FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

Detectron is deprecated. Please see detectron2, a ground-up rewrite of Detectron in PyTorch.

Detectron

Detectron is Facebook AI Research's software system that implements state-of-the-art object detection algorithms, including Mask R-CNN. It is written in Python and powered by the Caffe2 deep learning framework.

At FAIR, Detectron has enabled numerous research projects, including: Feature Pyramid Networks for Object Detection, Mask R-CNN, Detecting and Recognizing Human-Object Interactions, Focal Loss for Dense Object Detection, Non-local Neural Networks, Learning to Segment Every Thing, Data Distillation: Towards Omni-Supervised Learning, DensePose: Dense Human Pose Estimation In The Wild, and Group Normalization.

Example Mask R-CNN output.

Introduction

The goal of Detectron is to provide a high-quality, high-performance codebase for object detection research. It is designed to be flexible in order to support rapid implementation and evaluation of novel research. Detectron includes implementations of the following object detection algorithms:

using the following backbone network architectures:

Additional backbone architectures may be easily implemented. For more details about these models, please see References below.

Update

License

Detectron is released under the Apache 2.0 license. See the NOTICE file for additional details.

Citing Detectron

If you use Detectron in your research or wish to refer to the baseline results published in the Model Zoo, please use the following BibTeX entry.

@misc{Detectron2018,
  author =       {Ross Girshick and Ilija Radosavovic and Georgia Gkioxari and
                  Piotr Doll\'{a}r and Kaiming He},
  title =        {Detectron},
  howpublished = {\url{https://github.com/facebookresearch/detectron}},
  year =         {2018}
}

Model Zoo and Baselines

We provide a large set of baseline results and trained models available for download in the Detectron Model Zoo.

Installation

Please find installation instructions for Caffe2 and Detectron in INSTALL.md.

Quick Start: Using Detectron

After installation, please see GETTING_STARTED.md for brief tutorials covering inference and training with Detectron.

Getting Help

To start, please check the troubleshooting section of our installation instructions as well as our FAQ. If you couldn't find help there, try searching our GitHub issues. We intend the issues page to be a forum in which the community collectively troubleshoots problems.

If bugs are found, we appreciate pull requests (including adding Q&A's to FAQ.md and improving our installation instructions and troubleshooting documents). Please see CONTRIBUTING.md for more information about contributing to Detectron.

References

Comments
  • multi-GPU training throw an illegal memory access

    multi-GPU training throw an illegal memory access

    When I use one GPU to train, there is no problem. But when I use two or four GPUs, the problem come out. The log output:

    terminate called after throwing an instance of 'caffe2::EnforceNotMet' what(): [enforce fail at context_gpu.h:170] . Encountered CUDA error: an illegal memory access was encountered Error from operator: input: "gpu_0/rpn_cls_logits_fpn2_w_grad" input: "gpu_1/rpn_cls_logits_fpn2_w_grad" output: "gpu_0/rpn_cls_logits_fpn2_w_grad" name: "" type: "Add" device_option { device_type: 1 cuda_gpu_id: 0 } *** Aborted at 1516866180 (unix time) try "date -d @1516866180" if you are using GNU date *** terminate called recursively terminate called recursively terminate called recursively PC: @ 0x7ff67559f428 gsignal terminate called recursively terminate called recursively E0125 07:43:00.745853 55683 pybind_state.h:422] Exception encountered running PythonOp function: RuntimeError: [enforce fail at context_gpu.h:307] error == cudaSuccess. 77 vs 0. Error at: /mnt/hzhida/project/caffe2/caffe2/core/context_gpu.h:307: an illegal memory access was encountered

    At: /mnt/hzhida/facebook/detectron/lib/ops/generate_proposals.py(101): forward *** SIGABRT (@0x3e80000d84f) received by PID 55375 (TID 0x7ff453fff700) from PID 55375; stack trace: *** terminate called recursively @ 0x7ff675945390 (unknown) @ 0x7ff67559f428 gsignal @ 0x7ff6755a102a abort @ 0x7ff66f37e84d __gnu_cxx::__verbose_terminate_handler() @ 0x7ff66f37c6b6 (unknown) @ 0x7ff66f37c701 std::terminate() @ 0x7ff66f3a7d38 (unknown) @ 0x7ff67593b6ba start_thread @ 0x7ff67567141d clone @ 0x0 (unknown) Aborted (core dumped)

