yolox importerror FasterRCNNBoxDecode

Issue Type

Bug

Source

pip (model-compression-toolkit)

MCT Version

2.2

OS Platform and Distribution

google colab

Python version

3.10

Describe the issue

running yolox on colab tutorials/notebooks/imx500_notebooks/pytorch/pytorch_yolox-tiny_for_imx500.ipynb

guess that newer (dev) version sony-custom-layers is required

error at
from tutorials.mct_model_garden.models_pytorch.yolox.yolox import YOLOX

--2024-10-22 12:02:43--  https://github.com/Megvii-BaseDetection/YOLOX/releases/download/0.1.1rc0/yolox_tiny.pth
Resolving github.com (github.com)... 20.205.243.166
Connecting to github.com (github.com)|20.205.243.166|:443... connected.
HTTP request sent, awaiting response... 302 Found
Location: https://objects.githubusercontent.com/github-production-release-asset-2e65be/386811486/cbf58ed8-49c4-401f-9764-93f785c6eade?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=releaseassetproduction%2F20241022%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20241022T120243Z&X-Amz-Expires=300&X-Amz-Signature=e1d4e63ba513e1646dc4bea9fbbd55dfdb739c8c043ca0930281185ca962ec10&X-Amz-SignedHeaders=host&response-content-disposition=attachment%3B%20filename%3Dyolox_tiny.pth&response-content-type=application%2Foctet-stream [following]
--2024-10-22 12:02:43--  https://objects.githubusercontent.com/github-production-release-asset-2e65be/386811486/cbf58ed8-49c4-401f-9764-93f785c6eade?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=releaseassetproduction%2F20241022%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20241022T120243Z&X-Amz-Expires=300&X-Amz-Signature=e1d4e63ba513e1646dc4bea9fbbd55dfdb739c8c043ca0930281185ca962ec10&X-Amz-SignedHeaders=host&response-content-disposition=attachment%3B%20filename%3Dyolox_tiny.pth&response-content-type=application%2Foctet-stream
Resolving objects.githubusercontent.com (objects.githubusercontent.com)... 185.199.108.133, 185.199.109.133, 185.199.110.133, ...
Connecting to objects.githubusercontent.com (objects.githubusercontent.com)|185.199.108.133|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 40755013 (39M) [application/octet-stream]
Saving to: ‘yolox_tiny.pth’

yolox_tiny.pth      100%[===================>]  38.87M  41.3MB/s    in 0.9s    

2024-10-22 12:02:46 (41.3 MB/s) - ‘yolox_tiny.pth’ saved [40755013/40755013]

/usr/local/lib/python3.10/dist-packages/sony_custom_layers/pytorch/object_detection/nms.py:120: FutureWarning: `torch.library.impl_abstract` was renamed to `torch.library.register_fake`. Please use that instead; we will remove `torch.library.impl_abstract` in a future version of PyTorch.
  @torch.library.impl_abstract(MULTICLASS_NMS_TORCH_OP_QUALNAME)
---------------------------------------------------------------------------
ImportError                               Traceback (most recent call last)
[<ipython-input-4-39a3ff4fff99>](https://localhost:8080/#) in <cell line: 4>()
      2 get_ipython().system('wget -nc https://github.com/Megvii-BaseDetection/YOLOX/releases/download/0.1.1rc0/yolox_tiny.pth')
      3 
----> 4 from tutorials.mct_model_garden.models_pytorch.yolox.yolox import YOLOX
      5 import yaml
      6 

[/content/tutorials/mct_model_garden/models_pytorch/yolox/yolox.py](https://localhost:8080/#) in <module>
     36 from model_compression_toolkit.core.pytorch.pytorch_device_config import get_working_device
     37 from .darknet import CSPDarknet, CSPLayer, BaseConv, DWConv
---> 38 from sony_custom_layers.pytorch import multiclass_nms, FasterRCNNBoxDecode
     39 
     40 

ImportError: cannot import name 'FasterRCNNBoxDecode' from 'sony_custom_layers.pytorch' (/usr/local/lib/python3.10/dist-packages/sony_custom_layers/pytorch/__init__.py)

Expected behaviour

No response

Code to reproduce the issue

see above

Log output