sungh66

yolov5l测试，内存指针占用FATAL ERROR! pool allocator destroyed too early

3

## error log | 日志或报错信息 | ログ FATAL ERROR! pool allocator destroyed too early 0x55bcadf83680 still in use 0x55bcabb83480 still in use 0x55bca83a3080 still in use 0x55bcacd83580 still in use...

It's hard to converge

1

My loss down to 0.75 and its hard to converge（150epochs）. I use the M3 model, how can i fix the issue? My data is good and i had done some...

cannot use svcg

3

**Describe the bug** The conda enviroment is OK and i infer my own model what i trained before successfully, but i cannot run the svcg Traceback (most recent call last):...

[BUG/Help] p-tuningv2的时候报了No huggingface_hub attribute hf_api

2

### Is there an existing issue for this? - [X] I have searched the existing issues ### Current Behavior 尝试使用ptuningv2来微调模型，用的是提供的衣服数据集，用的是6b-int8的预训练权重（本地下载） ### Expected Behavior _No response_ ### Steps To Reproduce 我使用了本地下载的6b-int8权重，并覆盖了https://huggingface.co/THUDM/chatglm-6b-int8的clone，能正常部署cli_demo.py，...

I want to train on 1 gpu without using distributed training, so i ran > python tools/train.py local_configs/topformer/topformer_small_512x512_160k_2x8_ade20k.py 1 --work-dir runs/ and added ``` import sys sys.path.append("/home/xx/TopFormer-main") ``` to train.py...

conv pruning issue

31

Thanks for your work, i have pruning my two-stage detection model faster rcnn with the resnet50+fpn backbone, while running the gen_schema.py, i met a conv pruned issue, becuase the model...

我的问题是大概有1k+条音频序列的数据，在预处理的时候到whisper过程直接killed了，并且前面系统会死机，有办法解决吗，还是因为音频时间有严格的30s限制，我有一些大概35~38s

Traceback (most recent call last): File "/home/xx/Download/pytorch_AMC-master/cifar_search.py", line 151, in main() File "/home/xx/Download/pytorch_AMC-master/cifar_search.py", line 100, in main next_state, real_action, done, score = learner.compress(action) File "/home/xx/Download/pytorch_AMC-master/learners/channel_pruning.py", line 194, in compress next_state,...

Several questions.Whats the differences between the "tprompt" and "prompt" in config.yaml?

1

I want to add some custom operations, such as file read and write local modules, is this possible? Beacuse i think AutoGPT is too flexible. Also, how does the code...