  • Not able to run GPU for Caffe2/Detectron

    Not able to run GPU for Caffe2/Detectron

    • Operating system: Ubuntu 16.04
    • GPU models (for all devices if they are not all the same): GTX 1080 8GB
    • python --version: 2.7 Caffe2/Detectron OS: Ubuntu 16.04 Python: 2.7 GPU: GTX 1080 gcc version: 5.4.0

    I have installed CUDA, Cudnn and nccl in a conda environment and followed the steps in the installation file. I used conda (as mentioned) to install caffe2 and other libraries.

    conda install -c caffe2 caffe2-cuda9.0-cudnn7

    Then, to see if GPU is working, I get the following: WARNING:root:This caffe2 python run does not have GPU support. Will run in CPU only mode. WARNING:root:Debug message: libnccl.so.2: cannot open shared object file: No such file or directory Segmentation fault (core dumped)

    I don't know what I am doing wrong or something I am missing. Please let me know.

  • Community effort to bring CPU and pure Caffe2 / C++ inference support

    Community effort to bring CPU and pure Caffe2 / C++ inference support

    It looks like many people are asking for CPU inference and it seems it needs much work to make it happen. What I offer is that we use this issue to publicly state what work is needed and so people eager to have this feature could easily help to implement it.

    @daquexian, @orionr, @rbgirshick do you have time to share a list of features / ops needed to convert all the models with convert_pkl_to_pb.py ?

    | Feature/Operator | Where do we need it ?| State | Difficulty | | ------------- | ------------- | --------------- |------------- | | CollectAndDistributeFpnRpnProposals | FPN | 🕔 PR #372 submitted & Review needed | ? | | ... | ... | ... | ... |

    I would like to contribute to this effort but I do not know where to begin. If you are willing to implement a feature do not hesitate to tell it in this issue.

    Ps: To avoid any confusion I am only a random user of the Detectron & my initiative was not solicited by the maintainers

  • Trouble training custom dataset

    Trouble training custom dataset

    Training Detectron on custom dataset

    I'm trying to train Mask RCNN on my custom dataset to perform segmentation task on new classes that coco or ImageNet never seen.

    • I first converted my dataset to coco format so it can be loaded by pycocotools.
    • I added my dataset path into dataset_catalog.py and created the correct link to images directory and annotations path. The config file I used is based on configs/getting_started/tutorial_1gpu_e2e_faster_rcnn_R-50-FPN.yaml . My dataset contains only 4 classes without background so I set NUM_CLASSES to 5 ( 4 does not work either). When I try to train using the command bellow : python2 tools/train_net.py --cfg configs/encov/copy_maskrcnn_R-101-FPN.yaml OUTPUT_DIR /tmp/detectron-output/

    ERROR 1:

    I get the following error (complete log file is here output.txt) At: /home/encov/Softwares/Detectron/lib/roi_data/fast_rcnn.py(269): _expand_bbox_targets /home/encov/Softwares/Detectron/lib/roi_data/fast_rcnn.py(181): _sample_rois /home/encov/Softwares/Detectron/lib/roi_data/fast_rcnn.py(112): add_fast_rcnn_blobs /home/encov/Softwares/Detectron/lib/ops/collect_and_distribute_fpn_rpn_proposals.py(62): forward terminate called after throwing an instance of 'caffe2::EnforceNotMet' what(): [enforce fail at pybind_state.h:423] . Exception encountered running PythonOp function: ValueError: could not broadcast input array from shape (4) into shape (0)

    This error comes from the expand box procedure that increase the size of bounding box weights by 4 (see roi_data/fast_rcnn.py). It basically takes the first element which represents the class, checks that it is not 0 (the background) and copy weights values at index_class x 4. Error happens because the index is greater than the NUM_CLASSES parameter which has been used to create the output array.


