最近几个月有在跑detectron2和yolof但是遇到了很多困难，下次出一期安装detectron2的教程，其实可以搬运来自我自己的csdn写的内容也可以的

最近概况：

最近在学习一些视觉的内容detectron2还有yolof，遇到了很多的问题，在csdn上基本上都可以寻找到相关答案的

https://blog.csdn.net/blink182007?type=blog “我的csdn主页”
https://blog.csdn.net/blink182007/article/details/124222921?spm=1001.2014.3001.5502 “Detectron2安装踩坑记录（比较详细版）”

基本格式示例：python demo/demo.py –config-file configs/COCO-Detection/faster_rcnn_R_50_FPN_1x.yaml –input /images/1.jpg –output results –opt MODEL.WEIGHTS output/model_0049999.pth

python demo/demo.py –config-file configs/COCO-Detection/faster_rcnn_R_50_FPN_1x.yaml –input images/1.jpg –output results 可以但是没有结果

我的detectron2模型本地存储地址”E:\anacondalib\detectron2-master\detectron2-master\configs\COCO-Detection\retinanet_R_50_FPN_3x.yaml”

参考文献来源：

参考来自博客网站： https://blog.csdn.net/winorlose2000/article/details/112549795 “(82条消息) Detectron2 快速开始，使用 WebCam 测试_GoCodingInMyWay的博客-CSDN博客”

模型137849600/model_final_f10217.pkl下载来自Modelzoo网站：detectron2/MODEL_ZOO.md at main · facebookresearch/detectron2 (github.com) https://github.com/facebookresearch/detectron2/blob/main/MODEL_ZOO.md “137849600/model_final_f10217.pkl”

Python demo/demo.py –config-file configs/COCO-Detection/faster_rcnn_R_50_FPN_3x.yaml –webcam –output results –opt MODEL.WEIGHTS models/model_final_280758.pkl 实时检测失败
Python demo/demo.py –config-file configs/COCO-Detection/faster_rcnn_R_50_FPN_3x.yaml –input images/4.jpg –output results –opt MODEL.WEIGHTS models/model_final_280758.pkl

Python demo/demo.py –config-file configs/LVISv1-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml –input images/5.jpg –output results –opt MODEL.WEIGHTS models/model_final_571f7c.pkl 失败

“E:\anacondalib\detectron2-master\detectron2-master\configs\COCO-InstanceSegmentation\mask_rcnn_R_50_FPN_1x.yaml”

“E:\anacondalib\detectron2-master\detectron2-master\configs\LVISv1-InstanceSegmentation\mask_rcnn_R_50_FPN_1x.yaml”

检测代码和实例

1.1 普通目标检测：
Python demo/demo.py –config-file configs/COCO-Detection/faster_rcnn_R_50_FPN_3x.yaml –input images/1.jpg –output results –opt MODEL.WEIGHTS models/model_final_280758.pkl
成功语句 普通目标检测√
2.1 关键点检测：
Python demo/demo.py –config-file configs/COCO-Keypoints/keypoint_rcnn_R_50_FPN_3x.yaml –input images/7.jpg –output results –opt MODEL.WEIGHTS models/model_final_a6e10b.pkl 关键点检测成功√（”E:\anacondalib\detectron2-master\detectron2-master\configs\COCO-Keypoints\keypoint_rcnn_R_50_FPN_3x.yaml”
）（model_final_a6e10b.pkl）
3.1 语义分割实例：
Python demo/demo.py –config-file configs/COCO-PanopticSegmentation/panoptic_fpn_R_50_3x.yaml –input images/8.jpg –output results –opt MODEL.WEIGHTS models/model_final_c10459.pkl 语义分割实例成功√
（”E:\anacondalib\detectron2-master\detectron2-master\configs\COCO-PanopticSegmentation\panoptic_fpn_R_50_3x.yaml”）
（model_final_c10459.pkl）
4.1城市街道平面图实例
Python demo/demo.py –config-file configs\Cityscapes\mask_rcnn_R_50_FPN.yaml –input images/13.jpg –output results –opt MODEL.WEIGHTS models/model_final_af9cf5.pkl

5.1实时摄像头目标侦测
Python demo/demo.py –config-file configs/COCO-Detection/faster_rcnn_R_50_FPN_3x.yaml –webcam –output results –opt MODEL.WEIGHTS models/model_final_280758.pkl
(成功)
对于报错ERROR——File “demo/demo.py”, line 141, in
assert args.output is None, “output not yet supported with –webcam!”

