Download Latest Version
DeepDetect v0.26.0 source code.zip (7.0 MB)
Get an email when there's a new version of DeepDetect
| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| DeepDetect v0.25.0 source code.tar.gz | 2024-01-10 | 6.6 MB | |
| DeepDetect v0.25.0 source code.zip | 2024-01-10 | 6.9 MB | |
| README.md | 2024-01-10 | 3.2 kB | |
| Totals: 3 Items | 13.5 MB | 0 | |
⚠ BREAKING CHANGES
- trt: dropped support for caffe refinedet
Features
- allow returning images in json in base64 format (05096fd)
- build Deepdetect + pytorch MPS on Apple platforms (aa8822d)
- recompose action to recreate an image from a GAN + crop (e1118b1)
- torch: add map metrics with arbitrary iou threshold (20d8ebe)
- torch: Added param
disable_concurrent_predict(71cb66a)
Bug Fixes
- add more explicit error messages (ca2703c)
- allow two chain calls with the same name to be executed simultaneously (b26b5b9)
- chain: empty predictions were too empty (57bed0b)
- docker: build CPU dockers (9e56aba)
- no resize when training with images (e84c616)
- prevent crash when a service is deleted before finishing predict (0ef1f46)
- support boolean value for service info parameters (737724d)
- torch architecture selected correctly at docker build (5eb7890)
- torch: black&white image now working with crnn & dataaug (2b07002)
- torch: concurrent_predict was always true (edb28c1)
Docker images:
- CPU version:
docker pull docker.jolibrain.com/deepdetect_cpu:v0.25.0 - GPU (CUDA only):
docker pull docker.jolibrain.com/deepdetect_gpu:v0.25.0 - GPU (CUDA and Tensorrt) :
docker pull docker.jolibrain.com/deepdetect_cpu_tensorrt:v0.25.0 - GPU with torch backend:
docker pull docker.jolibrain.com/deepdetect_gpu_torch:v0.25.0 - All images available from https://docker.jolibrain.com/, list images with {"repositories":["deepdetect_cpu","deepdetect_cpu_torch","deepdetect_gpu","deepdetect_gpu_tensorrt","deepdetect_gpu_torch","filebrowser","gpustat_server","joligen_server","joligen_ui","jupyter_dd_notebook","platform_annotations_backend","platform_annotations_frontend","platform_data","platform_ui"]}