-
Where is the distillation loss reflected in your code？
The total is : loss_tot = loss + loss_exist * 0.1. I fail to find the distillation loss.
in https://github.com/cardwing/Codes-for-Lane-Detecti…
-
Hello,
I have been trying to train ERF_Net on CULane and I have encountered some issues:
first of all, I change the parameters image_height and width to half the original value.
here is my t…
-
I want to get the result segmented to the vehicle in the final result,
so I want to re-learn using erfnet_model_sim3d_7class.tar.
All dataset paths were checked, and the pytorch version and CUDA …
-
Traceback (most recent call last):
File "e:/master/master1/RSISS/mmcv/mmsegmentation/ceshi.py", line 1, in
from mmseg.apis import inference_segmentor, init_segmentor
File "e:\master\master…
-
What weights[0] refers to?
In the train_erfnet.py:
weights = [1.0 for _ in range(5)]
weights[0] = 0.4
Thank you.
-
Hi
When u try to run python3 test_erfnet.py I get the following error:
```
`Traceback (most recent call last):
File "test_erfnet.py", line 5, in
import torchvision
File "/usr/local/…
-
I use the erfnet code.
What should I do if I want to detect no less than four lanes?
-
Traceback (most recent call last):
File "yolo2trt.py", line 22, in
model_trt = torch2trt(net, [x])
File "/opt/miniconda3/envs/tensorrt/lib/python3.7/site-packages/torch2trt-0.1.0-py3.7.egg…
-
Hi,
The training miou is always around 0.44 for TuSimple dataset. There is no any improvement after adjusting the learning rate, learning rate decay, momentum, weight decay...
Any advice? Than…
-
Hi, I have one question regarding to the CULane evaluation method. My thought may be not correct, but please read it and give me some suggestions if possible, thank you.
- In CULane, different ima…