• State TI Thinks Resolved
  • Locked Locked
  • Replies 3 replies
  • Answers 2 answers
  • Subscribers 99 subscribers
  • Views 429 views
  • Users 0 members are here
Support feedback
Options
Options
Related

This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

TDA4VM: TDA4 - TIDL segmentation training error

Rio Chan
Genius 14865 points
Part Number: TDA4VM

https://git.ti.com/cgit/jacinto-ai/pytorch-jacinto-ai-devkit/about/docs/Semantic_Segmentation.md

Hi CHamps:

I'm studying this link as the above.

While issuing this cmd:

python3 ./scripts/train_segmentation_main.py --model_name deeplabv3lite_mobilenetv2_tv --dataset_name cityscapes_segmentation --data_path ./data/datasets/cityscapes/data --img_resize 384 768 --output_size 1024 2048 --pretrained download.pytorch.org/.../mobilenet_v2-b0353104.pth --gpus 0 1

My ubuntu 18.04 will give me this error as the below, how to fix it?

=> will save everything to ./data/checkpoints/cityscapes_segmentation/2021-04-07_21-26-32_cityscapes_segmentation_deeplabv3lite_mobilenetv2_tv_resize768x384_traincrop768x384/training
=> fetching images in './data/datasets/cityscapes/data'
Traceback (most recent call last):
File "./scripts/train_segmentation_main.py", line 163, in <module>
train_pixel2pixel.main(args)
File "/opt/TDA4_Jacinto_AI_devkit_stuffs/pytorch-jacinto-ai-devkit/modules/pytorch_jacinto_ai/engine/train_pixel2pixel.py", line 279, in main
train_dataset, val_dataset = xvision.datasets.pixel2pixel.__dict__[args.dataset_name](args.dataset_config, args.data_path, split=split_arg, transforms=transforms)
File "/opt/TDA4_Jacinto_AI_devkit_stuffs/pytorch-jacinto-ai-devkit/modules/pytorch_jacinto_ai/xvision/datasets/pixel2pixel/cityscapes_plus.py", line 431, in cityscapes_segmentation
*args, **kwargs)
File "/opt/TDA4_Jacinto_AI_devkit_stuffs/pytorch-jacinto-ai-devkit/modules/pytorch_jacinto_ai/xvision/datasets/pixel2pixel/cityscapes_plus.py", line 234, in __init__
raise Exception("> No files for split=[%s] found in %s" % (split, self.segmentation_base))
Exception: > No files for split=[train] found in ./data/datasets/cityscapes/data/gtFine/train

ps. I'm using Python3 to issue this cmd.

BR Rio

  • 0
    TI__Genius 11466 points

    Hi Rio,

    Cityscapes dataset cannot be automatically downloaded. You have to manually download and make it available at the location mentioned in the error message.

    Best regards,

    Manu

  • 0 in reply to Manu Mathew
    TI__Genius 14865 points

    Hi Manu:

    THanks for your helping.

    I have downloaded the CityScapes manually.

    Now, I'm issuing this cmd and have the below error log as the below:

    python3 ./scripts/train_segmentation_main.py --dataset_name cityscapes_segmentation --model_name fpnlite_pixel2pixel_aspp_regnetx800mf --data_path ./data/datasets/cityscapes/data --img_resize 384 768 --output_size 1024 2048 --gpus 0 1 --pretrained https://dl.fbaipublicfiles.com/pycls/dds_baselines/160906036/RegNetX-800MF_dds_8gpu.pyth

    May you guide me how to solve it?

    THanks.

    BR Rio

    /usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:2973: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.
    "See the documentation of nn.Upsample for details.".format(mode))
    => Size = [384, 768], GFLOPs = 14.572910592, GMACs = 7.286455296
    /usr/local/lib/python3.7/dist-packages/torch/onnx/symbolic_helper.py:243: UserWarning: You are trying to export the model with onnx:Upsample for ONNX opset version 9. This operator might cause results to not match the expected results by PyTorch.
    ONNX's Upsample/Resize operator did not match Pytorch's Interpolation until opset 11. Attributes to determine how to transform the input were added in onnx:Resize in opset 11 to support Pytorch's behavior (like coordinate_transformation_mode and nearest_mode).
    We recommend using opset 11 and above for models using this operator.
    "" + str(_export_onnx_opset_version) + ". "
    Traceback (most recent call last):
    File "./scripts/train_segmentation_main.py", line 163, in <module>
    train_pixel2pixel.main(args)
    File "/opt/TDA4_Jacinto_AI_devkit_stuffs/pytorch-jacinto-ai-devkit/modules/pytorch_jacinto_ai/engine/train_pixel2pixel.py", line 420, in main
    model = model.cuda()
    File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 307, in cuda
    return self._apply(lambda t: t.cuda(device))
    File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 203, in _apply
    module._apply(fn)
    File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 203, in _apply
    module._apply(fn)
    File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 203, in _apply
    module._apply(fn)
    [Previous line repeated 2 more times]
    File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 225, in _apply
    param_applied = fn(param)
    File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 307, in <lambda>
    return self._apply(lambda t: t.cuda(device))
    File "/usr/local/lib/python3.7/dist-packages/torch/cuda/__init__.py", line 149, in _lazy_init
    _check_driver()
    File "/usr/local/lib/python3.7/dist-packages/torch/cuda/__init__.py", line 47, in _check_driver
    raise AssertionError("Torch not compiled with CUDA enabled")
    AssertionError: Torch not compiled with CUDA enabled

  • 0 in reply to Rio Chan
    TI__Genius 11466 points

    That's because you have installed CPU version of PyTorch. Please install the GPU version of PyTorch and also run on machines with GPUs.