Matches in SemOpenAlex for { <https://semopenalex.org/work/W3023648375> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W3023648375 abstract "In order to contrast the explosion in size of state-of-the-art machine learning models that can be attributed to the empirical advantages of over-parametrization, and due to the necessity of deploying fast, sustainable, and private on-device models on resource-constrained devices, the community has focused on techniques such as pruning, quantization, and distillation as central strategies for model compression. Towards the goal of facilitating the adoption of a common interface for neural network pruning in PyTorch, this contribution describes the recent addition of the PyTorch torch.nn.utils.prune module, which provides shared, open source pruning functionalities to lower the technical implementation barrier to reducing model size and capacity before, during, and/or after training. We present the module's user interface, elucidate implementation details, illustrate example usage, and suggest ways to extend the contributed functionalities to new pruning methods." @default.
- W3023648375 created "2020-05-13" @default.
- W3023648375 creator A5059618221 @default.
- W3023648375 creator A5089018232 @default.
- W3023648375 date "2020-04-28" @default.
- W3023648375 modified "2023-10-03" @default.
- W3023648375 title "Streamlining Tensor and Network Pruning in PyTorch." @default.
- W3023648375 cites W1686810756 @default.
- W3023648375 cites W2112796928 @default.
- W3023648375 cites W2119144962 @default.
- W3023648375 cites W2279098554 @default.
- W3023648375 cites W2513554817 @default.
- W3023648375 cites W2554302513 @default.
- W3023648375 cites W2769502706 @default.
- W3023648375 cites W2948223045 @default.
- W3023648375 cites W2962988160 @default.
- W3023648375 cites W2970971581 @default.
- W3023648375 cites W3005957694 @default.
- W3023648375 hasPublicationYear "2020" @default.
- W3023648375 type Work @default.
- W3023648375 sameAs 3023648375 @default.
- W3023648375 citedByCount "5" @default.
- W3023648375 countsByYear W30236483752020 @default.
- W3023648375 countsByYear W30236483752021 @default.
- W3023648375 crossrefType "posted-content" @default.
- W3023648375 hasAuthorship W3023648375A5059618221 @default.
- W3023648375 hasAuthorship W3023648375A5089018232 @default.
- W3023648375 hasConcept C108010975 @default.
- W3023648375 hasConcept C108583219 @default.
- W3023648375 hasConcept C11413529 @default.
- W3023648375 hasConcept C119857082 @default.
- W3023648375 hasConcept C154945302 @default.
- W3023648375 hasConcept C28855332 @default.
- W3023648375 hasConcept C41008148 @default.
- W3023648375 hasConcept C50644808 @default.
- W3023648375 hasConcept C6557445 @default.
- W3023648375 hasConcept C86803240 @default.
- W3023648375 hasConceptScore W3023648375C108010975 @default.
- W3023648375 hasConceptScore W3023648375C108583219 @default.
- W3023648375 hasConceptScore W3023648375C11413529 @default.
- W3023648375 hasConceptScore W3023648375C119857082 @default.
- W3023648375 hasConceptScore W3023648375C154945302 @default.
- W3023648375 hasConceptScore W3023648375C28855332 @default.
- W3023648375 hasConceptScore W3023648375C41008148 @default.
- W3023648375 hasConceptScore W3023648375C50644808 @default.
- W3023648375 hasConceptScore W3023648375C6557445 @default.
- W3023648375 hasConceptScore W3023648375C86803240 @default.
- W3023648375 hasOpenAccess W3023648375 @default.
- W3023648375 hasRelatedWork W1970529826 @default.
- W3023648375 hasRelatedWork W2089310500 @default.
- W3023648375 hasRelatedWork W2532550412 @default.
- W3023648375 hasRelatedWork W2806003270 @default.
- W3023648375 hasRelatedWork W2891568166 @default.
- W3023648375 hasRelatedWork W2893890695 @default.
- W3023648375 hasRelatedWork W2899645952 @default.
- W3023648375 hasRelatedWork W2972370592 @default.
- W3023648375 hasRelatedWork W2989130096 @default.
- W3023648375 hasRelatedWork W3007701209 @default.
- W3023648375 hasRelatedWork W3017209591 @default.
- W3023648375 hasRelatedWork W3017573341 @default.
- W3023648375 hasRelatedWork W3034275715 @default.
- W3023648375 hasRelatedWork W3042482718 @default.
- W3023648375 hasRelatedWork W3048541663 @default.
- W3023648375 hasRelatedWork W3118514493 @default.
- W3023648375 hasRelatedWork W3177376760 @default.
- W3023648375 hasRelatedWork W3180989657 @default.
- W3023648375 hasRelatedWork W3190002042 @default.
- W3023648375 hasRelatedWork W3212733080 @default.
- W3023648375 isParatext "false" @default.
- W3023648375 isRetracted "false" @default.
- W3023648375 magId "3023648375" @default.
- W3023648375 workType "article" @default.