-
1. SFE模块的unfold可以用如下模块代替，可以减少很多算子
```
import torch
import torch.nn as nn
class Unfold(nn.Module):
def __init__(self):
super().__init__()
kernel = torch.eye(3)
kerne…
-
c1.mlir:112:12: error: failed to legalize operation 'torch.operator' that was explicitly marked illegal
%109 = torch.operator "onnx.Clip"(%106, %107, %108) : (!torch.vtensor, !torch.vtensor, !torch.v…
-
### 在提问之前...
- [X] 我填写了简短且清晰明确的标题，以便开发者在翻阅 issue 列表时能快速确定大致问题。而不是“一个建议”、“卡住了”等
- [X] 我基本确定这是一个新功能/建议，而不是遇到了 bug（不确定的话请附上日志）
### 说说你遇到的问题？
目前的onnx模型是直接从torch或者paddle导出的，性能可能还不是最优
### 有什么好的想法？
使用ht…
-
1 请问pt转onnx的过程，我的命令是这样：
python export.py --weights weights/yolov7-face.pt --img 640 --batch 1 --grid --simplify
转出来的模型 存在“slice”结构。
2 由于1中转出来的模型存在这个"slice" 结构，导致转ncnn一直失败。
请问您转onnx的代码 是怎么样的
-
## Description
When I use your demo/Diffusion/demo_txt2img_xl.py for INT8 datatype inference, it reports an error:
Invoked with: %338 : Tensor = onnx::Constant(), scope: transformers.models.clip…
-
### Feature request
It is hoped that "transformers" will support the conversion of llava models to onnx form
### Motivation
Not supported during conversion of llava model to onnx form
### Your con…
-
我已经导出onnx 了,但是应该如何进行推理呢
-
### Search before asking
- [X] I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussions) and fou…
-
### Feature request
Hi, I've created a 4-bit quantized model using `BitsAndBytesConfig`, for example
```
from transformers import AutoModelForTokenClassification, BitsAndBytesConfig
from optim…
-
### First, confirm
- [X] I have read the [instruction](https://github.com/Gourieff/sd-webui-reactor/blob/main/README.md) carefully
- [X] I have searched the existing issues
- [X] I have updated the e…