    ERROR 2

    I try same training except I set NUM_CLASSES to 81 which was the number of classes used for coco training which is working on my set-up by the way. The error I described above does not appear but in the really early beginning of the the iterations, bounding box areas is null which cause some divisions by zero. output2.txt

    Has someone experienced the same issue for training fast rcnn or mask rcnn on a custom dataset ? I really suspect an error in my json coco-like file because training on coco dataset in working correctly. Thank you for your help,

    System information

    • Operating system: Ubuntu 16.04
    • Compiler version: GCC 5.4.0
    • CUDA version: 8.0
    • cuDNN version: 7.0
    • NVIDIA driver version: 384
    • GPU model: GeForce GTX 1080 (x1)
    • python --version output: Python 2.7.12
  • Support exporting fpn

    Support exporting fpn

    Based on @orionr's work

    • [x] Solve the problem about GenerateProposals
    • [x] Use the existing ResizeNearest layer instead of UpsampleNearest. ResizeNearest has cpu implementation and neon optimization
    • [x] Make it work (with https://github.com/pytorch/pytorch/pull/7091)

    With this PR, FPN is supported in cooperation with https://github.com/pytorch/pytorch/pull/7091. I have verified that it works on e2e_faster_rcnn_R-50-FPN_1x.yaml

  • Detectron ops lib not found

    Detectron ops lib not found

    After installing caffe2 from source on Ubuntu 16.04, and trying to test with: python2 detectron/tests/test_spatial_narrow_as_op.py I get the following:

    No handlers could be found for logger "caffe2.python.net_drawer"
    net_drawer will not run correctly. Please install the correct dependencies.
    E0207 16:36:41.320443  4125 init_intrinsics_check.cc:59] CPU feature avx is present on your machine, but the Caffe2 binary is not compiled with it. It means you may not get the full speed of your CPU.
    Traceback (most recent call last):
      File "detectron/tests/test_spatial_narrow_as_op.py", line 88, in <module>
        utils.c2.import_detectron_ops()
      File "/home/gene/detectron/lib/utils/c2.py", line 41, in import_detectron_ops
        detectron_ops_lib = envu.get_detectron_ops_lib()
      File "/home/gene/detectron/lib/utils/env.py", line 73, in get_detectron_ops_lib
        'version includes Detectron module').format(detectron_ops_lib)
    AssertionError: Detectron ops lib not found at '/usr/local/lib/python2.7/dist-packages/lib/libcaffe2_detectron_ops_gpu.so'; make sure that your Caffe2 version includes Detectron module
    

    But the detectron module is present in the modules folder. Do I need to modify CMakeLists somehow before installing caffe2 to make sure it gets included correctly?

    System information

    • Operating system: Ubuntu 16.04
    • Compiler version: gcc version 5.4.0 20160609 (Ubuntu 5.4.0-6ubuntu1~16.04.5)
    • CUDA version: 8.0
    • cuDNN version: 6.0.21
    • NVIDIA driver version:
    • GPU models (for all devices if they are not all the same): 4x Tesla k80
    • PYTHONPATH environment variable: /usr/local:/home/ubuntu/caffe2/build
    • python --version output: 2.7.12
  • Support exporting for CPU Mask & Keypoint nets

    Support exporting for CPU Mask & Keypoint nets

    Prerequisite : ~~#372~~ Purpose : enable exporting all the models for CPU by exporting 2 separate nets : one for the bboxes and one for the rest of the inference.

    Two main modifications

    • Refactor the main() : it will call a function convert_to_pb for each sub network
    • run_model_pb : always do the inference for bbox and then call mask or keypoint part if needed. The exact same approach is adopted.

    Then helper functions are only lightly modified to fit with the new objective to export 2 pb files

  • How to visualize the network structure

    How to visualize the network structure

    Hi, Is there any easy way to visualize the network? like Netscope for caffe? I can use the net_drawer in caffe2, but found it;' so hard to read the network?

  • there are no output .pdf when successfully complier demo files?

    there are no output .pdf when successfully complier demo files?

