-
the ERFNet trained model is invalid
Please provide another
Thanks!!!
-
hi, I use the ENET calculate_class_weighting.py generare the loss weight for my training.
and I find some problems.
First, the weight is：
0.0819
0.4754
0.1324
1.5224
1.5190
2.4730
8.1865
5…
-
why a tensor [2,16,104,485] , by Downsampleblock , some to be [2,48,52,243]. some to be [2,16,52,242] ,can't torch.cat ?
`output = torch.cat([self.conv(input), self.pool(input)], 1) .
RuntimeEr…
-
Hello, @sacmehta
Thank you for your impressive work.
However, I don't know how to measure the inference speed of the network properly.
I created the [1, 3, 512, 1024] size of input and tried to mea…
-
Hi， I have tried to submit my result for Car 3D instance. But it seems that the server is not responding to give the result feedback. Can we still evaluate our result on the platform?
-
I can't get .pth file from archive:"tar: This does not look like a tar archive". Can you check your files on google drive?
-
For Curve category, the F1 measure of ERFNet should be 66.3 instead of 71.6
https://github.com/cardwing/Codes-for-Lane-Detection
I ran the evaluation code on your trained model, and obtained exact…
-
```
[TensorRT] ERROR: Internal error: could not find any implementation for node (Unnamed Layer* 202) [Deconvolution], try increasing the workspace size with IBuilder::setMaxWorkspaceSize()
[TensorR…
-
Hi I have some questions regarding ERFNet.
Which dataset is used for pretraining ERFNet ? Seems weird ERFNet is so powerful than any other models :)
Thanks
-
Hello!
Nice looking library! I'd like to train mobilenetv2 for semantic segmentation using my coco-like dataset. I've copied the coco dataloader and updated things for my data.
But even though m…