将这一行注释掉即可
参考来自：(82条消息) Detectron2 快速开始，使用 WebCam 测试_GoCodingInMyWay的博客-CSDN博客

6.1实时语义分割检测
Python demo/demo.py –config-file configs/COCO-PanopticSegmentation/panoptic_fpn_R_50_3x.yaml –webcam –output results –opt MODEL.WEIGHTS models/model_final_c10459.pkl
（成功）

跑YOLOF的相关内容：

训练命令为：

***\Python ./tools/train_net.py –num-gpus 1 –config-file ./configs/yolof_R_50_C5_1x.yaml –eval-only MODEL.WEIGHTS output/yolof/R_50_C5_1x/model_final.pth

报错如下，需要注册coco2017数据集，自己标注数据，按照b站小鸡炖技术来训练文件，寻找出路和改进方向方法。标签平滑？

参考一下：一位b站深度学习up的训练命令如上图所示。

根据官方文档的内容——测试（test）命令如下：

python ./tools/train_net.py –num-gpus 1 –config-file ./configs/yolof_R_50_C5_1x.yaml –eval-only MODEL.WEIGHTS /path/to/checkpoint_file

运行过程如下（复制的比较多，可能有点长）
[04/23 11:13:46 detectron2]: Environment info:

sys.platform win32
Python 3.8.13 (default, Mar 28 2022, 06:59:08) [MSC v.1916 64 bit (AMD64)]
numpy 1.21.5
detectron2 0.5 @e:\anacondalib\detectron2-master\detectron2-master\detectron2
Compiler MSVC 192829923
CUDA compiler CUDA 11.1
detectron2 arch flags e:\anacondalib\detectron2-master\detectron2-master\detectron2_C.cp38-win_amd64.pyd; cannot find cuobjdump
DETECTRON2_ENV_MODULE
PyTorch 1.9.0+cu111 @D:\Anaconda3\envs\detectron2\lib\site-packages\torch
PyTorch debug build False
GPU available Yes
GPU 0 GeForce GTX 1650 (arch=7.5)
Driver version 457.63
CUDA_HOME C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.1
Pillow 9.0.1
torchvision 0.10.0+cu111 @D:\Anaconda3\envs\detectron2\lib\site-packages\torchvision
torchvision arch flags D:\Anaconda3\envs\detectron2\lib\site-packages\torchvision_C.pyd; cannot find cuobjdump
fvcore 0.1.5.post20220414
iopath 0.1.9
cv2 4.5.5

PyTorch built with:

  • C++ Version: 199711
  • MSVC 192829337
  • Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 architecture applications
  • Intel(R) MKL-DNN v2.1.2 (Git Hash 98be7e8afa711dc9b66c8ff3504129cb82013cdb)
  • OpenMP 2019
  • CPU capability usage: AVX2
  • CUDA Runtime 11.1
  • NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=compute_37
  • CuDNN 8.0.5
  • Magma 2.5.4
  • Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.1, CUDNN_VERSION=8.0.5, CXX_COMPILER=C:/w/b/windows/tmp_bin/sccache-cl.exe, CXX_FLAGS=/DWIN32 /D_WINDOWS /GR /EHs
    c /w /bigobj -DUSE_PTHREADPOOL -openmp:experimental -IC:/w/b/windows/mkl/include -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOCUPTI -DUSE_FBGEMM -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE,
    LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.9.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=OFF, USE_NNPACK=OFF, USE_OPENMP=ON,

[04/23 11:13:46 detectron2]: Command line arguments: Namespace(config_file=’./configs/yolof_R_50_C5_1x.yaml’, dist_url=’tcp://127.0.0.1:49153’, eval_only=True, machine_rank=0, num_gpus=1, num_machines=1, opts=[‘MODEL.WEIGHTS’, ‘/path/to/checkpoint_file’], resume=False)
[04/23 11:13:47 detectron2]: Contents of args.config_file=./configs/yolof_R_50_C5_1x.yaml:
BASE: “Base-YOLOF.yaml”
MODEL:
WEIGHTS: “detectron2://ImageNetPretrained/MSRA/R-50.pkl”
RESNETS:
DEPTH: 50
OUTPUT_DIR: “output/yolof/R_50_C5_1x”

