FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19)

Overview

FCOS: Fully Convolutional One-Stage Object Detection

This project hosts the code for implementing the FCOS algorithm for object detection, as presented in our paper:

FCOS: Fully Convolutional One-Stage Object Detection;
Zhi Tian, Chunhua Shen, Hao Chen, and Tong He;
In: Proc. Int. Conf. Computer Vision (ICCV), 2019.
arXiv preprint arXiv:1904.01355 

The full paper is available at: https://arxiv.org/abs/1904.01355.

Implementation based on Detectron2 is included in AdelaiDet.

A real-time model with 46FPS and 40.3 in AP on COCO minival is also available here.

Highlights

  • Totally anchor-free: FCOS completely avoids the complicated computation related to anchor boxes and all hyper-parameters of anchor boxes.
  • Better performance: The very simple one-stage detector achieves much better performance (38.7 vs. 36.8 in AP with ResNet-50) than Faster R-CNN. Check out more models and experimental results here.
  • Faster training and testing: With the same hardwares and backbone ResNet-50-FPN, FCOS also requires less training hours (6.5h vs. 8.8h) than Faster R-CNN. FCOS also takes 12ms less inference time per image than Faster R-CNN (44ms vs. 56ms).
  • State-of-the-art performance: Our best model based on ResNeXt-64x4d-101 and deformable convolutions achieves 49.0% in AP on COCO test-dev (with multi-scale testing).

Updates

  • FCOS with Fast And Diverse (FAD) neural architecture search is avaliable at FAD. (30/10/2020)
  • Script for exporting ONNX models. (21/11/2019)
  • New NMS (see #165) speeds up ResNe(x)t based models by up to 30% and MobileNet based models by 40%, with exactly the same performance. Check out here. (12/10/2019)
  • New models with much improved performance are released. The best model achieves 49% in AP on COCO test-dev with multi-scale testing. (11/09/2019)
  • FCOS with VoVNet backbones is available at VoVNet-FCOS. (08/08/2019)
  • A trick of using a small central region of the BBox for training improves AP by nearly 1 point as shown here. (23/07/2019)
  • FCOS with HRNet backbones is available at HRNet-FCOS. (03/07/2019)
  • FCOS with AutoML searched FPN (R50, R101, ResNeXt101 and MobileNetV2 backbones) is available at NAS-FCOS. (30/06/2019)
  • FCOS has been implemented in mmdetection. Many thanks to @yhcao6 and @hellock. (17/05/2019)

Required hardware

We use 8 Nvidia V100 GPUs.
But 4 1080Ti GPUs can also train a fully-fledged ResNet-50-FPN based FCOS since FCOS is memory-efficient.

Installation

Testing-only installation

For users who only want to use FCOS as an object detector in their projects, they can install it by pip. To do so, run:

pip install torch  # install pytorch if you do not have it
pip install git+https://github.com/tianzhi0549/FCOS.git
# run this command line for a demo 
fcos https://github.com/tianzhi0549/FCOS/raw/master/demo/images/COCO_val2014_000000000885.jpg

Please check out here for the interface usage.

For a complete installation

This FCOS implementation is based on maskrcnn-benchmark. Therefore the installation is the same as original maskrcnn-benchmark.

Please check INSTALL.md for installation instructions. You may also want to see the original README.md of maskrcnn-benchmark.

A quick demo

Once the installation is done, you can follow the below steps to run a quick demo.

# assume that you are under the root directory of this project,
# and you have activated your virtual environment if needed.
wget https://cloudstor.aarnet.edu.au/plus/s/ZSAqNJB96hA71Yf/download -O FCOS_imprv_R_50_FPN_1x.pth
python demo/fcos_demo.py

Inference

The inference command line on coco minival split:

python tools/test_net.py \
    --config-file configs/fcos/fcos_imprv_R_50_FPN_1x.yaml \
    MODEL.WEIGHT FCOS_imprv_R_50_FPN_1x.pth \
    TEST.IMS_PER_BATCH 4    

Please note that:

  1. If your model's name is different, please replace FCOS_imprv_R_50_FPN_1x.pth with your own.
  2. If you enounter out-of-memory error, please try to reduce TEST.IMS_PER_BATCH to 1.
  3. If you want to evaluate a different model, please change --config-file to its config file (in configs/fcos) and MODEL.WEIGHT to its weights file.
  4. Multi-GPU inference is available, please refer to #78.
  5. We improved the postprocess efficiency by using multi-label nms (see #165), which saves 18ms on average. The inference metric in the following tables has been updated accordingly.

Models

For your convenience, we provide the following trained models (more models are coming soon).

ResNe(x)ts:

All ResNe(x)t based models are trained with 16 images in a mini-batch and frozen batch normalization (i.e., consistent with models in maskrcnn_benchmark).

Model Multi-scale training Testing time / im AP (minival) Link
FCOS_imprv_R_50_FPN_1x No 44ms 38.7 download
FCOS_imprv_dcnv2_R_50_FPN_1x No 54ms 42.3 download
FCOS_imprv_R_101_FPN_2x Yes 57ms 43.0 download
FCOS_imprv_dcnv2_R_101_FPN_2x Yes 73ms 45.6 download
FCOS_imprv_X_101_32x8d_FPN_2x Yes 110ms 44.0 download
FCOS_imprv_dcnv2_X_101_32x8d_FPN_2x Yes 143ms 46.4 download
FCOS_imprv_X_101_64x4d_FPN_2x Yes 112ms 44.7 download
FCOS_imprv_dcnv2_X_101_64x4d_FPN_2x Yes 144ms 46.6 download

Note that imprv denotes improvements in our paper Table 3. These almost cost-free changes improve the performance by ~1.5% in total. Thus, we highly recommend to use them. The following are the original models presented in our initial paper.

