Missing lighter and alternative detection backbones
Users need lighter or alternative backbones such as VGG16, ResNet18, EfficientNet, and ViT in detection models, which the library lacks.
Tier II · Emerging Problems that are still building up.
4 public reports · first reported 15 October 2019 · last reported 16 November 2023
What's going wrong
Users ask for backbone networks that the library does not ship, including VGG16, ResNet18 and ResNet34, EfficientNet, and Vision Transformer variants for Mask R-CNN.
AI-assisted: written with the help of AI from the reports. The idea report has the full summary.
In the idea report
- The full summary.
- The products the 4 reports are about, and how many came each month.
- Related problems.
No business has been found with this problem yet, so the report has no contacts. All sales are final — no refunds. Pricing.