[04/23 11:13:47 detectron2]: Running with full config:
CUDNN_BENCHMARK: false
DATALOADER:
ASPECT_RATIO_GROUPING: true
FILTER_EMPTY_ANNOTATIONS: true
NUM_WORKERS: 2
REPEAT_THRESHOLD: 0.0
SAMPLER_TRAIN: TrainingSampler
DATASETS:
PRECOMPUTED_PROPOSAL_TOPK_TEST: 1000
PRECOMPUTED_PROPOSAL_TOPK_TRAIN: 2000
PROPOSAL_FILES_TEST: []
PROPOSAL_FILES_TRAIN: []
TEST:

  • coco_2017_val
    TRAIN:
  • coco_2017_train
    GLOBAL:
    HACK: 1.0
    INPUT:
    CROP:
    ENABLED: false
    SIZE:
    • 0.9
    • 0.9
      TYPE: relative_range
      DISTORTION:
      ENABLED: false
      EXPOSURE: 1.5
      HUE: 0.1
      SATURATION: 1.5
      FORMAT: BGR
      JITTER_CROP:
      ENABLED: false
      JITTER_RATIO: 0.3
      MASK_FORMAT: polygon
      MAX_SIZE_TEST: 1333
      MAX_SIZE_TRAIN: 1333
      MIN_SIZE_TEST: 800
      MIN_SIZE_TRAIN:
  • 800
    MIN_SIZE_TRAIN_SAMPLING: choice
    MOSAIC:
    ENABLED: false
    MIN_OFFSET: 0.2
    MOSAIC_HEIGHT: 640
    MOSAIC_WIDTH: 640
    NUM_IMAGES: 4
    POOL_CAPACITY: 1000
    RANDOM_FLIP: horizontal
    RESIZE:
    ENABLED: false
    SCALE_JITTER:
    • 0.8
    • 1.2
      SHAPE:
    • 640
    • 640
      TEST_SHAPE:
    • 608
    • 608
      SHIFT:
      SHIFT_PIXELS: 32
      MODEL:
      ANCHOR_GENERATOR:
      ANGLES:
      • -90
      • 0
      • 90
        ASPECT_RATIOS:
      • 1.0
        NAME: DefaultAnchorGenerator
        OFFSET: 0.0
        SIZES:
      • 32
      • 64
      • 128
      • 256
      • 512
        BACKBONE:
        FREEZE_AT: 2
        NAME: build_resnet_backbone
        DARKNET:
        DEPTH: 53
        NORM: BN
        OUT_FEATURES:
    • res5
      RES5_DILATION: 1
      WITH_CSP: true
      DEVICE: cuda
      FPN:
      FUSE_TYPE: sum
      IN_FEATURES: []
      NORM: ‘’
      OUT_CHANNELS: 256
      KEYPOINT_ON: false
      LOAD_PROPOSALS: false
      MASK_ON: false
      META_ARCHITECTURE: YOLOF
      PANOPTIC_FPN:
      COMBINE:
      ENABLED: true
      INSTANCES_CONFIDENCE_THRESH: 0.5
      OVERLAP_THRESH: 0.5
      STUFF_AREA_LIMIT: 4096
      INSTANCE_LOSS_WEIGHT: 1.0
      PIXEL_MEAN:
  • 103.53
  • 116.28
  • 123.675
    PIXEL_STD:
  • 1.0
  • 1.0
  • 1.0
    PROPOSAL_GENERATOR:
    MIN_SIZE: 0
    NAME: RPN
    RESNETS:
    DEFORM_MODULATED: false
    DEFORM_NUM_GROUPS: 1
    DEFORM_ON_PER_STAGE:
    • false
    • false
    • false
    • false
      DEPTH: 50
      NORM: FrozenBN
      NUM_GROUPS: 1
      OUT_FEATURES:
    • res5
      RES2_OUT_CHANNELS: 256
      RES5_DILATION: 1
      STEM_OUT_CHANNELS: 64
      STRIDE_IN_1X1: true
      WIDTH_PER_GROUP: 64
      RETINANET:
      BBOX_REG_LOSS_TYPE: smooth_l1
      BBOX_REG_WEIGHTS: &id002
    • 1.0
    • 1.0
    • 1.0
    • 1.0
      FOCAL_LOSS_ALPHA: 0.25
      FOCAL_LOSS_GAMMA: 2.0
      IN_FEATURES:
    • p3
    • p4
    • p5
    • p6
    • p7
      IOU_LABELS:
    • 0
    • -1
    • 1
      IOU_THRESHOLDS:
    • 0.4
    • 0.5
      NMS_THRESH_TEST: 0.5
      NORM: ‘’
      NUM_CLASSES: 80
      NUM_CONVS: 4
      PRIOR_PROB: 0.01
      SCORE_THRESH_TEST: 0.05
      SMOOTH_L1_LOSS_BETA: 0.1
