-
I want to convert a ERFNet modelto ONNX, so I write some code as follows.
(This model is from https://github.com/wvangansbeke/LaneDetection_End2End)
```
from torch.autograd import Variable
impor…
-
I am trying to run the inference code of ERFNet to generate the label masks but I am getting seg fault whenever I try to save the predictions. It randomly runs and then gives seg fault. There are tota…
-
I use Anaconda to install PyTorch 1.3 with python=3.7.4, opencv=3.1.
But when I run the test_erfnet.sh, it show messages like that
> Traceback (most recent call last):
File "test_erfnet.py", li…
-
@cardwing Hello，i find an interesting thing. In my own computer(1080ti 11G), I try to change different tensorflow such as 1.4, 1.7... and I also re-install cudu9, Nvidia driver and cudnn. I all get t…
-
why I run the test_erfnet.py ,it has no response，and no displaying error , , I check it ，its stuck in ` model = torch.nn.DataParallel(model, device_ids=range(args.gpus)).cuda()` .., , ,
-
After several experiments, I found the forward pass is very fast and only takes less than 10ms on my machine with 1060 Ti. But copying data from gpu to cpu is really time consuming, which costs more t…
-
May I ask how do you pretrain the ERFNet? Thanks!
-
Hello, Cardwing
I want to confirm if all your code shared, different directories ( ENet-BDD100K-Torch, ENet-Label-Torch, ENet-TuSimple-Torch, ERFNet-CULane-PyTorch, SCNN-Tensorflow ) means you tried …
-
The newly added code for the lane evaluation in CULane can fasten the evaluation process about 20 x. Just compile with make in `ERFNet-CULane-PyTorch/tools/lane_evaluation/` (make clean first). If you…
-
Thanks for your codes for lane detection. I wonder where the ERFNet pretrained model comes from or could you provide more details about pretraining setting?
In `train_erfnet.sh`, the image shape is…