 조사 -> 해당 모델을 통해…
-
After a big number of iterations (~100K), I get AP = -1 for every class. Do you have any idea what could possibly go wrong? During the training there is nothing strange oserved, e.g. `loss_= nan`
-
JSON
- [x] write a sample json for imdb data
- [x] load that data in python into a dictionary
- [x] print in a human readable format
- [x] take input from user to create new movie record
- [x] wr…