      TOPK_CANDIDATES_TEST: 1000
      ROI_BOX_CASCADE_HEAD:
      BBOX_REG_WEIGHTS:
    • &id001
      • 10.0
      • 10.0
      • 5.0
      • 5.0
      • 20.0
      • 20.0
      • 10.0
      • 10.0
      • 30.0
      • 30.0
      • 15.0
      • 15.0
        IOUS:
    • 0.5
    • 0.6
    • 0.7
      ROI_BOX_HEAD:
      BBOX_REG_LOSS_TYPE: smooth_l1
      BBOX_REG_LOSS_WEIGHT: 1.0
      BBOX_REG_WEIGHTS: *id001
      CLS_AGNOSTIC_BBOX_REG: false
      CONV_DIM: 256
      FC_DIM: 1024
      NAME: ‘’
      NORM: ‘’
      NUM_CONV: 0
      NUM_FC: 0
      POOLER_RESOLUTION: 14
      POOLER_SAMPLING_RATIO: 0
      POOLER_TYPE: ROIAlignV2
      SMOOTH_L1_BETA: 0.0
      TRAIN_ON_PRED_BOXES: false
      ROI_HEADS:
      BATCH_SIZE_PER_IMAGE: 512
      IN_FEATURES:
    • res4
      IOU_LABELS:
    • 0
    • 1
      IOU_THRESHOLDS:
    • 0.5
      NAME: Res5ROIHeads
      NMS_THRESH_TEST: 0.5
      NUM_CLASSES: 80
      POSITIVE_FRACTION: 0.25
      PROPOSAL_APPEND_GT: true
      SCORE_THRESH_TEST: 0.05
      ROI_KEYPOINT_HEAD:
      CONV_DIMS:
    • 512
    • 512
    • 512
    • 512
    • 512
    • 512
    • 512
    • 512
      LOSS_WEIGHT: 1.0
      MIN_KEYPOINTS_PER_IMAGE: 1
      NAME: KRCNNConvDeconvUpsampleHead
      NORMALIZE_LOSS_BY_VISIBLE_KEYPOINTS: true
      NUM_KEYPOINTS: 17
      POOLER_RESOLUTION: 14
      POOLER_SAMPLING_RATIO: 0
      POOLER_TYPE: ROIAlignV2
      ROI_MASK_HEAD:
      CLS_AGNOSTIC_MASK: false
      CONV_DIM: 256
      NAME: MaskRCNNConvUpsampleHead
      NORM: ‘’
      NUM_CONV: 0
      POOLER_RESOLUTION: 14
      POOLER_SAMPLING_RATIO: 0
      POOLER_TYPE: ROIAlignV2
      RPN:
      BATCH_SIZE_PER_IMAGE: 256
      BBOX_REG_LOSS_TYPE: smooth_l1
      BBOX_REG_LOSS_WEIGHT: 1.0
      BBOX_REG_WEIGHTS: *id002
      BOUNDARY_THRESH: -1
      CONV_DIMS:
    • -1
      HEAD_NAME: StandardRPNHead
      IN_FEATURES:
    • res4
      IOU_LABELS:
    • 0
    • -1
    • 1
      IOU_THRESHOLDS:
    • 0.3
    • 0.7
      LOSS_WEIGHT: 1.0
      NMS_THRESH: 0.7
      POSITIVE_FRACTION: 0.5
      POST_NMS_TOPK_TEST: 1000
      POST_NMS_TOPK_TRAIN: 2000
      PRE_NMS_TOPK_TEST: 6000
      PRE_NMS_TOPK_TRAIN: 12000
      SMOOTH_L1_BETA: 0.0
      SEM_SEG_HEAD:
      COMMON_STRIDE: 4
      CONVS_DIM: 128
      IGNORE_VALUE: 255
      IN_FEATURES:
    • p2
    • p3
    • p4
    • p5
      LOSS_WEIGHT: 1.0
      NAME: SemSegFPNHead
      NORM: GN
      NUM_CLASSES: 54
      WEIGHTS: /path/to/checkpoint_file
      YOLOF:
      BOX_TRANSFORM:
      ADD_CTR_CLAMP: true
      BBOX_REG_WEIGHTS:
      • 1.0
      • 1.0
      • 1.0
      • 1.0
        CTR_CLAMP: 32
        DECODER:
        ACTIVATION: ReLU
        CLS_NUM_CONVS: 2
        IN_CHANNELS: 512
        NORM: BN
        NUM_ANCHORS: 5
        NUM_CLASSES: 80
        PRIOR_PROB: 0.01
        REG_NUM_CONVS: 4
        DETECTIONS_PER_IMAGE: 100
        ENCODER:
        ACTIVATION: ReLU
        BACKBONE_LEVEL: res5
        BLOCK_DILATIONS:
      • 2
      • 4
      • 6
      • 8
        BLOCK_MID_CHANNELS: 128
        IN_CHANNELS: 2048
        NORM: BN
        NUM_CHANNELS: 512
