Hongyu, Chiu

I also faced the duplicated logs and I fixed by following: ```python # logconfig_dict: remove handlers of root logconfig_dict = dict( version=1, disable_existing_loggers=False, root={'level': 'INFO', 'handlers': []}, formatters={ 'generic': {...

Hi @VC86, Thank you for your fast and informative reply! May I ask further for the `Normals Estimation Block`? I try to build it like this: ```python import numpy as...

Thanks again for your reply! From the information that you said you convert to millimeter before normals computing, I modified the code as following: ```python import h5py import numpy as...

I met the same issue and ended up replacing MobileNetV3-Small with EfficientNet-lite0 which fully supports PTQ and QAT. (Also I saw big quantization error from SE blocks of MoblieNetV3-Small) https://www.tensorflow.org/lite/api_docs/python/tflite_model_maker/image_classifier/EfficientNetLite0Spec

I met the same problem and I solved it by slightly modifying the original metis wrapper to support the lastest networkx. You can check my repo: https://github.com/james77777778/metis_python

> We could add another case that looks something like `((6, 7), None)` and that would lead to this case being covered for our runs with larger `JAX_NUM_GENERATED_CASES`. What do...

> Last thing: could you please squash the changes into a single commit? See https://jax.readthedocs.io/en/latest/contributing.html#single-change-commits-and-pull-requests. Thanks! It should be a one-commit PR right now. Thanks for the tip.

Kindly ping @jakevdp Is there any unresolved issue? Happy to update.

Hi @lxzheng You should use the new API (`keras.Model.export`) introduced in Keras 3 A working example: ```python import tensorflow as tf import keras (train_images, train_labels), ( test_images, test_labels, ) =...

I believe this is the limitation of tensorflow, as it cannot directly perform `sqrt` on `int32` tensor. Workaround: ```python from keras_core import ops print(ops.arange(10).dtype) # # method 1: cast before...