Add HF Spaces YAML frontmatter to README.md

update: experimentV2

Remove MobileNetV3 monkey-patch, proceed with 5/7 models

Fix: scope Layer.__call__ patch to only activate during load_model

Fix: smarter Layer.__call__ patch — convert floats + fallback list wrap

Fix: use enable_unsafe_deserialization for MobileNetV3 loading

Fix: use tf.constant instead of keras.backend.convert_to_tensor

Fix: monkey-patch Layer.__call__ for MobileNetV3 hard_swish compat

Fix: use TF 2.16.2 + Keras 3.3.3 — pre-hard_swish regression

Fix: load MobileNetV3 weights via h5py to handle layer count mismatch

Fix: rebuild MobileNetV3 architecture + load weights to bypass hard_swish bug

Fix: pin keras==3.8.0 to avoid MobileNetV3 hard_swish regression in 3.12

Fix: add custom_objects compat layer to handle quantization_config from newer Keras

Fix: bump keras>=3.8.0 to match model quantization_config format

Fix: bump tensorflow to 2.18.0 for Keras 3 model compatibility

Fix: add compile=False to load_model, capture load errors in /debug

Add /debug endpoint to diagnose model loading issue

Fix TensorFlow API usage: replace tf.h5 with tf.keras

Merge remote-tracking branch 'origin/main'

Add Hugging Face Spaces YAML metadata to README

Delete measure_latency.py

Merge branch 'main' of https://huggingface.co/spaces/wisamWR/latency-experiment

Initial commit for Hugging Face latency experiment

initial commit