Hello, I see that Mapillary uses a remapping to 19 classes,

https://github.com/NVlabs/SegFormer/blob/3561d14362abe60675755ee00d266308e4e3015e/mmseg/datasets/pipelines/transforms.py#L1025

Does this mean the experiments done in the paper uses 19 classes for all methods on Mapilary?

Hello How are you? Thanks for contributing to this project. It is difficult for us to use this project because it contains many other scripts. Did u check https://github.com/lucidrains/segformer-pytorch which is a third-party implementation for SegFormer? This project contains ONLY a simple segformer network class so it is easy to use. But the number of params of MiT-B0 network by this implementation is 7M. I know that the number of params of MiT-B0 is 3.6M in the paper. Could u check https://github.com/lucidrains/segformer-pytorch shortly? If it is difficult, could u make the SegFormer network class like the above implementation? Thanks

It's a great honor for me to study your reserch, when i download the pretrained model into pretrained directory . It shows as follows, hope you can give me some advice. Thanks for your time and kindness.

The Swin transformer release a large model pretrained on ImageNet-22K for semantic segmentation and achieved a good result. I wonder if you are interested in improving segformer in a similar way? Thanks!

Hello How are you? Thanks for contributing to this project. Which device did u test your models on?

You did NOT explain the device specification in the paper.

Hi, I'm trying to reproduce SegFormer on PASCAL VOC dataset. When using the codes of this repo, I could get ~77% mIoU (without multi-scale test). However, I only got ~75% mIoU with my reproduced code. Here are my training details.

I have reproduced the training and validation data pipeline, including random scaling , random horizontal flipping , and random cropping, etc. For the model, I used the code of this repo and the pre-trained weights. I also used an AdamW optimizer with a warmup scheduler. The other optimizer settings are set as the same with this repo.

Therefore, I'm wondering if there are any extra training details in SegFormer or mmseg itself. I'll very appreciate for your reply.

Hi,

I would like to ask a question about the efficient attention module, please: I see that you use a reduction ratio R to descrease the spatial size of input sequences, normally this operation will produce a output sequence of spatial size N/R. But according to your Table.6 it doesn't, the output spatial size is still N. I would like to ask where do you upsample your sequence spatial size from N/R back to N in the attention module after the reduced QKV multiplication?

Thank you!

I met a problem when training on Mapillary and evaluating on cityscapes. The class "wall" miou=0.0. Could you please provide the training log of Mapillary pretrain and eval？(prefer Model B2) Thanks a lot!

+---------------+-------+-------+
|     Class     |  IoU  |  Acc  |
+---------------+-------+-------+
|      road     | 96.93 | 98.09 |
|    sidewalk   | 76.57 | 90.46 |
|    building   | 89.02 | 95.67 |
|      wall     |  0.0  |  0.0  |
|     fence     | 35.52 | 59.93 |
|      pole     | 52.85 | 63.03 |
| traffic light | 59.63 | 71.81 |
|  traffic sign | 68.11 | 77.09 |
|   vegetation  | 89.89 | 96.67 |
|    terrain    |  26.0 |  26.5 |
|      sky      | 90.97 | 93.58 |
|     person    | 72.78 | 87.27 |
|     rider     | 33.21 |  41.0 |
|      car      | 91.25 | 97.25 |
|     truck     |  61.8 | 64.37 |
|      bus      | 66.93 | 71.56 |
|     train     | 62.85 | 65.31 |
|   motorcycle  | 47.68 | 65.62 |
|    bicycle    | 67.57 | 74.03 |
+---------------+-------+-------+
2021-06-21 16:06:43,150 - mmseg - INFO - Summary:
2021-06-21 16:06:43,150 - mmseg - INFO - 
+-------+-------+-------+
|  aAcc |  mIoU |  mAcc |
+-------+-------+-------+
| 93.66 | 62.61 | 70.49 |
+-------+-------+-------+

Hi,

I hava a similar error to #2. I've just forked the repo to add a print statement, so fix #1 is included. When running python tools/test.py, I'm getting the following:

Traceback (most recent call last):
  File "/usr/local/lib/python3.7/dist-packages/mmcv/utils/registry.py", line 51, in build_from_cfg
    return obj_cls(**args)
  File "/usr/local/lib/python3.7/dist-packages/mmseg/datasets/pipelines/test_time_aug.py", line 59, in __init__
    self.transforms = Compose(transforms)
  File "/usr/local/lib/python3.7/dist-packages/mmseg/datasets/pipelines/compose.py", line 22, in __init__
    transform = build_from_cfg(transform, PIPELINES)
  File "/usr/local/lib/python3.7/dist-packages/mmcv/utils/registry.py", line 44, in build_from_cfg
    f'{obj_type} is not in the {registry.name} registry')
KeyError: 'AlignedResize is not in the pipeline registry'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/usr/local/lib/python3.7/dist-packages/mmcv/utils/registry.py", line 51, in build_from_cfg
    return obj_cls(**args)
  File "/usr/local/lib/python3.7/dist-packages/mmseg/datasets/ade.py", line 91, in __init__
    **kwargs)
  File "/usr/local/lib/python3.7/dist-packages/mmseg/datasets/custom.py", line 88, in __init__
    self.pipeline = Compose(pipeline)
  File "/usr/local/lib/python3.7/dist-packages/mmseg/datasets/pipelines/compose.py", line 22, in __init__
    transform = build_from_cfg(transform, PIPELINES)
  File "/usr/local/lib/python3.7/dist-packages/mmcv/utils/registry.py", line 54, in build_from_cfg
    raise type(e)(f'{obj_cls.__name__}: {e}')
KeyError: "MultiScaleFlipAug: 'AlignedResize is not in the pipeline registry'"

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "tools/test.py", line 170, in <module>
    main()
  File "tools/test.py", line 122, in main
    dataset = build_dataset(cfg.data.test)
  File "/usr/local/lib/python3.7/dist-packages/mmseg/datasets/builder.py", line 73, in build_dataset
    dataset = build_from_cfg(cfg, DATASETS, default_args)
  File "/usr/local/lib/python3.7/dist-packages/mmcv/utils/registry.py", line 54, in build_from_cfg
    raise type(e)(f'{obj_cls.__name__}: {e}')
KeyError: 'ADE20KDataset: "MultiScaleFlipAug: \'AlignedResize is not in the pipeline registry\'"'

I've made a Google Colab to reproduce: https://colab.research.google.com/drive/1-t_lj5K2ZEFemxn88DSfcy9W7RTvklsz?usp=sharing

hi thanks for your great repo

I have no idea why but it seems to import mmseg not from local module but from installed one and it keeps shows me this error

No module named 'mmseg'

When I run pycharm as debugging mode, than it works all fine... only when I try to run it with terminal or run mode...

any help will be very appreciated

Hi, first of all, thank you for your research and code.

I see that during training, the model is saved every 4000 iterations. Where can I change this spec, such that my model is saved every, lets say, 1000 iterations?

Thank you

For robot implementation, we need onnx or openvino version of segformer, but currently, I found that segformer is not to to be converted to those versions, Does anyone can help us to find the reason or share your successful examples, thank you!

Hi,

I am working on a task of semantic segmentation. I am facing issue in generation of data in the required format. Can anyone help me with free tools that I can use to generate the data?

Patching CVE-2007-4559

Hi, we are security researchers from the Advanced Research Center at Trellix. We have began a campaign to patch a widespread bug named CVE-2007-4559. CVE-2007-4559 is a 15 year old bug in the Python tarfile package. By using extract() or extractall() on a tarfile object without sanitizing input, a maliciously crafted .tar file could perform a directory path traversal attack. We found at least one unsantized extractall() in your codebase and are providing a patch for you via pull request. The patch essentially checks to see if all tarfile members will be extracted safely and throws an exception otherwise. We encourage you to use this patch or your own solution to secure against CVE-2007-4559. Further technical information about the vulnerability can be found in this blog.

If you have further questions you may contact us through this projects lead researcher Kasimir Schulz.

I found it diffcult to understand this two file. #1 local_configs/base/models/segformer.py #2 local_configs/base/models/segformer.py I knew that #1 means the base of #2, but I find the code in file 2: "backbone = dict(type= ‘mit_b0’)",
and the other code in file 1: "backbone = dict(type= ‘IMTRv21_5’)",

I wonder what does "type = IMTRv21_5" mean? Please Guide me!