HexaConv

Authors: Emiel Hoogeboom, Jorn W.T. Peters, Taco S. Cohen, Max Welling

ICLR 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate our method on the CIFAR-10 benchmark and on the Aerial Image Dataset (AID) (Xia et al., 2017). The CIFAR-10 results are presented in Table 1, obtained by taking the average of 10 experiments with different random weight initializations.
Researcher Affiliation Academia Emiel Hoogeboom , Jorn W.T. Peters & Taco S. Cohen University of Amsterdam {e.hoogeboom,j.w.t.peters,t.s.cohen}@uva.nl Max Welling University of Amsterdam & CIFAR m.welling@uva.nl
Pseudocode No No explicit pseudocode or algorithm blocks are provided in the paper.
Open Source Code Yes Source code of G-Hexa Convs is available on Github: https://github.com/ehoogeboom/hexaconv.
Open Datasets Yes We evaluate our method on the CIFAR-10 benchmark and on the Aerial Image Dataset (AID) (Xia et al., 2017).
Dataset Splits No The paper mentions splitting data into '80% train/20% test sets' for AID but does not specify a validation split or its proportion for either dataset.
Hardware Specification No The paper does not specify any particular hardware (e.g., GPU models, CPU types) used for running the experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., Python 3.x, TensorFlow 1.x).
Experiment Setup No The paper describes network architectures (e.g., '3 stages, with 4 blocks per stage', 'first convolution layer has stride two') but does not provide specific hyperparameter values like learning rate, batch size, or number of epochs for training.