Model Multi-scale training Testing time / im AP (minival) AP (test-dev) Link
FCOS_R_50_FPN_1x No 45ms 37.1 37.4 download
FCOS_R_101_FPN_2x Yes 59ms 41.4 41.5 download
FCOS_X_101_32x8d_FPN_2x Yes 110ms 42.5 42.7 download
FCOS_X_101_64x4d_FPN_2x Yes 113ms 43.0 43.2 download

MobileNets:

We update batch normalization for MobileNet based models. If you want to use SyncBN, please install pytorch 1.1 or later.

Model Training batch size Multi-scale training Testing time / im AP (minival) Link
FCOS_syncbn_bs32_c128_MNV2_FPN_1x 32 No 26ms 30.9 download
FCOS_syncbn_bs32_MNV2_FPN_1x 32 No 33ms 33.1 download
FCOS_bn_bs16_MNV2_FPN_1x 16 No 44ms 31.0 download

[1] 1x and 2x mean the model is trained for 90K and 180K iterations, respectively.
[2] All results are obtained with a single model and without any test time data augmentation such as multi-scale, flipping and etc..
[3] c128 denotes the model has 128 (instead of 256) channels in towers (i.e., MODEL.RESNETS.BACKBONE_OUT_CHANNELS in config).
[4] dcnv2 denotes deformable convolutional networks v2. Note that for ResNet based models, we apply deformable convolutions from stage c3 to c5 in backbones. For ResNeXt based models, only stage c4 and c5 use deformable convolutions. All models use deformable convolutions in the last layer of detector towers.
[5] The model FCOS_imprv_dcnv2_X_101_64x4d_FPN_2x with multi-scale testing achieves 49.0% in AP on COCO test-dev. Please use TEST.BBOX_AUG.ENABLED True to enable multi-scale testing.

Training

The following command line will train FCOS_imprv_R_50_FPN_1x on 8 GPUs with Synchronous Stochastic Gradient Descent (SGD):

python -m torch.distributed.launch \
    --nproc_per_node=8 \
    --master_port=$((RANDOM + 10000)) \
    tools/train_net.py \
    --config-file configs/fcos/fcos_imprv_R_50_FPN_1x.yaml \
    DATALOADER.NUM_WORKERS 2 \
    OUTPUT_DIR training_dir/fcos_imprv_R_50_FPN_1x

Note that:

  1. If you want to use fewer GPUs, please change --nproc_per_node to the number of GPUs. No other settings need to be changed. The total batch size does not depends on nproc_per_node. If you want to change the total batch size, please change SOLVER.IMS_PER_BATCH in configs/fcos/fcos_R_50_FPN_1x.yaml.
  2. The models will be saved into OUTPUT_DIR.
  3. If you want to train FCOS with other backbones, please change --config-file.
  4. If you want to train FCOS on your own dataset, please follow this instruction #54.
  5. Now, training with 8 GPUs and 4 GPUs can have the same performance. Previous performance gap was because we did not synchronize num_pos between GPUs when computing loss.

ONNX

Please refer to the directory onnx for an example of exporting the model to ONNX. A converted model can be downloaded here. We recommend you to use PyTorch >= 1.4.0 (or nightly) and torchvision >= 0.5.0 (or nightly) for ONNX models.

Contributing to the project

Any pull requests or issues are welcome.

Citations

Please consider citing our paper in your publications if the project helps your research. BibTeX reference is as follows.

@inproceedings{tian2019fcos,
  title   =  {{FCOS}: Fully Convolutional One-Stage Object Detection},
  author  =  {Tian, Zhi and Shen, Chunhua and Chen, Hao and He, Tong},
  booktitle =  {Proc. Int. Conf. Computer Vision (ICCV)},
  year    =  {2019}
}
@article{tian2021fcos,
  title   =  {{FCOS}: A Simple and Strong Anchor-free Object Detector},
  author  =  {Tian, Zhi and Shen, Chunhua and Chen, Hao and He, Tong},
  booktitle =  {IEEE T. Pattern Analysis and Machine Intelligence (TPAMI)},
  year    =  {2021}
}

Acknowledgments

We would like to thank @yqyao for the tricks of center sampling and GIoU. We also thank @bearcatt for his suggestion of positioning the center-ness branch with box regression (refer to #89).

License

For academic use, this project is licensed under the 2-clause BSD License - see the LICENSE file for details. For commercial use, please contact the authors.

Comments
  • How to train my own datasets (format is like coco datasets)

    How to train my own datasets (format is like coco datasets)

    Now I have converted my datasets format to coco format, andI want to train my own datasets using FCOS. I referenced GETTING_STARTED.md in mmdetection repo, and there is a tutorial in mmdetection repo to train my own datasets. But in FCOS repo, I find the file FCOS/maskrcnn_benchmark/data/datasets/coco.py is different like /mmdetection/mmdet/datasets/coco.py. Is there any suggestions?

    opened by Xavier-Zeng 51
  • Do you have a plan for instance segmentation?

    Do you have a plan for instance segmentation?

    Hi,

    In your paper,

    "The proposed detector can be immediately extended to solve other vision tasks with minimal modification, including instance segmentation and key-point detection."

    is described.

