-
From the paper:
"We first train both parts of the framework individually and use a pretrained ERFNet on Cityscapes [22] for our global network."
I was wondering how global and local networks are tra…
-
In the README you that that : "you can download the cityscapes scripts and use the conversor to generate trainIds from labelIds". How do I use this script to convert the data? Sorry I am new to this a…
-
I was trying to load the [pretrained model](https://drive.google.com/drive/folders/1U7dvH4sC85KRVuV19fRpaMzJjE-m3D9x?usp=sharing) as follows `torch.nn.DataParallel(densifier).cuda().load_state_dict(lo…
-
You've given a link to the TensorFlow implementation. So I was wondering if you have one in PyTorch as well.
-
Hi @cardwing , first I want to thank you for sharing your excellent work, it really helps!
I want to train erfnet-sad on my own data, but the number of lanes in my custom data varies a lot. So clearl…
-
Hi @wvangansbeke ,
Great work!
I downloaded the sample Tusimple dataset provided in the repo. It has only two folders namely images and groundtruth.
After this, I ran the code using below comma…
-
```
Init model: 'erfnet'
Number of parameters in model ERFNET is 2.063M
=> Start train set for EPOCH 1
0it [00:00, ?it/s]..\aten\src\ATen\native\cuda\LegacyDefinitions.cpp:70: UserWarning: mask…
eeyrw updated
4 years ago
-
Thanks for sharing your latest algorithm!
But I am confused about table 3 in your paper. The F1 measure of ERFNet is only 70.2, which is much lower than 73.1 as previously reported here:
https://g…
-
Can the ERFNet-CULane-PyTorch model be used to train TuSimple dataset?
-
作者您好！我想问下您在用ERFNet来训练CULane时是否用到了什么训练技巧，我在用ERFNet训练Tusimple数据集时，训练了60k，但结果总是不是很理想，训练集和测试集得出iou之间相差很大，训练集上iou达到0.96，但测试集只有0.47，我的学习速率和weight_decay这些参数设置都与您设置的一样