-
Hi,
I have a question about the graph (It's on 4.2 Semantic segmentation -- Results -- (a) ESPNet vs. ESPNetv2 (validation set)) on your ESPNetv2 paper.
There are 6 points in the graph, 3 is for E…
msson updated
5 years ago
-
In the paper 《DiCENet: Dimension-wise Convolutions for Efficient Networks》, the network width scaling parameter **s** can be selected, but in the experiment of **image multi-label classification**, th…
-
Hello,Thank you for your impressive work!
I know the training is followed by two steps.When I set the variable 'decoder' to 'True',there is a problem with '
> RuntimeError: input and target batch…
-
I trained the same ESPNetV2 on my GTX 1080 CUDA GPU for 10 class semantic segmentation. I did some modifications to code so it works for my 10 classes. Input image size was 640x480 I got an mIoU of 62…
-
https://github.com/sacmehta/ESPNetv2/blob/6c70184fb4cc4d64fac0f9ffb4b4f1a5b65c941f/segmentation/main.py#L209
The value of best_val always be 0 , which means that model_best.pth stores not the best, …
-
When I run the segmentation codes , i got this error!
It …
-
Thanks for the great work! And I also find that ESPNetv2 has comparable performance with MobileNet or ShuffleNet with even less FLOPS, but is the actual inference speed (images / sec) on ARM or CPU fa…
-
hi, when i run the segmentation with two classes ,i get the error as below:
-
Thank you for developing ESPNet!
I have three questions
・ About labels to be ignored
My own dataset has 11 classes except the background. And we assigned 255 labels to the background.
So in Data…
-
Hi,
I would like to train ESPNet model with my dataset from Cityscapes pretrained weights that you uploaded on /pretrained/encoder/ folder, not from scratch.
Could you please give some advice how …
msson updated
5 years ago