Releases: jolibrain/deepdetect
Releases · jolibrain/deepdetect
DeepDetect v0.26.0
Features
- generate mask for diffusion models in trt (5c16ad0)
- opencv optional build (ce9b9a7)
- output: add false positive metrics for detection (bec49c4)
- torch: add JIT FusionStrategy selection (d2331be)
- torch: Added script to trace HuggingFace Transformers CLIP models based on https://huggingface.co/openai/clip-vit-large-patch14-336 (c2373ea)
Bug Fixes
- torch: errors in input connector are caught correctly (ac09c52)
- torch: segmentation with test_batch_size > 1 (0d8d3da)
Docker images:
- CPU version:
docker pull docker.jolibrain.com/deepdetect_cpu:v0.26.0 - GPU (CUDA only):
docker pull docker.jolibrain.com/deepdetect_gpu:v0.26.0 - GPU (CUDA and Tensorrt) :
docker pull docker.jolibrain.com/deepdetect_cpu_tensorrt:v0.26.0 - GPU with torch backend:
docker pull docker.jolibrain.com/deepdetect_gpu_torch:v0.26.0 - All images available from https://docker.jolibrain.com/, list images with {"repositories":["cuda12.5.1-devel-ubuntu22.04-preinst-devel","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"]}
DeepDetect v0.25.0
⚠ 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"]}
DeepDetect v0.24.0
Features
- add custom api path to swagger (4fe0df7)
- add percent error measure display (1cc15d6)
- api: add a model_stats field containing the number of parameters of the model (b562fee)
- api: add labels in service info (66cbff5)
- api: increase accepted header size (07f6ff3)
- log model parameters and size at service startup (041b649)
- regression: add l1 metric for regression (c82f08d)
- torch: add radam optimizer (5bba045)
- torch: add translation and bbox duplication to data augmentation (8752e1f)
- torch: allow data aug to be only noise or distort (5a02234)
- torch: allow data augmentation w/o db (f5b16b3)
- torch: data augmentation w/o db for bbox (a99ca7b)
- torch: set data augmentation factors as requested (e26a775)
- torch: update torch to 1.13 (9c5da36)
- trt: add int8 inference (a212a8e)
- trt: recompile engine if wrong version is detected (0f0bb62)
- upgrade to TensorRT 8.4.3 (1132760)
Bug Fixes
- api: re-add parameters in info call (df318cb)
- raise exception when a bbox file contains invalid classes (3a82a9d)
- readme: correct docker tags for ci-master (49dde89)
- regression: fix eucl metric in case of thresholded metric (a006615)
- take into account false negatives when computing average precision (11905eb)
- tensorrt: clarify conditions to rebuild engine (9d08b0a)
- torch: add measures to output event when training not done (5714767)
- torch: avoid race condition when building alphabet (b1accb7)
- torch: correctly normalize l1 and l2 metrics in case of multi dim regression (cc9a636)
- torch: data augmentation handle dummy bboxes correctly (53d0c39)
- torch: dataset size is half the database size (9541de1)
- torch: make multi dim regression for images work (00985bf)
- torch: small glitches in data augmentation (678944a)
- torch: when reading bbox dataset, also check that the class is not >= nclasses (7b2de88)
- trace_yolox: bbox shifted by 1 when training yolox (487bad7)
- trace_yolox: input shape for nonsquare images (6db03be)
Docker images:
- CPU version:
docker pull docker.jolibrain.com/deepdetect_cpu:v0.24.0 - GPU (CUDA only):
docker pull docker.jolibrain.com/deepdetect_gpu:v0.24.0 - GPU (CUDA and Tensorrt) :
docker pull docker.jolibrain.com/deepdetect_cpu_tensorrt:v0.24.0 - GPU with torch backend:
docker pull docker.jolibrain.com/deepdetect_gpu_torch:v0.24.0 - All images available from https://docker.jolibrain.com/, list images with
curl -X GET https://docker.jolibrain.com/v2/_catalog
DeepDetect v0.23.1
Features
- chain: crop with minimum dims, force square (a41ca51)
Bug Fixes
Docker images:
- CPU version:
docker pull jolibrain/deepdetect_cpu:v0.23.1 - GPU (CUDA only):
docker pull jolibrain/deepdetect_gpu:v0.23.1 - GPU (CUDA and Tensorrt) :
