⚠ 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"]}

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

Features

• chain: crop with minimum dims, force square (a41ca51)

Bug Fixes

• torch: class_weights with multigpu (9c1ed4c)
• torch: metrics naming for multiple test sets (17b8cbb)

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

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: Open Source Deep Learning Server & API (Changelog)

0.22.1 (2022-05-28)

Bug Fixes

• caffe build can use custom opencv (fde90cd)
• wrong cuda runtime in docker images (8ca5acf)

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

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

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

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

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

Features

• build: CMake config file to link with dede (dd71a35)
• ml: add multigpu support for external native models (90dcadd)
• ml: inference for GAN generators with TensorRT backend (c93188c)
• ml: python script to trace timm vision models (055fdfe)
• predict: add best_bbox for torch, trt, caffe, ncnn backend (7890401)
• torch: add dataloader_threads in API (74a036d)
• torch: add multigpu for torch models (447dd53)
• torch: support detection models in chains (7bb9705)
• TRT: port to TensorRT 21.04/7.2.3 (4377451)

Bug Fixes

• moving back to FAISS master (916338b)
• build: add required definitions and include directory for building external dd api (a059428)
• build: do not patch/rebuild tensorrt if not needed (bfd29ec)
• build: torch 1.8 with cuda 11.3 string_view patch (5002308)
• chain: fixed_size crops now work at the edges of images (8e38e35)
• dto: allow scale input param to be either bool for csv/csvts or float for img (168fc7c)
• log: typo in ncnn model log (0163b02)
• ncnn: fix ncnnapi deserialization error (089aacd)
• ncnn: fix typo in ut (893217b)

Docker images:

• CPU version: docker pull jolibrain/deepdetect_cpu:v0.18.0
• GPU (CUDA only): docker pull jolibrain/deepdetect_gpu:v0.18.0
• GPU (CUDA and Tensorrt) :docker pull jolibrain/deepdetect_cpu_tensorrt:v0.18.0
• GPU with torch backend: docker pull jolibrain/deepdetect_gpu_torch:v0.18.0
• All images available on https://hub.docker.com/u/jolibrain