Spaces:

keras-io

/

what-convnets-learn

like 3

Build error

I selected

1. ResNet50V2
2. input_1
3. All filters

I got following error

File "/home/user/.local/lib/python3.8/site-packages/streamlit/scriptrunner/script_runner.py", line 475, in _run_script
    exec(code, module.__dict__)
File "/home/user/app/app.py", line 144, in <module>
    main()
File "/home/user/app/app.py", line 120, in main
    loss, img = visualize_filter(
File "/home/user/app/app.py", line 45, in visualize_filter
    loss, img = gradient_ascent_step(
File "/home/user/.local/lib/python3.8/site-packages/tensorflow/python/util/traceback_utils.py", line 153, in error_handler
    raise e.with_traceback(filtered_tb) from None
File "/tmp/__autograph_generated_filev1j33asp.py", line 12, in tf__gradient_ascent_step
    loss = ag__.converted_call(ag__.ld(compute_loss), (ag__.ld(feature_extractor), ag__.ld(img), ag__.ld(filter_index)), None, fscope)
File "/tmp/__autograph_generated_file4bztrcts.py", line 11, in tf__compute_loss
    filter_activation = ag__.ld(activation)[:, 2:(- 2), 2:(- 2), ag__.ld(filter_index)]