    [email protected]:/detectron# python2 tools/infer_simple.py \

    --cfg configs/12_2017_baselines/e2e_mask_rcnn_R-101-FPN_2x.yaml \
    --output-dir demo/output \
    --image-ext jpg \
    --wts https://s3-us-west-2.amazonaws.com/detectron/35861858/12_2017_baselines/e2e_mask_rcnn_R-101-FPN_2x.yaml.02_32_51.SgT4y1cO/output/train/coco_2014_train:coco_2014_valminusminival/generalized_rcnn/model_final.pkl \
    demo
    

    E0202 10:06:27.787480 38 init_intrinsics_check.cc:54] CPU feature avx is present on your machine, but the Caffe2 binary is not compiled with it. It means you may not get the full speed of your CPU. E0202 10:06:27.787498 38 init_intrinsics_check.cc:54] CPU feature avx2 is present on your machine, but the Caffe2 binary is not compiled with it. It means you may not get the full speed of your CPU. E0202 10:06:27.787502 38 init_intrinsics_check.cc:54] CPU feature fma is present on your machine, but the Caffe2 binary is not compiled with it. It means you may not get the full speed of your CPU. WARNING cnn.py: 40: [====DEPRECATE WARNING====]: you are creating an object from CNNModelHelper class which will be deprecated soon. Please use ModelHelper object with brew module. For more information, please refer to caffe2.ai and python/brew.py, python/brew_test.py for more information. INFO net.py: 57: Loading weights from: /tmp/detectron-download-cache/35861858/12_2017_baselines/e2e_mask_rcnn_R-101-FPN_2x.yaml.02_32_51.SgT4y1cO/output/train/coco_2014_train:coco_2014_valminusminival/generalized_rcnn/model_final.pkl I0202 10:06:32.272874 38 net_dag_utils.cc:118] Operator graph pruning prior to chain compute took: 0.000144569 secs I0202 10:06:32.273200 38 net_dag.cc:61] Number of parallel execution chains 63 Number of operators = 402 I0202 10:06:32.290997 38 net_dag_utils.cc:118] Operator graph pruning prior to chain compute took: 0.000129367 secs I0202 10:06:32.291281 38 net_dag.cc:61] Number of parallel execution chains 30 Number of operators = 358 I0202 10:06:32.292923 38 net_dag_utils.cc:118] Operator graph pruning prior to chain compute took: 1.0203e-05 secs I0202 10:06:32.292951 38 net_dag.cc:61] Number of parallel execution chains 5 Number of operators = 18 INFO infer_simple.py: 111: Processing demo/18124840932_e42b3e377c_k.jpg -> demo/output/18124840932_e42b3e377c_k.jpg.pdf INFO infer_simple.py: 119: Inference time: 0.872s INFO infer_simple.py: 121: | im_detect_bbox: 0.824s INFO infer_simple.py: 121: | misc_mask: 0.023s INFO infer_simple.py: 121: | im_detect_mask: 0.023s INFO infer_simple.py: 121: | misc_bbox: 0.002s INFO infer_simple.py: 124: \ Note: inference on the first image will be slower than the rest (caches and auto-tuning need to warm up) INFO infer_simple.py: 111: Processing demo/17790319373_bd19b24cfc_k.jpg -> demo/output/17790319373_bd19b24cfc_k.jpg.pdf