GFPGAN-onnxruntime-demo

GFPGAN-onnxruntime-demo copied to clipboard

gfpgan onnx model giving bad results

1

I have used your script and converted gfpgan pth model into onnx model but I am getting horrible results. Like output image is same as input image (in terms of...

dummyuser-123

Batching

1

I will release a PR which supports the batching of the model via ONNX. I have a protoype working.

lschaupp

Any chance we can load the onnx model and run it into TensorRT

5

Such a great work. I am looking for quicker inference for GFPGAN. Is there any chance we can load the GFPGAN.onnx and run it on TensorRT? Looking forward to your...

nelsontseng0704

在GPU环境下，使用onnxruntime的时间和PyTorch基本是一致的。

1

在GPU环境下，使用onnxruntime的时间和PyTorch基本是一致的。

fanghaiquan1

我按照上述步骤成功将1.4和1.3版本的模型导出成onnx模型了，经过我测试，似乎只在输入的图像仅包含头部的时候效果最好。我有个想法，将一张全身照的图片的头部截下来，调整尺寸到512后运行得到生成的图像，再将图像调整回原来的尺寸后放会原来裁剪的位置，但这种方式会导致裁剪出的图像边缘有条纹，结果如下所示：**请问这种问题该如何解决**？    

lasifea

infer time

2

nice work! i run at 4090，the infer time is: 0.6s，a little long. Is this the normal effect?

chenkaiC4

Hi, is there any chance I can do batch inference with ONNX model, I notice the example is do single imge inference. Does the onnx model generated from torch2onnx.py support...

lognat0704

I have noted a quality decrease when comparing the results to GFPGAN 1.4 on Replicate. Any reasons why that could be happening?

lschaupp

Running Ubuntu 22.04 LTS I get the following error: `Traceback (most recent call last): File "/home/user/GFPGAN-onnxruntime-demo/torch2onnx.py", line 67, in ort_session = onnxruntime.InferenceSession(onnx_model_path) File "/home/user/miniconda3/envs/richard-roop/lib/python3.10/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 396, in __init__ raise e...

hashnag

great work 😊

TachibanaYoshino