    Do you have a plan to extend for instance segmentation such as Mask R-CNN ?

    opened by stigma0617 17
  • loss nan

    loss nan

    I try to train coco, but loss is nan. this is my training script:

    CUDA_VISIBLE_DEVICES=1,3,4,5 python -m torch.distributed.launch \
        --nproc_per_node=4 \
        --master_port=$((RANDOM + 10000)) \
        tools/train_net.py \
        --skip-test \
        --config-file configs/fcos/fcos_R_50_FPN_1x.yaml \
        DATALOADER.NUM_WORKERS 2 \
        OUTPUT_DIR training_dir/fcos_R_50_FPN_1x
    

    this is my result

    2019-04-16 09:19:17,383 maskrcnn_benchmark.trainer INFO: Start training
    2019-04-16 09:19:33,719 maskrcnn_benchmark.trainer INFO: eta: 20:24:50  iter: 20  loss: 4.2079 (4.8923)  loss_centerness: 0.6670 (0.6685)  loss_cls: 0.9797 (0.9730)  loss_reg: 2.5527 (3.2508)  time: 0.6882 (0.8167)  data: 0.0219 (0.0651)  lr: 0.003333  max mem: 7051
    2019-04-16 09:19:48,380 maskrcnn_benchmark.trainer INFO: eta: 19:21:49  iter: 40  loss: 3.2185 (4.0965)  loss_centerness: 0.6607 (0.6652)  loss_cls: 0.8450 (0.9074)  loss_reg: 1.6475 (2.5240)  time: 0.6947 (0.7749)  data: 0.0265 (0.0462)  lr: 0.003333  max mem: 7051
    2019-04-16 09:20:02,270 maskrcnn_benchmark.trainer INFO: eta: 18:41:23  iter: 60  loss: 2.9554 (3.7219)  loss_centerness: 0.6592 (0.6634)  loss_cls: 0.7685 (0.8647)  loss_reg: 1.5265 (2.1938)  time: 0.6972 (0.7481)  data: 0.0283 (0.0399)  lr: 0.003333  max mem: 7051
    2019-04-16 09:20:15,608 maskrcnn_benchmark.trainer INFO: eta: 18:10:43  iter: 80  loss: 2.8321 (nan)  loss_centerness: 0.6582 (nan)  loss_cls: 0.7013 (nan)  loss_reg: 1.4726 (nan)  time: 0.6690 (0.7278)  data: 0.0277 (0.0374)  lr: 0.003333  max mem: 7051
    2019-04-16 09:20:28,939 maskrcnn_benchmark.trainer INFO: eta: 17:52:08  iter: 100  loss: nan (nan)  loss_centerness: nan (nan)  loss_cls: nan (nan)  loss_reg: nan (nan)  time: 0.6653 (0.7156)  data: 0.0262 (0.0353)  lr: 0.003333  max mem: 7051
    

    I have tried for 3 times, always nan. what's wrong with me?

    opened by bei-startdt 16
  • box target?

    box target?

    Does the network output the box offsets (l*,r*,t*,b*) normalized by image size? I tried to train fcos in another task and find the regression branch's output value is unstable.

    opened by YongtaoGe 15
  • comparison of inference time to Faster R-CNN

    comparison of inference time to Faster R-CNN

    Hi,

    I measured inference time and compare with Faster R-CNN on Titan Xp

    CUDA v9.0 pytorch 1.1.0

    | meta-arch. | backbone | AP(minival) |inf. time(ms) | |:---:|:---:|:---:|:---:| | Faster R-CNN | R-50 | 36.8| 78 | | FCOS | R-50 | 37.1| 98 |

    Why anchor-free FCOS is slower than anchor-based Faster R-CNN ??

    Have you profiled which component is time bottleneck?

    opened by stigma0617 13
  • FCOS_R_50_FPN_1x mAP 36.59

    FCOS_R_50_FPN_1x mAP 36.59

    Hey, I have run your baseline config "fcos_R_50_FPN_1x.yaml" without any change, but only got 36.59 mAP as reported in 4.1.2 in the paper. But I noticed that you report 37.1 mAP of the FCOS_R_50_FPN_1x baseline in README.md. Is there any small details I have not noticed? Thanks!

    opened by WitLes 12
  • error in install step,  python setup.py

    error in install step, python setup.py

    Hello, I have met a problem when I install that. When I run python setup.py build develop, there are some errors. Could you help me? Thank you!

