BiRefNet

BiRefNet copied to clipboard

Any information on compared with MVANet?

4

What's your superiority compared with the work [Multi-view Aggregation Network for Dichotomous Image Segmentation]?

wang21jun

使用resnet50作为backbone时候提示形状不匹配

1

x4 = self.squeeze_module(x4)： RuntimeError: Given groups=1, weight of size [64, 3712, 3, 3], expected input[4, 1856, 128, 128] to have 3712 channels, but got 1856 channels instea

wangwuwu

Guiding what to segment

18

Hi ! Firstly amazing work ! Not really an issue but more a question. By reading the white paper, I am not sure if you can choose what to segment...

hbardak

inference speed extremely slow

4

Hello, The inference speed is extremely slow. I am doing the inference with GPU, but its the same i am doing with u2net and ths speed there is 12x faster....

razvypp

Finetuning with small dataset

15

First of all, thank you for your great project. I want to ask you for some recommendation about finetuning with a small dataset (Around 400 images), my problem is main...

LeDuySon

CoreML model

7

Hey ZhengPeng, I'm interested in helping you to convert this model to CoreML, so it can run on Apple device locally. I'm planning to take a look in late August...

ynie

So many models

3

Hey @ZhengPeng7 I have been busy not been able to keep up with your progress I see many models on the drive ( stuff ) which is the best ones...

rishabh063

Onnx accuracy

3

Hi, First of all thanks for developing this and making them available for the community. I've downloaded the onnx models and i found they are not as accurate as the...

jtsanborn1

Feature: Onnx Export

8

Do you plan to build an Onnx export? I like deploying models with Onnx to reduce dependencies and use the model in C++.

schirrmacher

Model Zoo - general use is matting or segment?

4

Great work! I noticed that the "general use task" model in model zoo use many matting dataset for training, such as TR-P3M-10k. The GT mask value is between [0,1]. So...

sandy-ssdut