INFO infer_simple.py: 119: Inference time: 0.380s INFO infer_simple.py: 121: | im_detect_bbox: 0.307s INFO infer_simple.py: 121: | misc_mask: 0.040s INFO infer_simple.py: 121: | im_detect_mask: 0.031s INFO infer_simple.py: 121: | misc_bbox: 0.002s INFO infer_simple.py: 111: Processing demo/19064748793_bb942deea1_k.jpg -> demo/output/19064748793_bb942deea1_k.jpg.pdf INFO infer_simple.py: 119: Inference time: 0.320s INFO infer_simple.py: 121: | im_detect_bbox: 0.210s INFO infer_simple.py: 121: | misc_mask: 0.058s INFO infer_simple.py: 121: | im_detect_mask: 0.050s INFO infer_simple.py: 121: | misc_bbox: 0.002s INFO infer_simple.py: 111: Processing demo/34501842524_3c858b3080_k.jpg -> demo/output/34501842524_3c858b3080_k.jpg.pdf INFO infer_simple.py: 119: Inference time: 0.239s INFO infer_simple.py: 121: | im_detect_bbox: 0.215s INFO infer_simple.py: 121: | misc_mask: 0.012s INFO infer_simple.py: 121: | im_detect_mask: 0.010s INFO infer_simple.py: 121: | misc_bbox: 0.002s INFO infer_simple.py: 111: Processing demo/15673749081_767a7fa63a_k.jpg -> demo/output/15673749081_767a7fa63a_k.jpg.pdf INFO infer_simple.py: 119: Inference time: 0.324s INFO infer_simple.py: 121: | im_detect_bbox: 0.220s INFO infer_simple.py: 121: | misc_mask: 0.056s INFO infer_simple.py: 121: | im_detect_mask: 0.045s INFO infer_simple.py: 121: | misc_bbox: 0.002s INFO infer_simple.py: 111: Processing demo/16004479832_a748d55f21_k.jpg -> demo/output/16004479832_a748d55f21_k.jpg.pdf INFO infer_simple.py: 119: Inference time: 0.238s INFO infer_simple.py: 121: | im_detect_bbox: 0.211s INFO infer_simple.py: 121: | misc_mask: 0.015s INFO infer_simple.py: 121: | im_detect_mask: 0.009s INFO infer_simple.py: 121: | misc_bbox: 0.002s INFO infer_simple.py: 111: Processing demo/24274813513_0cfd2ce6d0_k.jpg -> demo/output/24274813513_0cfd2ce6d0_k.jpg.pdf INFO infer_simple.py: 119: Inference time: 0.250s INFO infer_simple.py: 121: | im_detect_bbox: 0.215s INFO infer_simple.py: 121: | misc_mask: 0.017s INFO infer_simple.py: 121: | im_detect_mask: 0.016s INFO infer_simple.py: 121: | misc_bbox: 0.002s INFO infer_simple.py: 111: Processing demo/33823288584_1d21cf0a26_k.jpg -> demo/output/33823288584_1d21cf0a26_k.jpg.pdf INFO infer_simple.py: 119: Inference time: 0.417s INFO infer_simple.py: 121: | im_detect_bbox: 0.313s INFO infer_simple.py: 121: | misc_mask: 0.058s INFO infer_simple.py: 121: | im_detect_mask: 0.044s INFO infer_simple.py: 121: | misc_bbox: 0.002s INFO infer_simple.py: 111: Processing demo/33887522274_eebd074106_k.jpg -> demo/output/33887522274_eebd074106_k.jpg.pdf INFO infer_simple.py: 119: Inference time: 0.224s INFO infer_simple.py: 121: | im_detect_bbox: 0.202s INFO infer_simple.py: 121: | misc_mask: 0.011s INFO infer_simple.py: 121: | im_detect_mask: 0.009s INFO infer_simple.py: 121: | misc_bbox: 0.002s