    running build running build_py running build_ext building 'maskrcnn_benchmark._C' extension gcc -pthread -B /home/travail/miniconda3/envs/FCOS/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_CUDA -I/home/travail/FCOS-master/FCOS/maskrcnn_benchmark/csrc -I/home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include -I/home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/TH -I/home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/THC -I/usr/local/cuda/include -I/home/travail/miniconda3/envs/FCOS/include/python3.7m -c /home/travail/FCOS-master/FCOS/maskrcnn_benchmark/csrc/vision.cpp -o build/temp.linux-x86_64-3.7/home/travail/FCOS-master/FCOS/maskrcnn_benchmark/csrc/vision.o -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++11 cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++ In file included from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/core/ScalarType.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/core/Scalar.h:9, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/core/Type.h:10, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/core/Tensor.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:2, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/Context.h:4, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/ATen.h:5, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:4, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/extension.h:4, from /home/travail/FCOS-master/FCOS/maskrcnn_benchmark/csrc/cpu/vision.h:3, from /home/travail/FCOS-master/FCOS/maskrcnn_benchmark/csrc/nms.h:3, from /home/travail/FCOS-master/FCOS/maskrcnn_benchmark/csrc/vision.cpp:2: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<_Tp>&) [with T = long int]’: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/core/TensorImpl.h:1399:34: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRef::Data’ from ‘std::initializer_list::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] 103 | : Data(Vec.begin() == Vec.end() ? static_cast<T*>(nullptr) : Vec.begin()), /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<_Tp>&) [with T = unsigned char]’: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/NativeFunctions.h:46:1: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRef::Data’ from ‘std::initializer_list::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<_Tp>&) [with T = signed char]’: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/NativeFunctions.h:46:1: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRef::Data’ from ‘std::initializer_list::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<_Tp>&) [with T = short int]’: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/NativeFunctions.h:46:1: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRef::Data’ from ‘std::initializer_list::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<_Tp>&) [with T = int]’: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/NativeFunctions.h:46:1: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRef::Data’ from ‘std::initializer_list::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<_Tp>&) [with T = float]’: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/NativeFunctions.h:46:1: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRef::Data’ from ‘std::initializer_list::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<_Tp>&) [with T = double]’: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/NativeFunctions.h:46:1: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRef::Data’ from ‘std::initializer_list::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<_Tp>&) [with T = c10::qint8]’: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/NativeFunctions.h:46:1: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRefc10::qint8::Data’ from ‘std::initializer_listc10::qint8::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<_Tp>&) [with T = c10::quint8]’: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/NativeFunctions.h:46:1: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRefc10::quint8::Data’ from ‘std::initializer_listc10::quint8::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<_Tp>&) [with T = c10::qint32]’: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/NativeFunctions.h:46:1: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRefc10::qint32::Data’ from ‘std::initializer_listc10::qint32::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<_Tp>&) [with T = at::Tensor]’: /home/travail/FCOS-master/FCOS/maskrcnn_benchmark/csrc/nms.h:19:52: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRefat::Tensor::Data’ from ‘std::initializer_listat::Tensor::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] gcc -pthread -B /home/travail/miniconda3/envs/FCOS/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_CUDA -I/home/travail/FCOS-master/FCOS/maskrcnn_benchmark/csrc -I/home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include -I/home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/TH -I/home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/THC -I/usr/local/cuda/include -I/home/travail/miniconda3/envs/FCOS/include/python3.7m -c /home/travail/FCOS-master/FCOS/maskrcnn_benchmark/csrc/cpu/nms_cpu.cpp -o build/temp.linux-x86_64-3.7/home/travail/FCOS-master/FCOS/maskrcnn_benchmark/csrc/cpu/nms_cpu.o -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++11 cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++ In file included from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/ATen.h:9, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:4, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/extension.h:4, from /home/travail/FCOS-master/FCOS/maskrcnn_benchmark/csrc/cpu/vision.h:3, from /home/travail/FCOS-master/FCOS/maskrcnn_benchmark/csrc/cpu/nms_cpu.cpp:2: /home/travail/FCOS-master/FCOS/maskrcnn_benchmark/csrc/cpu/nms_cpu.cpp: In lambda function: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/Dispatch.h:128:56: warning: ‘c10::ScalarType detail::scalar_type(const at::DeprecatedTypeProperties&)’ is deprecated [-Wdeprecated-declarations] 128 | at::ScalarType _st = ::detail::scalar_type(the_type);
    | ^ /home/travail/FCOS-master/FCOS/maskrcnn_benchmark/csrc/cpu/nms_cpu.cpp:71:3: note: in expansion of macro ‘AT_DISPATCH_FLOATING_TYPES’ 71 | AT_DISPATCH_FLOATING_TYPES(dets.type(), "nms", [&] { | ^~~~~~~~~~~~~~~~~~~~~~~~~~ /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/Dispatch.h:56:23: note: declared here 56 | inline at::ScalarType scalar_type(const at::DeprecatedTypeProperties &t) { | ^~~~~~~~~~~ /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/Dispatch.h:128:56: warning: ‘c10::ScalarType detail::scalar_type(const at::DeprecatedTypeProperties&)’ is deprecated [-Wdeprecated-declarations] 128 | at::ScalarType _st = ::detail::scalar_type(the_type);
    | ^ /home/travail/FCOS-master/FCOS/maskrcnn_benchmark/csrc/cpu/nms_cpu.cpp:71:3: note: in expansion of macro ‘AT_DISPATCH_FLOATING_TYPES’ 71 | AT_DISPATCH_FLOATING_TYPES(dets.type(), "nms", [&] { | ^~~~~~~~~~~~~~~~~~~~~~~~~~ /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/Dispatch.h:56:23: note: declared here 56 | inline at::ScalarType scalar_type(const at::DeprecatedTypeProperties &t) { | ^~~~~~~~~~~ In file included from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/core/ScalarType.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/core/Scalar.h:9, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/core/Type.h:10, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/core/Tensor.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:2, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/Context.h:4, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/ATen.h:5, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:4, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/extension.h:4, from /home/travail/FCOS-master/FCOS/maskrcnn_benchmark/csrc/cpu/vision.h:3, from /home/travail/FCOS-master/FCOS/maskrcnn_benchmark/csrc/cpu/nms_cpu.cpp:2: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<_Tp>&) [with T = long int]’: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/core/TensorImpl.h:1399:34: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRef::Data’ from ‘std::initializer_list::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] 103 | : Data(Vec.begin() == Vec.end() ? static_cast<T*>(nullptr) : Vec.begin()), /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<_Tp>&) [with T = unsigned char]’: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/NativeFunctions.h:46:1: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRef::Data’ from ‘std::initializer_list::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<_Tp>&) [with T = signed char]’: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/NativeFunctions.h:46:1: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRef::Data’ from ‘std::initializer_list::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<_Tp>&) [with T = short int]’: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/NativeFunctions.h:46:1: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRef::Data’ from ‘std::initializer_list::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<_Tp>&) [with T = int]’: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/NativeFunctions.h:46:1: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRef::Data’ from ‘std::initializer_list::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<_Tp>&) [with T = float]’: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/NativeFunctions.h:46:1: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRef::Data’ from ‘std::initializer_list::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<_Tp>&) [with T = double]’: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/NativeFunctions.h:46:1: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRef::Data’ from ‘std::initializer_list::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<_Tp>&) [with T = c10::qint8]’: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/NativeFunctions.h:46:1: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRefc10::qint8::Data’ from ‘std::initializer_listc10::qint8::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<_Tp>&) [with T = c10::quint8]’: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/NativeFunctions.h:46:1: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRefc10::quint8::Data’ from ‘std::initializer_listc10::quint8::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<_Tp>&) [with T = c10::qint32]’: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/NativeFunctions.h:46:1: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRefc10::qint32::Data’ from ‘std::initializer_listc10::qint32::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] gcc -pthread -B /home/travail/miniconda3/envs/FCOS/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_CUDA -I/home/travail/FCOS-master/FCOS/maskrcnn_benchmark/csrc -I/home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include -I/home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/TH -I/home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/THC -I/usr/local/cuda/include -I/home/travail/miniconda3/envs/FCOS/include/python3.7m -c /home/travail/FCOS-master/FCOS/maskrcnn_benchmark/csrc/cpu/ROIAlign_cpu.cpp -o build/temp.linux-x86_64-3.7/home/travail/FCOS-master/FCOS/maskrcnn_benchmark/csrc/cpu/ROIAlign_cpu.o -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++11 cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++ In file included from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/ATen.h:9, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:4, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/extension.h:4, from /home/travail/FCOS-master/FCOS/maskrcnn_benchmark/csrc/cpu/vision.h:3, from /home/travail/FCOS-master/FCOS/maskrcnn_benchmark/csrc/cpu/ROIAlign_cpu.cpp:2: /home/travail/FCOS-master/FCOS/maskrcnn_benchmark/csrc/cpu/ROIAlign_cpu.cpp: In lambda function: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/Dispatch.h:128:56: warning: ‘c10::ScalarType detail::scalar_type(const at::DeprecatedTypeProperties&)’ is deprecated [-Wdeprecated-declarations] 128 | at::ScalarType st = ::detail::scalar_type(the_type);
    | ^ /home/travail/FCOS-master/FCOS/maskrcnn_benchmark/csrc/cpu/ROIAlign_cpu.cpp:242:3: note: in expansion of macro ‘AT_DISPATCH_FLOATING_TYPES’ 242 | AT_DISPATCH_FLOATING_TYPES(input.type(), "ROIAlign_forward", [&] { | ^~~~~~~~~~~~~~~~~~~~~~~~~~ /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/Dispatch.h:56:23: note: declared here 56 | inline at::ScalarType scalar_type(const at::DeprecatedTypeProperties &t) { | ^~~~~~~~~~~ /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/Dispatch.h:128:56: warning: ‘c10::ScalarType detail::scalar_type(const at::DeprecatedTypeProperties&)’ is deprecated [-Wdeprecated-declarations] 128 | at::ScalarType st = ::detail::scalar_type(the_type);
    | ^ /home/travail/FCOS-master/FCOS/maskrcnn_benchmark/csrc/cpu/ROIAlign_cpu.cpp:242:3: note: in expansion of macro ‘AT_DISPATCH_FLOATING_TYPES’ 242 | AT_DISPATCH_FLOATING_TYPES(input.type(), "ROIAlign_forward", [&] { | ^~~~~~~~~~~~~~~~~~~~~~~~~~ /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/Dispatch.h:56:23: note: declared here 56 | inline at::ScalarType scalar_type(const at::DeprecatedTypeProperties &t) { | ^~~~~~~~~~~ In file included from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/core/ScalarType.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/core/Scalar.h:9, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/core/Type.h:10, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/core/Tensor.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:2, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/Context.h:4, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/ATen.h:5, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:4, from /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/extension.h:4, from /home/travail/FCOS-master/FCOS/maskrcnn_benchmark/csrc/cpu/vision.h:3, from /home/travail/FCOS-master/FCOS/maskrcnn_benchmark/csrc/cpu/ROIAlign_cpu.cpp:2: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<Tp>&) [with T = long int]’: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/core/TensorImpl.h:1399:34: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRef::Data’ from ‘std::initializer_list::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] 103 | : Data(Vec.begin() == Vec.end() ? static_cast<T*>(nullptr) : Vec.begin()), /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<Tp>&) [with T = unsigned char]’: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/NativeFunctions.h:46:1: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRef::Data’ from ‘std::initializer_list::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<Tp>&) [with T = signed char]’: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/NativeFunctions.h:46:1: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRef::Data’ from ‘std::initializer_list::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<Tp>&) [with T = short int]’: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/NativeFunctions.h:46:1: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRef::Data’ from ‘std::initializer_list::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<Tp>&) [with T = int]’: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/NativeFunctions.h:46:1: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRef::Data’ from ‘std::initializer_list::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<Tp>&) [with T = float]’: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/NativeFunctions.h:46:1: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRef::Data’ from ‘std::initializer_list::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<Tp>&) [with T = double]’: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/NativeFunctions.h:46:1: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRef::Data’ from ‘std::initializer_list::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<Tp>&) [with T = c10::qint8]’: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/NativeFunctions.h:46:1: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRefc10::qint8::Data’ from ‘std::initializer_listc10::qint8::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<Tp>&) [with T = c10::quint8]’: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/NativeFunctions.h:46:1: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRefc10::quint8::Data’ from ‘std::initializer_listc10::quint8::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h: In instantiation of ‘constexpr c10::ArrayRef::ArrayRef(const std::initializer_list<Tp>&) [with T = c10::qint32]’: /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/NativeFunctions.h:46:1: required from here /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/c10/util/ArrayRef.h:103:39: warning: initializing ‘c10::ArrayRefc10::qint32::Data’ from ‘std::initializer_listc10::qint32::begin’ does not extend the lifetime of the underlying array [-Winit-list-lifetime] /usr/local/cuda/bin/nvcc -DWITH_CUDA -I/home/travail/FCOS-master/FCOS/maskrcnn_benchmark/csrc -I/home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include -I/home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/TH -I/home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/THC -I/usr/local/cuda/include -I/home/travail/miniconda3/envs/FCOS/include/python3.7m -c /home/travail/FCOS-master/FCOS/maskrcnn_benchmark/csrc/cuda/ROIAlign_cuda.cu -o build/temp.linux-x86_64-3.7/home/travail/FCOS-master/FCOS/maskrcnn_benchmark/csrc/cuda/ROIAlign_cuda.o -D__CUDA_NO_HALF_OPERATORS -D__CUDA_NO_HALF_CONVERSIONS -D__CUDA_NO_HALF2_OPERATORS --compiler-options '-fPIC' -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS -D__CUDA_NO_HALF_CONVERSIONS -D__CUDA_NO_HALF2_OPERATORS -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++11 /opt/gcc/4.9.2/lib/gcc/x86_64-unknown-linux-gnu/4.9.2/include/avx512fintrin.h(3628): error: identifier "__builtin_ia32_pbroadcastq512_mem_mask" is undefined

