guillherms/human-activity-pose_v4
Viewer β’ Updated β’ 920 β’ 24 β’ 1
How to use guillherms/human-activity-pose-models with Keras:
# !pip install -U keras tensorflow huggingface_hub
# Keras needs TensorFlow installed to read "hf://" paths, so the tensorflow backend is selected here;
# "jax" and "torch" also work for computation once TensorFlow is installed.
import os
os.environ["KERAS_BACKEND"] = "tensorflow"
import keras
model = keras.saving.load_model("hf://guillherms/human-activity-pose-models")
This model classifies human activities (reading, waving, office work, etc.) using pose landmarks extracted from MediaPipe Pose.
mlp_pose.h5: Trained Keras modellabel_encoder.pkl: Encodes activity labelsCreated by Guilherme Santos