    demo/output folder got no pdf files.

  • ImportError: cannot import name task_evaluation

    ImportError: cannot import name task_evaluation

    Traceback (most recent call last): File "tools/infer_simple.py", line 42, in import core.test_engine as infer_engine File "/home/user523/zjs/detectron/lib/core/test_engine.py", line 36, in from datasets import task_evaluation ImportError: cannot import name task_evaluation

    I have added detectron/lib to pythonpath,but it still can not work.

  • OSError: /usr/local/lib/libcaffe2_detectron_ops_gpu.so: undefined symbol:

    OSError: /usr/local/lib/libcaffe2_detectron_ops_gpu.so: undefined symbol:

    I tried some solutions in issues, like exporting python path, but it didn't work for me.

    /home/chopin/anaconda3/envs/caffe2/caffe2/build/caffe2/python to ~/.bashrc and then pip install utils .

    I saw somewhere talking about the opencv version. I have 3.3.1 and the required version is 3.4.1. But caffe2 installed through conda (caffe2-cuda9.0-cudnn7) doesn't work with opencv 3.4.1.

    Expected results

    I was running this line:

    python launch.py --cfg configs/video/2d_best/01_R101_best_hungarian-4GPU.yaml --mode test TEST.WEIGHTS pretrained_models/configs/video/2d_best/01_R101_best_hungarian.yaml/model_final.pkl

    Actual results

    And then I ran into this error:

    Traceback (most recent call last): File "tools/test_net.py", line 33, in utils.c2.import_detectron_ops() File "/home/jingweim/DetectAndTrack/lib/utils/c2.py", line 50, in import_detectron_ops dyndep.InitOpsLibrary(detectron_ops_lib) File "/home/jingweim/anaconda2/envs/detect_and_track/lib/python2.7/site-packages/caffe2/python/dyndep.py", line 35, in InitOpsLibrary _init_impl(name) File "/home/jingweim/anaconda2/envs/detect_and_track/lib/python2.7/site-packages/caffe2/python/dyndep.py", line 48, in _init_impl ctypes.CDLL(path) File "/home/jingweim/anaconda2/envs/detect_and_track/lib/python2.7/ctypes/init.py", line 366, in init self._handle = _dlopen(self._name, mode) OSError: /usr/local/lib/libcaffe2_detectron_ops_gpu.so: undefined symbol: _ZN6caffe28TypeMeta2IdINS_6TensorINS_11CUDAContextEEEEENS_11CaffeTypeIdEv

    System information

    • Operating system: Ubuntu 16.04
    • Compiler version: gcc 5.4
    • CUDA version: 9.0
    • cuDNN version: 7.0
    • NVIDIA driver version: 396
    • GPU models (for all devices if they are not all the same): TITAN XP
    • PYTHONPATH environment variable: /home/jingweim/anaconda2/envs/detect_and_track/include/caffe2/python:/usr/bin/python
    • python --version output: Python 2.7.15 :: Anaconda custom (64-bit)
    • Anything else that seems relevant: opencv 3.3.1
  • Is there any script for batch inference?

    Is there any script for batch inference?

    detectron/tools/infer_simple.py is a clean and tiny inference demo for the case when batchsize equals to 1.

    For efficient inference, I want to detect several images at the same time.

    Could anyone give me some advice on implementing "batchsize > 1" inference demo?

  • How to train Faster R-CNN on my own custom dataset?

    How to train Faster R-CNN on my own custom dataset?

    Hello. I want to:

    1- train Faster RCNN on my own custom dataset. 2- use the pre-trained Faster RCNN on the VOC2007 as the initial weights to train it then on my own custom dataset. 3- modify the RPN network with different loss functions that I have come up with.

    I will greatly appreciate it if you could help me/let me know how to achieve the above goals.

  • libcaffe2_detectron_ops_gpu.so运行慢

    libcaffe2_detectron_ops_gpu.so运行慢

    PLEASE FOLLOW THESE INSTRUCTIONS BEFORE POSTING

    1. Please thoroughly read README.md, INSTALL.md, GETTING_STARTED.md, and FAQ.md
    2. Please search existing open and closed issues in case your issue has already been reported
    3. Please try to debug the issue in case you can solve it on your own before posting

    After following steps 1-3 above and agreeing to provide the detailed information requested below, you may continue with posting your issue

    (Delete this line and the text above it.)

    Expected results

    What did you expect to see?

    Actual results

    What did you observe instead?

    Detailed steps to reproduce

    E.g.:

    The command that you ran
    

    System information

    • Operating system: ?
    • Compiler version: ?
    • CUDA version: ?
    • cuDNN version: ?
    • NVIDIA driver version: ?
    • GPU models (for all devices if they are not all the same): ?
    • PYTHONPATH environment variable: ?
    • python --version output: ?
    • Anything else that seems relevant: ?
  • KeyError: u'Key TEST.SCALES was renamed to TEST.SCALE; please update your config. Note: Also convert from a tuple, e.g. (600, ), to a integer, e.g. 600.'

    KeyError: u'Key TEST.SCALES was renamed to TEST.SCALE; please update your config. Note: Also convert from a tuple, e.g. (600, ), to a integer, e.g. 600.'

