Jin, Hyunwoo

# python demo/test_attr_predictor.py --input demo/imgs/attr_pred_demo1.jpg ```error Traceback (most recent call last): File "demo/test_attr_predictor.py", line 62, in main() File "demo/test_attr_predictor.py", line 38, in main cfg = Config.fromfile(args.config) File "/opt/conda/lib/python3.7/site-packages/mmcv/utils/config.py", line 341,...

change 32 line of prepare_in_shop.py ``` # labelf = open(os.path.join(PREFIX, 'list_attr_items.txt')).readlines() labelf = open(os.path.join(PREFIX, 'attributes/list_attr_items.txt')).readlines() ```

Can't approch to DataSet and PreTrained model.. Please approve the access

[http://data.csail.mit.edu/places/ADEchallenge/ADEChallengeData2016.zip](http://data.csail.mit.edu/places/ADEchallenge/ADEChallengeData2016.zip) pless..

FROM nvidia/cuda:11.0.3-cudnn8-runtime-ubuntu18.04 as base FROM base as base-amd64 FROM base-amd64 FROM pytorch/pytorch:1.7.1-cuda11.0-cudnn8-runtime RUN apt-get update RUN apt-get upgrade -y RUN apt-get install gcc -y RUN pip3 install cython --use-feature=2020-resolver RUN...

Could not find a version that satisfies the requirement mmfashion==0.4.0

1

ERROR: Could not find a version that satisfies the requirement mmfashion==0.4.0 (from -r requirements.txt (line 59)) (from versions: none) ERROR: No matching distribution found for mmfashion==0.4.0 (from -r requirements.txt (line...

Can't use graphonmy

4

Do you have a recommendation for parse image model?

ImportError: No module named 'upfirdn2d_plugin'

3

### Error message ``` warnings.warn('Failed to build CUDA kernels for upfirdn2d. Falling back to slow reference implementation. Details:\n\n' + traceback.format_exc()) Setting up PyTorch plugin "upfirdn2d_plugin"... Failed! /workspace/PASTA-GAN-plusplus/torch_utils/ops/upfirdn2d.py:34: UserWarning: Failed to...

/opt/conda/lib/python3.8/site-packages/torch/nn/functional.py:3103: UserWarning: The default behavior for interpolate/upsample with float scale_factor changed in 1.6.0 to align with other frameworks/libraries, and now uses scale_factor directly, instead of relying on the computed output...