Zhang Cong

icon location Beijing, China icon location Artificial Intelligence Researcher&Engineer, Deep learning Engineer, Machine learning Engineer, Electronic and software engineer

Results 7 issues of Zhang Cong

Visdom successfully connected to server '>' not supported between instances of 'float' and 'NoneType' Traceback (most recent call last): File "e:/AI-pro/Insightface/Face_Pytorch-master/train_my.py", line 263, in <module> train(args) File "e:/AI-pro/Insightface/Face_Pytorch-master/train_my.py", line 155, in train total_loss.backward() File "C:\Users\Administrator\Anaconda3\lib\site-packages\torch\tensor.py", line 107, in backward torch.autograd.backward(self, gradient, retain_graph, create_graph) File "C:\Users\Administrator\Anaconda3\lib\site-packages\torch\autograd\__init__.py", line 93, in backward allow_unreachable=True) # allow_unreachable flag RuntimeError: cuda runtime error (59) : device-side assert triggered at C:/w/1/s/windows/pytorch/aten/src\THC/generic/THCTensorMath.cu:26

2 comment

When I ran train.py, I got the error. Who knows why and how to solve it?

How to get the original AgeDB-30 and CFP-FP test dataset?

MazeTaskSampler ๅฏผๅ…ฅๅคฑ่ดฅ

1 comment

File "E:\projects\MetaGym\metagym\metamaze\test.py", line 7, in from metagym.metamaze import MazeTaskSampler ImportError: cannot import name 'MazeTaskSampler' from 'metagym.metamaze' (D:\Programs\Anaconda3\lib\site-packages\metagym\metamaze\__init__.py)

RL related issues, code understanding , scores, rewards,ppo

1 comment

### ๐Ÿš€ The feature, motivation, and pitch https://github.com/CarperAI/trlx/blob/b91da7b03d8e9fa0c0d6dce10a8f2611aca3013f/trlx/trainer/accelerate_ppo_trainer.py (1) In line 307, scores = torch.tensor( self.reward_fn( samples=str_samples, prompts=str_prompts, outputs=str_outputs, ), dtype=torch.float, ).to(device) What's the meaning of scores and how it...

feature request

่ฎญ็ปƒD4ๅฎŒๅ…จๅคฑ่ดฅ

1 comment

xๅ…‰ๅ›พ็‰‡๏ผŒ2700ๅผ ๏ผŒ่ฎญ็ปƒๅ’Œ้ชŒ่ฏ้›†loss้ƒฝๅฏไปฅ ๅˆฐ0.6ๅทฆๅณ๏ผŒ้ชŒ่ฏ0.9๏ผŒ ไฝ†coco_eval.py็ป“ๆžœๅ‡ ไนŽๅ…จๆ˜ฏ0 ่ฏท้—ฎๅฏ่ƒฝๆ˜ฏๅ•ฅๅŽŸๅ› ๏ผŸ ็ฎ—ๆณ•ไปฃ็ ไธไผšๆœ‰้—ฎ้ข˜ๅง๏ผŸ ็œŸๆญฃ่ฎญ็ปƒๆ—ถ็š„labelๆ˜ฏๅ•ฅ ๆˆ‘็š„ๆ ‡ๆณจๆ–‡ไปถimage_idๆ˜ฏๅฏนๅบ”ๅ›พ็‰‡ๆ–‡ไปถๅๆ•ฐๅญ—็ผ–ๅท๏ผŒ ๅŒไธ€ไธชๅ›พ็š„box็š„image_id ไธๅ˜ใ€‚

convert qwen-7b-chat , failed

4 comment

When I run: python llm_export.py --type Qwen-7B-Chat --path /mnt/LLM_Data/Qwen-7B-Chat --export_split --export_token --export_mnn --onnx_path /mnt/LLM_Data/Qwen-7B-Chat-onnx --mnn_path /mnt/LLM_Data/Qwen-7B-Chat-mnn I got: Loading checkpoint shards: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:06

when install, I got error : AttributeError: 'dict' object has no attribute 'to_dict'

File "C:\Users\smart\anaconda3\Lib\site-packages\transformers\configuration_utils.py", line 572, in from_pretrained return cls.from_dict(config_dict, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\smart\anaconda3\Lib\site-packages\transformers\configuration_utils.py", line 771, in from_dict logger.info(f"Model config {config}") ^^^^^^^^ File "C:\Users\smart\anaconda3\Lib\site-packages\transformers\configuration_utils.py", line 803, in __repr__ return f"{self.__class__.__name__} {self.to_json_string()}" ^^^^^^^^^^^^^^^^^^^^^...