    /opt/gcc/4.9.2/lib/gcc/x86_64-unknown-linux-gnu/4.9.2/include/avx512fintrin.h(3643): error: identifier "__builtin_ia32_pbroadcastq512_mem_mask" is undefined

    /opt/gcc/4.9.2/lib/gcc/x86_64-unknown-linux-gnu/4.9.2/include/avx512fintrin.h(3659): error: identifier "__builtin_ia32_pbroadcastq512_mem_mask" is undefined

    /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/cuda/NumericLimits.cuh(91): warning: calling a constexpr host function("from_bits") from a host device function("lowest") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

    /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/cuda/NumericLimits.cuh(92): warning: calling a constexpr host function("from_bits") from a host device function("max") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

    /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/cuda/NumericLimits.cuh(93): warning: calling a constexpr host function("from_bits") from a host device function("lower_bound") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

    /home/travail/miniconda3/envs/FCOS/lib/python3.7/site-packages/torch/include/ATen/cuda/NumericLimits.cuh(94): warning: calling a constexpr host function("from_bits") from a host device function("upper_bound") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

    3 errors detected in the compilation of "/tmp/tmpxft_000021bf_00000000-6_ROIAlign_cuda.cpp1.ii". error: command '/usr/local/cuda/bin/nvcc' failed with exit status 1

    opened by Kangzf1996 12
  • ModuleNotFoundError: No module named 'maskrcnn_benchmark.solver'

    ModuleNotFoundError: No module named 'maskrcnn_benchmark.solver'

    when i run the demo in nas-fcos everything is ok,but once i move the training pyfile to nas-fcos,the problem happens,I comfused about the maskrcnn-benchmark installlation. expect your reply ,thank you

    opened by yokings 11
  • Can not download the pre-trained model

    Can not download the pre-trained model

    When I run train.py to train FCOS_X_101_64x4d_FPN_2x, but it happens download error: Downloading: "https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/20171220/X-101-64x4d.pkl" to /home/zhengchenbin/.torch/models/X-101-64x4d.pkl Traceback (most recent call last): File "tools/train_net.py", line 175, in <module> main() File "tools/train_net.py", line 168, in main model = train(cfg, args.local_rank, args.distributed) File "tools/train_net.py", line 54, in train extra_checkpoint_data = checkpointer.load(cfg.MODEL.WEIGHT) File "/home/zhengchenbin/FcosNet/FCOS/maskrcnn_benchmark/utils/checkpoint.py", line 65, in load checkpoint = self._load_file(f) File "/home/zhengchenbin/FcosNet/FCOS/maskrcnn_benchmark/utils/checkpoint.py", line 133, in _load_file cached_f = cache_url(f) File "/home/zhengchenbin/FcosNet/FCOS/maskrcnn_benchmark/utils/model_zoo.py", line 54, in cache_url _download_url_to_file(url, cached_file, hash_prefix, progress=progress) File "/home/zhengchenbin/anaconda3/envs/FCOS/lib/python3.7/site-packages/torch/utils/model_zoo.py", line 76, in _download_url_to_file u = urlopen(url) File "/home/zhengchenbin/anaconda3/envs/FCOS/lib/python3.7/urllib/request.py", line 222, in urlopen return opener.open(url, data, timeout) File "/home/zhengchenbin/anaconda3/envs/FCOS/lib/python3.7/urllib/request.py", line 531, in open response = meth(req, response) File "/home/zhengchenbin/anaconda3/envs/FCOS/lib/python3.7/urllib/request.py", line 641, in http_response 'http', request, response, code, msg, hdrs) File "/home/zhengchenbin/anaconda3/envs/FCOS/lib/python3.7/urllib/request.py", line 569, in error return self._call_chain(*args) File "/home/zhengchenbin/anaconda3/envs/FCOS/lib/python3.7/urllib/request.py", line 503, in _call_chain result = func(*args) File "/home/zhengchenbin/anaconda3/envs/FCOS/lib/python3.7/urllib/request.py", line 649, in http_error_default raise HTTPError(req.full_url, code, msg, hdrs, fp) urllib.error.HTTPError: HTTP Error 403: Forbidden Can you provide the pre-trained model X-101-64x4d.pkl or give another download link such as baiduyun or google drive? Thank you very much!

    opened by ZhengMengbin 11
  • 600ms on mx150 which is slow

    600ms on mx150 which is slow

    I can run yolov3 mobilenet on my laptop which has mx150 2G GPU memory and CUDA10 with 30fps.

    But FCOS runs 600ms! Which is far way from realtime and really slow!

    Does there any speed inference on gtx1080 ti? how's the speed on that? I don't know why it is slow

    opened by jinfagang 10
  • a problem about ground-truth center-ness generation for inference

    a problem about ground-truth center-ness generation for inference

    I have tried using the ground-truth center-ness for inference, however only got AP 38.8 rather than 42.1 metioned in the paper. I wonder if there are some errors in my code of ground-truth center-ness generation. Can you help me find the problem or give me your code? thx. My code is as follow:

            labels, reg_targets = self.prepare_targets(locations, targets)
            centerness_target = []
            for l in range(len(labels)):
                reg_targets_flatten = reg_targets[l].reshape(-1, 4)
                reg_targets_flatten = (labels[l]!=0)[:,None].float()*reg_targets_flatten
                reg_targets_flatten = self.compute_centerness_targets(reg_targets_flatten)
                centerness_target.append(reg_targets_flatten.reshape(centerness[l].shape))
    
            return centerness_target
    ```
    
    opened by gaoyuchris 10
  • weird time consuming of FCOS head when changing the backbone

    weird time consuming of FCOS head when changing the backbone

    Hi, I want to test the FPS of FCOS with different backbones. But I found the results below is weird.

