DeepDetect release v0.17.0
DeepDetect v0.17.0 was released a few weeks agao. Below we review the main features, fixes and additions.
DeepDetect v0.17 was released few weeks ago. It has the novel Visformer architecture, and new image data augmentation with Torch in C++, among other things.https://t.co/jy42d1zXMf
— jolibrain (@jolibrain) June 1, 2021
The DeepDetect is fully Open Source and continues to bring our real-world DL advances to production
In summary
- Improved image data augmentation for image classification and object detection models with the Torch backend
- Improved inference batching for object detectors with torch C++
- Visformer architecture for large-scale image classification
Fixes & Improvements
- fix to RetinaNet training
- torch graph fix when loading weights
Docker images
- CPU version:
docker pull jolibrain/deepdetect_cpu:v0.17.0
- GPU (CUDA only):
docker pull jolibrain/deepdetect_gpu:v0.17.0
- GPU (CUDA and Tensorrt) :
docker pull jolibrain/deepdetect_gpu_tensorrt:v0.17.0
- GPU with torch backend:
docker pull jolibrain/deepdetect_gpu_torch:v0.17.0
All images available on https://hub.docker.com/u/jolibrain