Xia Meng

How to train it well?

1

I use train.py to run about 300 epoch, other settings are also default(CamVid, FC-DenseNet56). But when i use the model to predict a image, its performance is very bad. Then...

how to use gpu?

3

I have refered to some similar issues but they do not help. I changed "/cpu:0" to "gpu:0", and run train.py, several lines of message show up like below, which doesn't...

mIOU and acc looks normal at first thousands of epoch but all become 0 after like 80000 epoch

3

I tried segformer b0, b0-tiny, b1 to train several custom dataset(different purpose using different model on different datasets). All have a problem. At the first several epoch, for example, 20000...

trainning error when using segmenter

5

I meet the simular problem like #1351 (maybe...). I have two classes and i set the num_classes as 3. with pixel label from 0 to 2. It worked well on...

what is the gpu memory needed by the h model

10

cuda out of memory 3060 8g

RuntimeError: operation does not have an identity

8

I meet it when i try to train lstr. Loading targets into memory... 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2037/2037 [00:01

read mask error? only batches of spatial targets supported (3D tensors) but got targets of size: : [1, 360, 640, 3]

5

the error is below: **RuntimeError: only batches of spatial targets supported (3D tensors) but got targets of size: : [1, 360, 640, 3]** I think it is because the dataloader...

using branch deploy, c++ version on xavier become worse

6

I am using branch deploy, I get the .so of the unsupport ops, and the python scripts work fine. Nearly the same. I moved to xaiver(aarch64), and generate the onnx...