Can't use this package in M1 chip Macbook Pro

[AtzeniMichele]

Hello! First of all thanks for this inspiring work.

I am trying to use your package in a Macbook PRO with M1 chip. However I am encountering an error running your example:

024-04-17 16:31:34.857785: I metal_plugin/src/device/metal_device.cc:1154] Metal device set to: Apple M1 Pro
2024-04-17 16:31:34.857806: I metal_plugin/src/device/metal_device.cc:296] systemMemory: 16.00 GB
2024-04-17 16:31:34.857811: I metal_plugin/src/device/metal_device.cc:313] maxCacheSize: 5.33 GB
2024-04-17 16:31:34.857944: I tensorflow/core/common_runtime/pluggable_device/pluggable_device_factory.cc:305] Could not identify NUMA node of platform GPU ID 0, defaulting to 0. Your kernel may not have been built with NUMA support.
2024-04-17 16:31:34.857958: I tensorflow/core/common_runtime/pluggable_device/pluggable_device_factory.cc:271] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 0 MB memory) -> physical PluggableDevice (device: 0, name: METAL, pci bus id: )
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type) ┃ Output Shape ┃ Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ mono_dense (MonoDense) │ (None, 128) │ 512 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ mono_dense_1 (MonoDense) │ (None, 128) │ 16,512 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ mono_dense_2 (MonoDense) │ (None, 1) │ 129 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
Total params: 17,153 (67.00 KB)
Trainable params: 17,153 (67.00 KB)
Non-trainable params: 0 (0.00 B)
Epoch 1/10
Traceback (most recent call last):
File "/Users/micheleatzeni/Desktop/TestPellisa/test.py", line 57, in
model.fit(
File "/Users/micheleatzeni/Desktop/Deepalas/TestPellisa/lib/python3.9/site-packages/keras/src/utils/traceback_utils.py", line 122, in error_handler
raise e.with_traceback(filtered_tb) from None
File "/Users/micheleatzeni/Desktop/Deepalas/TestPellisa/lib/python3.9/site-packages/airt/_components/mono_dense_layer.py", line 302, in call
with replace_kernel_using_monotonicity_indicator(
File "/Applications/Xcode.app/Contents/Developer/Library/Frameworks/Python3.framework/Versions/3.9/lib/python3.9/contextlib.py", line 117, in enter
return next(self.gen)
File "/Users/micheleatzeni/Desktop/Deepalas/TestPellisa/lib/python3.9/site-packages/airt/_components/mono_dense_layer.py", line 172, in replace_kernel_using_monotonicity_indicator
layer.kernel = apply_monotonicity_indicator_to_kernel(
AttributeError: Exception encountered when calling MonoDense.call().
can't set attribute
Arguments received by MonoDense.call():
• inputs=tf.Tensor(shape=(None, 3),
dtype=float32)>

Thanks for the help.