keyu-tian/SparK
[ICLR'23 Spotlightš„] The first successful BERT/MAE-style pretraining on any convolutional network; Pytorch impl. of "Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling"
Star & Fork Trend (18 data points)
Multi-Source Signals
Growth Velocity
keyu-tian/SparK has +0 stars this period . Velocity data will be available after more historical data is collected.
Deep analysis is being generated for this repository.
Signal-backed technical analysis will be available soon.
| Metric | SparK | cnn_graph | ppl.nn | TorchSSL |
|---|---|---|---|---|
| Stars | 1.4k | 1.4k | 1.4k | 1.4k |
| Forks | 84 | 390 | 221 | 187 |
| Weekly Growth | +0 | +0 | +0 | +0 |
| Language | Python | Jupyter Notebook | C++ | Python |
| Sources | 1 | 1 | 1 | 1 |
| License | MIT | MIT | Apache-2.0 | MIT |
Capability Radar vs cnn_graph
Last code push 807 days ago.
Fork-to-star ratio: 6.1%. Lower fork ratio may indicate passive usage.
Issue data not yet available.
No measurable growth in the current period (first-day cold start expected).
Licensed under MIT. Permissive ā safe for commercial use.
Risk scores are computed from real-time repository data. Higher scores indicate healthier metrics.