    [email protected] /m/b/2/d/detectron-traffic-signs (villard) [1]> python tools/infer_simple.py --cfg configs/12_2017_baselines/e2e_mask_rcnn_R-101-FPN_2x.yaml --output-dir /tmp/detectron-visualizations --image-ext jpg --wts https://s3-us-west-2.amazonaws.com/detectron/35861858/12_2017_baselines/e2e_mask_rcnn_R-101-FPN_2x.yaml.02_32_51.SgT4y1cO/output/train/coco_2014_train:coco_2014_valminusminival/generalized_rcnn/model_final.pkl demo Found Detectron ops lib: /home/dyx/anaconda3/envs/caffe2_install/lib/python2.7/site-packages/torch/lib/libcaffe2_detectron_ops_gpu.so [E init_intrinsics_check.cc:43] CPU feature avx is present on your machine, but the Caffe2 binary is not compiled with it. It means you may not get the full speed of your CPU. [E init_intrinsics_check.cc:43] CPU feature avx2 is present on your machine, but the Caffe2 binary is not compiled with it. It means you may not get the full speed of your CPU. [E init_intrinsics_check.cc:43] CPU feature fma is present on your machine, but the Caffe2 binary is not compiled with it. It means you may not get the full speed of your CPU. /mnt/big_disk/2020/dyx/detectron/detectron/core/config.py:1145: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details. return envu.yaml_load(cfg_to_load) Traceback (most recent call last): File "tools/infer_simple.py", line 149, in main(args) File "tools/infer_simple.py", line 97, in main merge_cfg_from_file(args.cfg) File "/mnt/big_disk/2020/dyx/detectron/detectron/core/config.py", line 1152, in merge_cfg_from_file _merge_a_into_b(yaml_cfg, __C) File "/mnt/big_disk/2020/dyx/detectron/detectron/core/config.py", line 1212, in _merge_a_into_b _merge_a_into_b(v, b[k], stack=stack_push) File "/mnt/big_disk/2020/dyx/detectron/detectron/core/config.py", line 1200, in _merge_a_into_b _raise_key_rename_error(full_key) File "/mnt/big_disk/2020/dyx/detectron/detectron/core/config.py", line 1241, in _raise_key_rename_error format(full_key, new_key, msg) KeyError: u'Key TEST.SCALES was renamed to TEST.SCALE; please update your config. Note: Also convert from a tuple, e.g. (600, ), to a integer, e.g. 600.'

    Who can help me? thanks

  • Detectron2 In-Place One-to-Many Augmentations

    Detectron2 In-Place One-to-Many Augmentations

    Hi there! This is a simple question: I haven't been able to find documentation for applying in-place augmentations that can produce multiple transformed "images" from a single image. It appears that the current system simply chooses some augmentation, applies it to the image, and moves onto the next one.

    Am I missing something, and if not, is there any way this feature can be implemented with Detectron? Thank you!

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

Mask R-CNN for Object Detection and Segmentation This is an implementation of Mask R-CNN on Python 3, Keras, and TensorFlow. The model generates bound

Jun 28, 2022
The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on dealing with medical images.
The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on dealing with medical images.

The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on dealing with medical images.

Jun 30, 2022
Face Mask Detection is a project to determine whether someone is wearing mask or not, using deep neural network.
Face Mask Detection is a project to determine whether someone is wearing mask or not, using deep neural network.

face-mask-detection Face Mask Detection is a project to determine whether someone is wearing mask or not, using deep neural network. It contains 3 scr

Jan 18, 2022
DCT-Mask: Discrete Cosine Transform Mask Representation for Instance Segmentation

DCT-Mask: Discrete Cosine Transform Mask Representation for Instance Segmentation This project hosts the code for implementing the DCT-MASK algorithms

May 5, 2022
The Face Mask recognition system uses AI technology to detect the person with or without a mask.
The Face Mask recognition system uses AI technology to detect the person with or without a mask.

Face Mask Detection Face Mask Detection system built with OpenCV, Keras/TensorFlow using Deep Learning and Computer Vision concepts in order to detect

Apr 5, 2022
一个目标检测的通用框架(不需要cuda编译),支持Yolo全系列(v2~v5)、EfficientDet、RetinaNet、Cascade-RCNN等SOTA网络。
一个目标检测的通用框架(不需要cuda编译),支持Yolo全系列(v2~v5)、EfficientDet、RetinaNet、Cascade-RCNN等SOTA网络。

一个目标检测的通用框架(不需要cuda编译),支持Yolo全系列(v2~v5)、EfficientDet、RetinaNet、Cascade-RCNN等SOTA网络。

Jun 22, 2022
An implementation of RetinaNet in PyTorch.
An implementation of RetinaNet in PyTorch.