    backbone               time consuming of backbone+neck+head
    Resnext101-64x4d 35+2+120
    R50                        15+2.5+48
    

    My question is that why the time of FCOS head would change a lot with different backbones, as the structure of FCOS head do not change?

    opened by goldentimecoolk 0
  • ValueError: Unknown CUDA arch (8.6) or GPU not supported

    ValueError: Unknown CUDA arch (8.6) or GPU not supported

    When run python setup.py build develop --no-deps I got the following error: ValueError: Unknown CUDA arch (8.6) or GPU not supported

    How can i fix this?

    opened by YuxuanWen-Code 0
  • Testing with test dataset while training

    Testing with test dataset while training

    AFAIK, in the code, testing can be done only after completing all the training iterations. But is it possible to test with the test dataset while training? (Ex: 500 test iterations while 5000 training iterations). Any tips on how to modify the code to accommodate that?

    image

    opened by bimsarapathiraja 0
  • fix issues with deprecated library THC

    fix issues with deprecated library THC

    First of all, thank you @tianzhi0549 for this great framework, it became quickly my favorite framework. I found that the THC library is deprecated for PyTorch > 1.6.0, and many of its methods are replaced by methods in the ATen library.

    opened by rram12 0
  • Can’t calculate the Params and FLOPs of Backbone

    Can’t calculate the Params and FLOPs of Backbone

    used thop,torchstat and ptflops to caculate the Flops of the model, but all of the results shows there is 0 params and 0 flops in ResNet and FPN. Why did this happen and how can I calucalte the Flops of model correctly. Thank you!

    The example of output of the pyflops: Warning: module Conv2d is treated as a zero-op. Warning: module FrozenBatchNorm2d is treated as a zero-op. Warning: module StemWithFixedBatchNorm is treated as a zero-op. Warning: module BottleneckWithFixedBatchNorm is treated as a zero-op. Warning: module ResNet is treated as a zero-op. Warning: module GeneralizedRCNN is treated as a zero-op. GeneralizedRCNN( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (backbone): ResNet( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (stem): StemWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (layer1): Sequential( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (0): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (downsample): Sequential( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (0): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (1): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (2): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) ) (layer2): Sequential( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (0): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (downsample): Sequential( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (0): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False) (1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 128, kernel_size=(1, 1), stride=(2, 2), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (1): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (2): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (3): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) ) (layer3): Sequential( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (0): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (downsample): Sequential( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (0): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False) (1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 512, 256, kernel_size=(1, 1), stride=(2, 2), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (1): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (2): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (3): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (4): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (5): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) ) (layer4): Sequential( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (0): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (downsample): Sequential( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (0): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False) (1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 1024, 512, kernel_size=(1, 1), stride=(2, 2), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (1): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) (2): BottleneckWithFixedBatchNorm( 0, 0.000% Params, 0.0 Mac, 0.000% MACs, (conv1): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv2): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) (conv3): Conv2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, 512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): FrozenBatchNorm2d(0, 0.000% Params, 0.0 Mac, 0.000% MACs, ) ) ) ) ) 0.0 Mac

    opened by Pooky-Z 0
  • use my dataset to train FCOS net,why the loss is nan?

    use my dataset to train FCOS net,why the loss is nan?

    my dataset is remote dataset DIOR that come from Northwestern Polytechnical University, so when i use the dataset to train FCOS net, the loss is nan,

    who can ask the reason?

    the follow is error informatoin:

    2022-06-17 07:54:53.057 | INFO | main:train:229 - cls loss : 5515.9775390625, reg loss : 7.476679801940918, ness loss : 0.7106261253356934, sum loss : 279.5187072753906 2022-06-17 07:54:54.175 | INFO | main:train:229 - cls loss : nan, reg loss : nan, ness loss : nan, sum loss : nan 2022-06-17 07:54:55.242 | INFO | main:train:229 - cls loss : nan, reg loss : nan, ness loss : nan, sum loss : nan 2022-06-17 07:54:56.419 | INFO | main:train:229 - cls loss : nan, reg loss : nan, ness loss : nan, sum loss : nan 2022-06-17 07:54:57.572 | INFO | main:train:229 - cls loss : nan, reg loss : nan, ness loss : nan, sum loss : nan 2022-06-17 07:54:58.608 | INFO | main:train:229 - cls loss : nan, reg loss : nan, ness loss : nan, sum loss : nan 2022-06-17 07:54:59.634 | INFO | main:train:229 - cls loss : nan, reg loss : nan, ness loss : nan, sum loss : nan 2022-06-17 07:55:00.939 | INFO | main:train:229 - cls loss : nan, reg loss : nan, ness loss : nan, sum loss : nan 2022-06-17 07:55:02.146 | INFO | main:train:229 - cls loss : nan, reg loss : nan, ness loss : nan, sum loss : nan 2022-06-17 07:55:03.483 | INFO | main:train:229 - cls loss : nan, reg loss : nan, ness loss : nan, sum loss : nan 2022-06-17 07:55:04.700 | INFO | main:train:229 - cls loss : nan, reg loss : nan, ness loss : nan, sum loss : nan 2022-06-17 07:55:05.925 | INFO | main:train:229 - cls loss : nan, reg loss : nan, ness loss : nan, sum loss : nan 2022-06-17 07:55:06.957 | INFO | main:train:229 - cls loss : nan, reg loss : nan, ness loss : nan, sum loss : nan 2022-06-17 07:55:08.256 | INFO | main:train:229 - cls loss : nan, reg loss : nan, ness loss : nan, sum loss : nan 2022-06-17 07:55:09.364 | INFO | main:train:229 - cls loss : nan, reg loss : nan, ness loss : nan, sum loss : nan 2022-06-17 07:55:10.461 | INFO | main:train:229 - cls loss : nan, reg loss : nan, ness loss : nan, sum loss : nan 2022-06-17 07:55:11.527 | INFO | main:train:229 - cls loss : nan, reg loss : nan, ness loss : nan, sum loss : nan 2022-06-17 07:55:12.584 | INFO | main:train:229 - cls loss : nan, reg loss : nan, ness loss : nan, sum loss : nan 2022-06-17 07:55:13.665 | INFO | main:train:229 - cls loss : nan, reg loss : nan, ness loss : nan, sum loss : nan 2022-06-17 07:55:14.936 | INFO | main:train:229 - cls loss : nan, reg loss : nan, ness loss : nan, sum loss : nan 2022-06-17 07:55:16.000 | INFO | main:train:229 - cls loss : nan, reg loss : nan, ness loss : nan, sum loss : nan

