We lifted 11 functions out of this paper's own repositories and ran 8 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 |
|---|---|---|
| iCGY96/AAP | canonical | 4 of 4 |
| iCGY96/syops-counter | pwc_unofficial | 4 of 7 |
| Function | Status | Where it lives |
|---|---|---|
| accuracy | Ran | iCGY96/AAP/imagenet/utils.py code served (permissive licence) · get_code("4134b8420b4c48b5") |
| conv1x1 | Ran | iCGY96/AAP/imagenet/dsnn.py code served (permissive licence) · get_code("d9def42110729a85") |
| conv3x3 | Ran | iCGY96/AAP/imagenet/dsnn.py code served (permissive licence) · get_code("160bb14bd76201b4") |
| convpxp | Ran | iCGY96/AAP/imagenet/dsnn.py code served (permissive licence) · get_code("79233a0a481d1c39") |
| params_to_string | Ran | iCGY96/syops-counter/syops/utils.py code served (permissive licence) · get_code("dc5ee8c0a918c502") |
| rnn_syops | Ran | iCGY96/syops-counter/syops/ops.py code served (permissive licence) · get_code("ff0de6ad446ac5df") |
| spike_rate | Ran | iCGY96/syops-counter/syops/ops.py code served (permissive licence) · get_code("315b7f4d135390d6") |
| syops_to_string | Ran | iCGY96/syops-counter/syops/utils.py code served (permissive licence) · get_code("eda2bc4c9144c14c") |
| accumulate_syops | Not yet run | iCGY96/syops-counter/syops/engine.py code served (permissive licence) · get_code("e805c6a2a25d5e39") |
| get_model_complexity_info | Not yet run | iCGY96/syops-counter/syops/flops_counter.py code served (permissive licence) · get_code("49528bea8c87044b") |
| print_model_with_syops | Not yet run | iCGY96/syops-counter/syops/engine.py code served (permissive licence) · get_code("11ca743c5945e560") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Due to the binary spike signals making converting the traditional high-power multiply-accumulation (MAC) into a low-power accumulation (AC) available, the brain-inspired Spiking Neural Networks (SNNs) are gaining more and more attention. However, the binary spike propagation of the Full-Spike Neural Networks (FSNN) with limited time steps is prone to significant information loss. To improve performance, several state-of-the-art SNN models trained from scratch inevitably bring many non-spike operations. The non-spike operations cause additional computational consumption and may not be deployed on some neuromorphic hardware where only spike operation is allowed. To train a large-scale FSNN with high performance, this paper proposes a novel Dual-Stream Training (DST) method which adds a detachable Auxiliary Accumulation Pathway (AAP) to the full spiking residual networks. The accumulation in AAP could compensate for the information loss during the forward and backward of full spike propagation, and facilitate the training of the FSNN. In the test phase, the AAP could be removed and only the FSNN remained. This not only keeps the lower energy consumption but also makes our model easy to deploy. Moreover, for some cases where the non-spike operations are available, the APP could also be retained in test inference and improve feature discrimination by introducing a little non-spike consumption. Extensive experiments on ImageNet, DVS Gesture, and CIFAR10-DVS datasets demonstrate the effectiveness of DST.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2301.11929")
get_code_for_paper("2301.11929")
have("2301.11929")
Connect an agent — have() is free.