-
开发机：ubuntu 20.04 mnn 3.0.0
模型 huggingface：Qwen2.5-0.5B-Instruct 和 Qwen2.5-0.5B-Instruct-GPTQ-Int8
## 导出 onnx 模型
$ python mnn/transformers/llm/export/llmexport.py --path pretrained_model/Qwen2.5…
-
File "D:\faceswap\faceSwapper\run.py", line 6, in
from faceSwapper import create_app
File "D:\faceswap\faceSwapper\faceSwapper\__init__.py", line 4, in
from faceSwapper.apis.SwapperAP…
-
训练好的pointrend模型使用官方的额export_onnx.py导出onnx发现在np.testing.assert_allclose(onnx_out, paddle_out, rtol=0, atol=1e-03)报错，代码如下，也使用了paddle2onnx来导出模型实测发现精度不一致
def export_onnx(args):
args.config = '/workspa…
-
ERROR: Cannot install -r D:\ComfyUI-wenxi\custom_nodes\comfyui-mixlab-nodes\requirements.txt (line 33), inference-gpu and inference-gpu==0.25.0 because these package versions have conflicting dependen…
-
### Search before asking
- [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussion…
-
最终目的是想从您的代码中把SuperPoint和LightGlue两个功能抽离出来单独使用，修改后的代码：
[SP_LG.zip](https://github.com/user-attachments/files/17690124/SP_LG.zip)
SuperPoint已经可以正常推理并生成正确的关键点，LightGlue推理时崩溃。在Windows和Ubuntu上均崩溃：
![ima…
-
从https://hf-mirror.com/下载的模型 `./hfd.sh IDEA-CCNL/Taiyi-Stable-Diffusion-1B-Chinese-v0.1 --tool wget -x 6`.
使用 MNN/transformers/diffusion/export/onnx_export.py 转换出错：
```
[root@localhost export]$ pyt…
-
-
im trying convert model (cnn+lstm) from onnx to rknn for rk3588
My code:
shape = (1, 7, 3, 608, 184)
import numpy as np
img_means = (np.array((0.19007764876619865, 0.15170388157131237, 0.106594…
-
parser = trt.OnnxParser(network, trt_logger)
parse_valid = parser.parse_from_file(onnx_model)
When I used the above two lines of code to parse the onnx model path with Chinese, I kept reporting error…