We lifted 14 functions out of this paper's own repositories and ran 10 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.
| Repository | Role | Ran |
|---|---|---|
| Edge-AI-Acceleration-Lab/RBFleX-NAS | canonical | 2 of 3 |
| feymanpriv/pymetric | pwc_unofficial | 7 of 10 |
| tuggeluk/pycls | extension | 1 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| ComputeVertexChannels | Ran | Edge-AI-Acceleration-Lab/RBFleX-NAS/designspace/Trans_Macro/model_wrapper_macro/backbones/model_nb101/model_nb101.py code served (permissive licence) · get_code("3122aea73ebb5edf") |
| Truncate | Ran | Edge-AI-Acceleration-Lab/RBFleX-NAS/designspace/Trans_Macro/model_wrapper_macro/backbones/model_nb101/model_nb101.py code served (permissive licence) · get_code("77137d76f02e37fe") |
| cache_url | Ran | feymanpriv/pymetric/metric/core/io.py pointer only (licence: MIT) · get_code("f623b3e3625d4e42") |
| complexity_batchnorm2d | Ran | feymanpriv/pymetric/metric/core/net.py pointer only (licence: MIT) · get_code("4136b6e9df422178") |
| complexity_conv2d | Ran | feymanpriv/pymetric/metric/core/net.py pointer only (licence: MIT) · get_code("b299737079f619a1") |
| complexity_maxpool2d | Ran | feymanpriv/pymetric/metric/core/net.py pointer only (licence: MIT) · get_code("ee4b7c6aef3ebb1f") |
| get_logger | Ran | feymanpriv/pymetric/metric/core/logging.py pointer only (licence: MIT) · get_code("8e4e129cb77e7f8b") |
| time_string | Ran | feymanpriv/pymetric/metric/core/meters.py pointer only (licence: MIT) · get_code("803bcd86e3301891") |
| topk_errors | Ran | feymanpriv/pymetric/metric/core/meters.py pointer only (licence: MIT) · get_code("b997b70e1ac2c2f1") |
| unwrap_model | Ran | tuggeluk/pycls/pycls/core/net.py code served (permissive licence) · get_code("8ba24560996e7d76") |
| Projection | Not yet run | Edge-AI-Acceleration-Lab/RBFleX-NAS/designspace/Trans_Macro/model_wrapper_macro/backbones/model_nb101/model_nb101.py code served (permissive licence) · get_code("9640a6667c162560") |
| download_url | Not yet run | feymanpriv/pymetric/metric/core/io.py pointer only (licence: MIT) · get_code("e10bd0e3f25f2b57") |
| dump_log_data | Not yet run | feymanpriv/pymetric/metric/core/logging.py pointer only (licence: MIT) · get_code("7defe868d1a6d115") |
| float_to_decimal | Not yet run | feymanpriv/pymetric/metric/core/logging.py pointer only (licence: MIT) · get_code("99b17e191b358f21") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Over the past several years progress in designing better neural network architectures for visual recognition has been substantial. To help sustain this rate of progress, in this work we propose to reexamine the methodology for comparing network architectures. In particular, we introduce a new comparison paradigm of distribution estimates, in which network design spaces are compared by applying statistical techniques to populations of sampled models, while controlling for confounding factors like network complexity. Compared to current methodologies of comparing point and curve estimates of model families, distribution estimates paint a more complete picture of the entire design landscape. As a case study, we examine design spaces used in neural architecture search (NAS). We find significant statistical differences between recent NAS design space variants that have been largely overlooked. Furthermore, our analysis reveals that the design spaces for standard model families like ResNeXt can be comparable to the more complex ones used in recent NAS work. We hope these insights into distribution analysis will enable more robust progress toward discovering better networks for visual recognition.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1905.13214")
get_code_for_paper("1905.13214")
have("1905.13214")
Connect an agent — have() is free.