SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.10061 · ICLR · 2022

Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification

Wensi Tang, Guodong Long, Lu Liu, Tianyi Zhou, Michael Blumenstein, Jing Jiang

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 11 functions out of this paper's own repositories and ran 7 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
wensi-tang/os-cnn canonical 1 of 3
Wensi-Tang/OS-CNN — 3 of 5
Anonymouslink/OS-CNN — 3 of 3
FunctionStatusWhere it lives
OS_CNN Ran Anonymouslink/OS-CNN/Classifiers/OS_CNN/OS_CNN.py
pointer only (licence: NONE) · get_code("cd0ce30eebdcec3c")
SampaddingConv1D_BN Ran Anonymouslink/OS-CNN/Classifiers/OS_CNN/OS_CNN.py
pointer only (licence: NONE) · get_code("0dee4616b6255680")
build_layer_with_layer_parameter Ran Anonymouslink/OS-CNN/Classifiers/OS_CNN/OS_CNN.py
pointer only (licence: NONE) · get_code("fdf58bf8189b9e66")
calculate_mask_index Ran Wensi-Tang/OS-CNN/Classifiers/OS_CNN/OS_block.py
code served (permissive licence) · get_code("5017468adad0af6b")
creak_layer_mask Ran wensi-tang/os-cnn/Classifiers/OS_CNN/OS_block.py
code served (permissive licence) · get_code("5dadd23392f4ca8c")
creak_layer_mask Ran Wensi-Tang/OS-CNN/Classifiers/OS_CNN/OS_block.py
code served (permissive licence) · get_code("b7f140a01a2fa577")
creat_mask Ran Wensi-Tang/OS-CNN/Classifiers/OS_CNN/OS_block.py
code served (permissive licence) · get_code("2613c4915a16c36d")
OS_block Not yet run Wensi-Tang/OS-CNN/Classifiers/OS_CNN/OS_block.py
code served (permissive licence) · get_code("c466ea8f0e598415")
build_layer_with_layer_parameter Not yet run Wensi-Tang/OS-CNN/Classifiers/OS_CNN/OS_block.py
code served (permissive licence) · get_code("b6c70c06f06614b0")
calculate_mask_index Not yet run wensi-tang/os-cnn/Classifiers/OS_CNN/OS_block.py
code served (permissive licence) · get_code("3b08b25c6a4703e0")
creat_mask Not yet run wensi-tang/os-cnn/Classifiers/OS_CNN/OS_block.py
code served (permissive licence) · get_code("a14cbea422c27566")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The Receptive Field (RF) size has been one of the most important factors for One Dimensional Convolutional Neural Networks (1D-CNNs) on time series classification tasks. Large efforts have been taken to choose the appropriate size because it has a huge influence on the performance and differs significantly for each dataset. In this paper, we propose an Omni-Scale block (OS-block) for 1D-CNNs, where the kernel sizes are decided by a simple and universal rule. Particularly, it is a set of kernel sizes that can efficiently cover the best RF size across different datasets via consisting of multiple prime numbers according to the length of the time series. The experiment result shows that models with the OS-block can achieve a similar performance as models with the searched optimal RF size and due to the strong optimal RF size capture ability, simple 1D-CNN models with OS-block achieves the state-of-the-art performance on four time series benchmarks, including both univariate and multivariate data from multiple domains. Comprehensive analysis and discussions shed light on why the OS-block can capture optimal RF sizes across different datasets. Code available here 1

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2002.10061")
get_code_for_paper("2002.10061")
have("2002.10061")

Connect an agent — have() is free.