Optic-flow-CNNs-MLPs-15x15
Collection
CNNs and MLPs trained on ~6k 15x15 optic flow patterns generated by uniformly sampled combinations of translation (T) and rotation (R). • 12 items • Updated
How to use OWLab/Optic-flow-CNN-LeakyReLU-15x15 with Keras:
# Available backend options are: "jax", "torch", "tensorflow".
import os
os.environ["KERAS_BACKEND"] = "jax"
import keras
model = keras.saving.load_model("hf://OWLab/Optic-flow-CNN-LeakyReLU-15x15")
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
From our paper: Layton, Peng, & Steinmetz (2024). ReLU, Sparseness, and the Encoding of Optic Flow in Neural Networks. Sensors.