This repository contains the
BEVFormer
model converted for high-performance inference on the Axera NPU. BEVFormer is a paradigm-shifting transformer-based framework for 3D object detection that learns unified spatio-temporal bird's-eye-view (BEV) representations from multi-camera inputs.
This version is optimized with
w8a16
quantization and is compatible with
Pulsar2 version 4.2
.
The model generates a 3D detection map projected onto the Bird's-Eye-View plane. Results are saved as images and videos which visualize the ego-vehicle and surrounding detected objects.
Runs of AXERA-TECH bevformer on huggingface.co
62
Total runs
1
24-hour runs
7
3-day runs
9
7-day runs
54
30-day runs
More Information About bevformer huggingface.co Model
bevformer huggingface.co is an AI model on huggingface.co that provides bevformer's model effect (), which can be used instantly with this AXERA-TECH bevformer model. huggingface.co supports a free trial of the bevformer model, and also provides paid use of the bevformer. Support call bevformer model through api, including Node.js, Python, http.
bevformer huggingface.co is an online trial and call api platform, which integrates bevformer's modeling effects, including api services, and provides a free online trial of bevformer, you can try bevformer online for free by clicking the link below.
AXERA-TECH bevformer online free url in huggingface.co:
bevformer is an open source model from GitHub that offers a free installation service, and any user can find bevformer on GitHub to install. At the same time, huggingface.co provides the effect of bevformer install, users can directly use bevformer installed effect in huggingface.co for debugging and trial. It also supports api for free installation.