    opened by funny000 2
Owner
Tian Zhi
PhD Candidate.
Tian Zhi
Implementation of ICCV19 Paper "Learning Two-View Correspondences and Geometry Using Order-Aware Network"

OANet implementation Pytorch implementation of OANet for ICCV'19 paper "Learning Two-View Correspondences and Geometry Using Order-Aware Network", by

Jiahui Zhang 225 Dec 5, 2022
TOOD: Task-aligned One-stage Object Detection, ICCV2021 Oral

One-stage object detection is commonly implemented by optimizing two sub-tasks: object classification and localization, using heads with two parallel branches, which might lead to a certain level of spatial misalignment in predictions between the two tasks.

null 264 Jan 9, 2023
DAFNe: A One-Stage Anchor-Free Deep Model for Oriented Object Detection

DAFNe: A One-Stage Anchor-Free Deep Model for Oriented Object Detection Code for our Paper DAFNe: A One-Stage Anchor-Free Deep Model for Oriented Obje

Steven Lang 58 Dec 19, 2022
End-to-End Object Detection with Fully Convolutional Network

This project provides an implementation for "End-to-End Object Detection with Fully Convolutional Network" on PyTorch.

null 472 Dec 22, 2022
A Data Annotation Tool for Semantic Segmentation, Object Detection and Lane Line Detection.(In Development Stage)

Data-Annotation-Tool How to Run this Tool? To run this software, follow the steps: git clone https://github.com/Autonomous-Car-Project/Data-Annotation

TiVRA AI 13 Aug 18, 2022
Code for Two-stage Identifier: "Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition"

Code for Two-stage Identifier: "Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition", accepted at ACL 2021. For details of the model and experiments, please see our paper.

tricktreat 87 Dec 16, 2022
Virtual Dance Reality Stage: a feature that offers you to share a stage with another user virtually

Portrait Segmentation using Tensorflow This script removes the background from an input image. You can read more about segmentation here Setup The scr

null 291 Dec 24, 2022
Pyramid Grafting Network for One-Stage High Resolution Saliency Detection. CVPR 2022

PGNet Pyramid Grafting Network for One-Stage High Resolution Saliency Detection. CVPR 2022, CVPR 2022 (arXiv 2204.05041) Abstract Recent salient objec

CVTEAM 109 Dec 5, 2022
Code for one-stage adaptive set-based HOI detector AS-Net.

AS-Net Code for one-stage adaptive set-based HOI detector AS-Net. Mingfei Chen*, Yue Liao*, Si Liu, Zhiyuan Chen, Fei Wang, Chen Qian. "Reformulating

Mingfei Chen 45 Dec 9, 2022
(CVPR2021) DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation

DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation CVPR2021(oral) [arxiv] Requirements python3.7 pytorch==

W-zx-Y 85 Dec 7, 2022
[CVPR2021] Look before you leap: learning landmark features for one-stage visual grounding.

LBYL-Net This repo implements paper Look Before You Leap: Learning Landmark Features For One-Stage Visual Grounding CVPR 2021. Getting Started Prerequ

SVIP Lab 45 Dec 12, 2022
A Fast and Accurate One-Stage Approach to Visual Grounding, ICCV 2019 (Oral)

One-Stage Visual Grounding ***** New: Our recent work on One-stage VG is available at ReSC.***** A Fast and Accurate One-Stage Approach to Visual Grou

Zhengyuan Yang 118 Dec 5, 2022
FishNet: One Stage to Detect, Segmentation and Pose Estimation

FishNet FishNet: One Stage to Detect, Segmentation and Pose Estimation Introduction In this project, we combine target detection, instance segmentatio

null 1 Oct 5, 2022
BMW TechOffice MUNICH 148 Dec 21, 2022
Hybrid CenterNet - Hybrid-supervised object detection / Weakly semi-supervised object detection

Hybrid-Supervised Object Detection System Object detection system trained by hybrid-supervision/weakly semi-supervision (HSOD/WSSOD): This project is

null 5 Dec 10, 2022
Yolo object detection - Yolo object detection with python

How to run download required files make build_image make download Docker versio

null 3 Jan 26, 2022
Single-Stage 6D Object Pose Estimation, CVPR 2020

Overview This repository contains the code for the paper Single-Stage 6D Object Pose Estimation. Yinlin Hu, Pascal Fua, Wei Wang and Mathieu Salzmann.

CVLAB @ EPFL 89 Dec 26, 2022
Single-stage Keypoint-based Category-level Object Pose Estimation from an RGB Image

CenterPose Overview This repository is the official implementation of the paper "Single-stage Keypoint-based Category-level Object Pose Estimation fro

NVIDIA Research Projects 188 Dec 27, 2022
The official PyTorch implementation of the paper: *Xili Dai, Xiaojun Yuan, Haigang Gong, Yi Ma. "Fully Convolutional Line Parsing." *.

F-Clip — Fully Convolutional Line Parsing This repository contains the official PyTorch implementation of the paper: *Xili Dai, Xiaojun Yuan, Haigang

Xili Dai 115 Dec 28, 2022