docker pull jolibrain/deepdetect_cpu_tensorrt:v0.23.1 - GPU with torch backend:
docker pull jolibrain/deepdetect_gpu_torch:v0.23.1 - All images available on https://hub.docker.com/u/jolibrain
DeepDetect v0.23.0
Features
- add crnn resnet native template (ec1f8ad)
- add deepdetect version to config variables for external projects (be79e54)
- dlib: update dlib backend (12d181f)
- torch: add multilabel classification (90d536e)
- torch: allow multigpu for traced models (6b3b9c0)
- torch: best model is computed over all the test sets (fbedf80)
- torch: update torch to 1.12 (7172314)
- yolox: export directly from trained dd repo to onnx (a612539)
Bug Fixes
- adamw default weight decay with torch backend (eb0cf83)
- add missing headers in predict_out.hpp (b23298f)
- docker: add libcupti to gpu_torch docker (1a5cd09)
- enable caffe chain with DTO & custom actions (d3e722e)
- exported yolox have the correct number of classes (4dac269)
- missing ifdef (e8a70cf)
- missing path to cub headers in tensorrt-oss build for jetson nano (00df9fd)
- oatpp: oatpp-zlib memory leak (fccd9a6)
- prevent a buggy optimization in traced fasterrcnn (dab88ca)
- reload best metric correctly after resume (c15c502)
- torch: OCR predict with native model (24aa37c)
Docker images:
- CPU version:
docker pull jolibrain/deepdetect_cpu:v0.23.0 - GPU (CUDA only):
docker pull jolibrain/deepdetect_gpu:v0.23.0 - GPU (CUDA and Tensorrt) :
docker pull jolibrain/deepdetect_cpu_tensorrt:v0.23.0 - GPU with torch backend:
docker pull jolibrain/deepdetect_gpu_torch:v0.23.0 - All images available on https://hub.docker.com/u/jolibrain
DeepDetect v0.22.1
DeepDetect: Open Source Deep Learning Server & API (Changelog)
0.22.1 (2022-05-28)
Bug Fixes
Docker images:
- CPU version:
docker pull jolibrain/deepdetect_cpu:v0.22.1 - GPU (CUDA only):
docker pull jolibrain/deepdetect_gpu:v0.22.1 - GPU (CUDA and Tensorrt) :
docker pull jolibrain/deepdetect_cpu_tensorrt:v0.22.1 - GPU with torch backend:
docker pull jolibrain/deepdetect_gpu_torch:v0.22.1 - All images available on https://hub.docker.com/u/jolibrain
DeepDetect v0.22.0
Features
- cpp: torch predict to DTO (b88f22a)
- sliding object detection script (0e3df67)
- tensorrt object detector top_k control (655aa48)
- torch: bump to torch 1.11 and torchvision 0.12 (5d312d0)
- torch: ocr model training and inference (3fc2e27)
- trt: update tensorrt to 22.03 (c03aa9d)
Bug Fixes
- cropped model input size when publishing torch models + tests (2dabd89)
- cutout and crops in data augmentation of torch models (1ef2796)
- docker: fix libraries not found in trt docker (86f3924)
- remove semantic commit check (5d0f0c7)
- seeded random crops at test time (92feae3)
- torch best model better or equal (4d50c8e)
- torch model publish crash and repository (6a89b83)
- torch: Fix update metrics and solver options when resuming (9b0019f)
Docker images:
- CPU version:
docker pull jolibrain/deepdetect_cpu:v0.22.0 - GPU (CUDA only):
docker pull jolibrain/deepdetect_gpu:v0.22.0 - GPU (CUDA and Tensorrt) :
docker pull jolibrain/deepdetect_cpu_tensorrt:v0.22.0 - GPU with torch backend:
docker pull jolibrain/deepdetect_gpu_torch:v0.22.0 - All images available on https://hub.docker.com/u/jolibrain
DeepDetect v0.21.0
Features
- add predict from video (02872eb)
- add video input connector and streaming endpoints (07644b4)
- allow pure negative samples for training object detectors with torch (cd23bad)
- bench: add monitoring of transform time (3f77d42)
- chain: add action to draw bboxes as trailing action (ae0a05f)
- chain: allow user to add their own custom actions (a470c7b)
- ml: added support for segformer with torch backend (ab03d1d)
- ml: random cropping for training segmentation models with torch (ac7ce0f)
- random crops for object detector training with torch backend (385122d)
- segmentation of large images with sliding window, example Python script (8528e9a)
Bug Fixes
- bbox clamping in torch inference (2d6efd3)
