SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1804.06300 · 2018

PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 7 functions out of this paper's own repositories and ran 3 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
stevenolvil/PredRNN-V2 pwc_unofficial 3 of 5
Flunzmas/vp-suite pwc_unofficial 0 of 2
FunctionStatusWhere it lives
merge Ran stevenolvil/PredRNN-V2/config.py
code served (permissive licence) · get_code("b2108b927c53418b")
parse_cli_to_yaml Ran stevenolvil/PredRNN-V2/config.py
code served (permissive licence) · get_code("3498f707d22460cd")
parse_yaml Ran stevenolvil/PredRNN-V2/config.py
code served (permissive licence) · get_code("c8d98ae32946f6f0")
batch_mae_frame_float Not yet run stevenolvil/PredRNN-V2/metrics.py
code served (permissive licence) · get_code("7ed146388146c4ef")
batch_psnr Not yet run stevenolvil/PredRNN-V2/metrics.py
code served (permissive licence) · get_code("bc969cd44c6bf1e7")
find_divisor_for_group_norm Not yet run Flunzmas/vp-suite/vp_suite/model_blocks/phydnet.py
code served (permissive licence) · get_code("672b7d6e7ade32ca")
tensordot Not yet run Flunzmas/vp-suite/vp_suite/model_blocks/phydnet.py
code served (permissive licence) · get_code("9bb66a55a94477cf")

Repositories linked to this paper

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

Abstract

We present PredRNN++, an improved recurrent network for video predictive learning. In pursuit of a greater spatiotemporal modeling capability, our approach increases the transition depth between adjacent states by leveraging a novel recurrent unit, which is named Causal LSTM for re-organizing the spatial and temporal memories in a cascaded mechanism. However, there is still a dilemma in video predictive learning: increasingly deep-in-time models have been designed for capturing complex variations, while introducing more difficulties in the gradient back-propagation. To alleviate this undesirable effect, we propose a Gradient Highway architecture, which provides alternative shorter routes for gradient flows from outputs back to long-range inputs. This architecture works seamlessly with causal LSTMs, enabling PredRNN++ to capture short-term and long-term dependencies adaptively. We assess our model on both synthetic and real video datasets, showing its ability to ease the vanishing gradient problem and yield state-of-the-art prediction results even in a difficult objects occlusion scenario.

For agents

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

get_harvested_code_for_paper("1804.06300")
get_code_for_paper("1804.06300")
have("1804.06300")

Connect an agent — have() is free.