BiSeNet

BiSeNet copied to clipboard

How to implement the BiSeNetV2 large?

1

Hi, Thanks a lot for sharing your code. I want to ask you if you know how the BiSeNetV2 large is implemented. In the paper, it mentions that BiSeNetV2 large...

Kevinpsk

images in kitti dataset cannot match

2

I want to implement the algorithm in kitti dataset. But it shows that the codes cannot match kitti dataset's images' size. CUDA_VISIBLE_DEVICES=0 python3 demo.py --ckpt res/model_final.pth --img_path ./2.png Traceback (most...

Shelfcol

inference time

3

Could anyone kindly share the inference time of this inplementation and the corresponding gpu used? Thanks a lot!

turboxin

Thanks for your great work. Is it possible to release the training log together with the pretrained weights? That would be easier for further comparison.

jzkay12

The authors report achieving an average IoU of 72.6% on the Cityscapes test set and 156 FPS on an NVIDIA GeForce GTX 1080Ti card. But on my laptop NVIDIA GeForce...

Datou98

I'm very confused that the GELayerS1 in paper is conv(out_chan=6in_chan)-->DW(out_chan=in_chan)-->...，but the block in code is conv(out_chan=in_chan)-->DW(out_chan=6in_chan)-->.... Is this still a DW? As far as I know that the out_channel of...

spirit-icer

Infer with one single image question

4

I use the model_final_v2_ade20k.pth that you provided, using the command: python tools/export_onnx.py --config configs/bisenetv2_city.py --weight-path /home/datou/BiSeNet/BiSeNet-master/model/model_final_v2_city.pth --outpath ./model_v2_city.onnx --aux-mode eval Convert pth to onnx and use the command： ./segment complie...

Datou98

internal error

11

 Hello, I would like to ask how to solve this problem, about Tensorrt versions ?

Datou98

onnx to tensorrt : Assertion failed: scales.is_weights() && "Resize scales must be an initializer!"

5

Here is the error log  Here is my environment cuda 11.6 TensorRT 8.2.3.0 ONNX 1.12 ONNXRuntime 1.8.1 Do you have any advice? Thanks in advance

yuzhj

train question

15

Hello@CoinCheung! I train this code but I have some questions, As follows: In base_dataset.py, when reading the label, why did you set the mode=0? def get_image(self, impth, lbpth): img =...

miscedence12