- caffe object detector training requires test set (2e4db7e)
- dataset output dimension after crop augmentation (636d455)
- detection/torch: correctly normalize MAP wrt torchlib outputs (b12d188)
- model.json file saving (809f00a)
- segmentation with torch backend + full cropping support (e14c3f2)
- torch MaP with bboxes (9bc840f)
- torch model published config file (b0d4e04)
Docker images:
- CPU version:
docker pull jolibrain/deepdetect_cpu:v0.21.0 - GPU (CUDA only):
docker pull jolibrain/deepdetect_gpu:v0.21.0 - GPU (CUDA and Tensorrt) :
docker pull jolibrain/deepdetect_cpu_tensorrt:v0.21.0 - GPU with torch backend:
docker pull jolibrain/deepdetect_gpu_torch:v0.21.0 - All images available on https://hub.docker.com/u/jolibrain
DeepDetect v0.20.0
Features
- feat: add elapsed time to training metrics (fe5fc41)
- feat: add onnx export for torchvision models (07f69b1)
- feat: add yolox export script for training and inference (0b2f20b)
- feat: add yolox onnx export and trt support (80b7e6a)
- api: chain uses dto end to end (5efbf28)
- ml: data augmentation for training segmentation models with torch backend (b55c218)
- ml: DETR export and inference with torch backend (1e4ea4e)
- feat: full cuda pipeline for tensorrt (93815d7)
- ml: noise image data augmentation for training with torch backend (2d9757d)
- ml: training segmentation models with torch backend (1e3ff16)
- ml: activate cutout for object detector training with torch backend (8a34aa1)
- ml: distortion noise for image training with torch backend (35a16df)
- ml: dice loss https://arxiv.org/abs/1707.03237 (542bcb4)
- ml: manage models with multiple losses (bea7cb4)
Bug Fixes
- cpu: cudnn is now on by default, auto switch it to off in case of cpu_only (3770baf)
- tensorrt: read onnx model to find topk (5cce134)
- simsearch ivf index craft after reload, disabling mmap (8a2e665)
- tensorrt: yolox postprocessing in C++ (1d781d2)
- torch: add include sometimes needed (74487dc)
- add mltype in metrics.json even if training is not over (9bda7f7)
- clang formatting of mlmodel (130626b)
- torch: avoid crashes caused by an exception in the training loop (667b264)
- torch: bad bbox rescaling on multiple uris (05451ed)
- torch: correct output name for onnx classification model (a03eb87)
- torch: prevent crash during training if an exception is thrown (4ce7802)
Docker images:
- CPU version:
docker pull jolibrain/deepdetect_cpu:v0.20.0 - GPU (CUDA only):
docker pull jolibrain/deepdetect_gpu:v0.20.0 - GPU (CUDA and Tensorrt) :
docker pull jolibrain/deepdetect_cpu_tensorrt:v0.20.0 - GPU with torch backend:
docker pull jolibrain/deepdetect_gpu_torch:v0.20.0 - All images available on https://hub.docker.com/u/jolibrain
DeepDetect v0.19.0
Features
- add DTO schemas to swagger automatic doc (9180ff4)
- add z-normalisation option (82d7cc5)
- dto: add custom dto vector type (01222db)
- torch: add ADAMP variant of adam in RANGER (2006.08217) (e26ed77)
- trt: add return cv::Mat instead of vector for GAN output (4990e7b)
- torch segmentation model prediction (d72a138)
Bug Fixes
- always depend on oatpp (f262114)
- test: tar archive was decompressed at each cmake call (910a0ee)
- torch: predictions handled correctly when data count > 1 (5a95c29)
- trt: detect architecture and rebuild model if necessary (5c9ff89)
- TRT: fix build wrt new external build script (7121dfe)
- TRT: make refinedet great again, also upgrades to TRT8.0.0/TRT-OSS21.08 (bdff2ae)
- CI on Jetson nano with lighter classification model (1673a99)
- dont rebuild torchvision everytime (4f17897)
- remove linking errors on oatpp access_log (ed276b3)
Docker images:
- CPU version:
docker pull jolibrain/deepdetect_cpu:v0.19.0 - GPU (CUDA only):
docker pull jolibrain/deepdetect_gpu:v0.19.0 - GPU (CUDA and Tensorrt) :
docker pull jolibrain/deepdetect_cpu_tensorrt:v0.19.0 - GPU with torch backend:
docker pull jolibrain/deepdetect_gpu_torch:v0.19.0 - All images available on https://hub.docker.com/u/jolibrain