Efficient Sparse-Winograd Convolutional Neural Networks

Authors: Xingyu Liu, Jeff Pool, Song Han, William J. Dally

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

Reproducibility Variable Result LLM Response
Research Type Experimental For models on CIFAR-10, CIFAR-100 and Image Net datasets, our method reduces the number of multiplications by 10.4 , 6.8 and 10.8 respectively with loss of accuracy less than 0.1%, outperforming previous baselines by 2.0 -3.0 .
Researcher Affiliation Collaboration Stanford University, NVIDIA, Massachusetts Institute of Technology, Google Brain
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code Yes We open-source our code and models at https://github.com/xingyul/Sparse-Winograd-CNN.
Open Datasets Yes We used image classification datasets of different scales: CIFAR-10, CIFAR-100 (Krizhevsky & Hinton, 2009) and Image Net 2012 (Russakovsky et al., 2015).
Dataset Splits No The paper mentions using 'validation set accuracy' for CIFAR-10, CIFAR-100, and ImageNet, implying the use of a validation split. However, it does not explicitly state the specific percentages or sample counts for the training, validation, and test dataset splits, nor does it cite a specific pre-defined split methodology for all three parts.
Hardware Specification No The paper does not provide specific hardware details such as GPU or CPU models, memory specifications, or cloud computing instance types used for running the experiments.
Software Dependencies No The paper mentions using the 'TensorFlow framework' but does not provide specific version numbers for TensorFlow or any other software libraries or dependencies used in the experiments.
Experiment Setup No The paper describes the training, pruning, and retraining phases, and mentions using the 'same data augmentation' across models. However, it does not provide specific experimental setup details such as learning rates, batch sizes, number of epochs, or optimizer settings for reproducibility.