RetinaNet An implementation of RetinaNet in PyTorch. Installation Training COCO 2017 Pascal VOC Custom Dataset Evaluation Todo Credits Installation In

Jun 18, 2022
This is a Keras implementation of a CNN for estimating age, gender and mask from a camera.

face-detector-age-gender This is a Keras implementation of a CNN for estimating age, gender and mask from a camera. Before run face detector app, expr

Dec 4, 2021
Boundary-preserving Mask R-CNN (ECCV 2020)
Boundary-preserving Mask R-CNN (ECCV 2020)

BMaskR-CNN This code is developed on Detectron2 Boundary-preserving Mask R-CNN ECCV 2020 Tianheng Cheng, Xinggang Wang, Lichao Huang, Wenyu Liu Video

May 31, 2022
[NeurIPS 2021] A weak-shot object detection approach by transferring semantic similarity and mask prior.

[NeurIPS 2021] A weak-shot object detection approach by transferring semantic similarity and mask prior.

Jun 13, 2022
This is an example of object detection on Micro bacterium tuberculosis using Mask-RCNN
This is an example of object detection on Micro bacterium tuberculosis using Mask-RCNN

Mask-RCNN on Mycobacterium tuberculosis This is an example of object detection on Mycobacterium Tuberculosis using Mask RCNN. Implement of Mask R-CNN

Sep 16, 2021
This is an example of object detection on Micro bacterium tuberculosis using Mask-RCNN
This is an example of object detection on Micro bacterium tuberculosis using Mask-RCNN

Mask-RCNN on Mycobacterium tuberculosis This is an example of object detection on Mycobacterium Tuberculosis using Mask RCNN. Implement of Mask R-CNN

Sep 16, 2021
NFT-Price-Prediction-CNN - Using visual feature extraction, prices of NFTs are predicted via CNN (Alexnet and Resnet) architectures.

NFT-Price-Prediction-CNN - Using visual feature extraction, prices of NFTs are predicted via CNN (Alexnet and Resnet) architectures.

Feb 14, 2022
This is an open source library implementing hyperbox-based machine learning algorithms
This is an open source library implementing hyperbox-based machine learning algorithms

hyperbox-brain is a Python open source toolbox implementing hyperbox-based machine learning algorithms built on top of scikit-learn and is distributed

May 19, 2022
BisQue is a web-based platform designed to provide researchers with organizational and quantitative analysis tools for 5D image data. Users can extend BisQue by implementing containerized ML workflows.
BisQue is a web-based platform designed to provide researchers with organizational and quantitative analysis tools for 5D image data. Users can extend BisQue by implementing containerized ML workflows.

Overview BisQue is a web-based platform specifically designed to provide researchers with organizational and quantitative analysis tools for up to 5D

Jun 29, 2022
Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection

Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection

Jun 6, 2022
Sparse R-CNN: End-to-End Object Detection with Learnable Proposals, CVPR2021
 Sparse R-CNN: End-to-End Object Detection with Learnable Proposals, CVPR2021

End-to-End Object Detection with Learnable Proposal, CVPR2021

Jul 5, 2022
Group R-CNN for Point-based Weakly Semi-supervised Object Detection (CVPR2022)
Group R-CNN for Point-based Weakly Semi-supervised Object Detection (CVPR2022)

Group R-CNN for Point-based Weakly Semi-supervised Object Detection (CVPR2022) By Shilong Zhang*, Zhuoran Yu*, Liyang Liu*, Xinjiang Wang, Aojun Zhou,

Jun 23, 2022
Pytorch implementations of popular off-policy multi-agent reinforcement learning algorithms, including QMix, VDN, MADDPG, and MATD3.

Off-Policy Multi-Agent Reinforcement Learning (MARL) Algorithms This repository contains implementations of various off-policy multi-agent reinforceme

Jun 22, 2022