Input shape incompatibility

[Jacopown]

I'm running the script on a perfectly functioning conda env. I'm on a macbook pro M1.
This winter i've used this tool frequently and never had any problem, after a full reset of my laptop the tool si giving me this error:

Traceback (most recent call last):
  File "/Users/jacopown/Applications/simple-ehm/simple_ehm-runnable.py", line 455, in <module>
    analyze_track(model, waveform, sample_rate)
  File "/Users/jacopown/Applications/simple-ehm/simple_ehm-runnable.py", line 136, in timed
    output = f(*args, **kw)
  File "/Users/jacopown/Applications/simple-ehm/simple_ehm-runnable.py", line 296, in analyze_track
    prediction = model(spectrogram)
  File "/opt/homebrew/Caskroom/miniconda/base/envs/tf/lib/python3.9/site-packages/keras/utils/traceback_utils.py", line 67, in error_handler
    raise e.with_traceback(filtered_tb) from None
  File "/opt/homebrew/Caskroom/miniconda/base/envs/tf/lib/python3.9/site-packages/keras/engine/input_spec.py", line 264, in assert_input_compatibility
    raise ValueError(f'Input {input_index} of layer "{layer_name}" is '
ValueError: Input 0 of layer "sequential" is incompatible with the layer: expected shape=(None, 124, 129, 1), found shape=(1, 125, 129)
Exception ignored in: <function tqdm.__del__ at 0x150ac0a60>
Traceback (most recent call last):
  File "/opt/homebrew/Caskroom/miniconda/base/envs/tf/lib/python3.9/site-packages/tqdm/std.py", line 1162, in __del__
  File "/opt/homebrew/Caskroom/miniconda/base/envs/tf/lib/python3.9/site-packages/tqdm/std.py", line 1304, in close
  File "/opt/homebrew/Caskroom/miniconda/base/envs/tf/lib/python3.9/site-packages/tqdm/std.py", line 1301, in fp_write
TypeError: 'NoneType' object is not callable

Simply running the command as:

python3 simple_ehm-runnable.py <filename.mp4>

I don't know if it's useful:
python = 3.9.13
conda = 4.13.0
tensorflow-macos = 2.9.2
tensorflow-metal = 0.5.0

[gcarlino97]

hello, i have a similar problem, macbook air m1.
has anyone been able to solve it?

/opt/homebrew/Caskroom/miniforge/base/lib/python3.9/site-packages/scipy/__init__.py:146: UserWarning: A NumPy version >=1.16.5 and <1.23.0 is required for this version of SciPy (detected version 1.24.2
  warnings.warn(f"A NumPy version >={np_minversion} and <{np_maxversion}"
WARNING:tensorflow:SavedModel saved prior to TF 2.5 detected when loading Keras model. Please ensure that you are saving the model with model.save() or tf.keras.models.save_model(), *NOT* tf.saved_model.save(). To confirm, there should be a file named "keras_metadata.pb" in the SavedModel directory.
Metal device set to: Apple M1

systemMemory: 8.00 GB
maxCacheSize: 2.67 GB

extracting audio track...
analyzing track...
  0%|                                                                                                                                                                         | 0/2320000 [00:00<?, ?it/s]
Traceback (most recent call last):
  File "/Users/gc/Documents/gitApp/simple-ehm/simple_ehm-runnable.py", line 314, in <module>
    analyze_track(model, waveform, sample_rate)
  File "/Users/gc/Documents/gitApp/simple-ehm/simple_ehm-runnable.py", line 92, in timed
    output = f(*args, **kw)
  File "/Users/gc/Documents/gitApp/simple-ehm/simple_ehm-runnable.py", line 189, in analyze_track
    prediction = model(spectrogram)
  File "/opt/homebrew/Caskroom/miniforge/base/lib/python3.9/site-packages/keras/utils/traceback_utils.py", line 70, in error_handler
    raise e.with_traceback(filtered_tb) from None
  File "/opt/homebrew/Caskroom/miniforge/base/lib/python3.9/site-packages/keras/engine/input_spec.py", line 298, in assert_input_compatibility
    raise ValueError(
ValueError: Input 0 of layer "sequential" is incompatible with the layer: expected shape=(None, 124, 129, 1), found shape=(1, 125, 129)
  0%|▌ 

[XSparter]

Hi, try now.
I think we have fixed the issues with tensor flow.