        NUM_RESIDUAL_BLOCKS: 4
        LOSSES:
        BBOX_REG_LOSS_TYPE: giou
        FOCAL_LOSS_ALPHA: 0.25
        FOCAL_LOSS_GAMMA: 2.0
        MATCHER:
        TOPK: 4
        NEG_IGNORE_THRESHOLD: 0.7
        NMS_THRESH_TEST: 0.6
        POS_IGNORE_THRESHOLD: 0.15
        SCORE_THRESH_TEST: 0.05
        TOPK_CANDIDATES_TEST: 1000
        OUTPUT_DIR: output/yolof/R_50_C5_1x
        SEED: -1
        SOLVER:
        AMP:
        ENABLED: false
        BACKBONE_MULTIPLIER: 0.334
        BASE_LR: 0.12
        BIAS_LR_FACTOR: 1.0
        CHECKPOINT_PERIOD: 2500
        CLIP_GRADIENTS:
        CLIP_TYPE: value
        CLIP_VALUE: 1.0
        ENABLED: false
        NORM_TYPE: 2.0
        GAMMA: 0.1
        IMS_PER_BATCH: 64
        LR_SCHEDULER_NAME: WarmupMultiStepLR
        MAX_ITER: 22500
        MOMENTUM: 0.9
        NESTEROV: false
        REFERENCE_WORLD_SIZE: 0
        STEPS:
  • 15000
  • 20000
    WARMUP_FACTOR: 0.00066667
    WARMUP_ITERS: 1500
    WARMUP_METHOD: linear
    WEIGHT_DECAY: 0.0001
    WEIGHT_DECAY_BIAS: 0.0001
    WEIGHT_DECAY_NORM: 0.0
    TEST:
    AUG:
    ENABLED: false
    FLIP: true
    MAX_SIZE: 4000
    MIN_SIZES:
    • 400
    • 500
    • 600
    • 700
    • 800
    • 900
    • 1000
    • 1100
    • 1200
      DETECTIONS_PER_IMAGE: 100
      EVAL_PERIOD: 0
      EXPECTED_RESULTS: []
      KEYPOINT_OKS_SIGMAS: []
      PRECISE_BN:
      ENABLED: false
      NUM_ITER: 200
      VERSION: 2
      VIS_PERIOD: 0

[04/23 11:13:47 detectron2]: Full config saved to output/yolof/R_50_C5_1x\config.yaml
[04/23 11:13:47 d2.utils.env]: Using a generated random seed 47610603
[04/23 11:13:53 d2.engine.defaults]: Model:
YOLOF(
(backbone): ResNet(
(stem): BasicStem(
(conv1): Conv2d(
3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False
(norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
)
)
(res2): Sequential(
(0): BottleneckBlock(
(shortcut): Conv2d(
64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv1): Conv2d(
64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
)
(conv2): Conv2d(
64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
)
(conv3): Conv2d(
64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
)
(1): BottleneckBlock(
(conv1): Conv2d(
256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
)
(conv2): Conv2d(
64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
)
(conv3): Conv2d(
64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
)
(2): BottleneckBlock(
(conv1): Conv2d(
256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
)
(conv2): Conv2d(
64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
)
(conv3): Conv2d(
64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
)
)
(res3): Sequential(
(0): BottleneckBlock(
(shortcut): Conv2d(
256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv1): Conv2d(
256, 128, kernel_size=(1, 1), stride=(2, 2), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv2): Conv2d(
128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv3): Conv2d(
128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
)
(1): BottleneckBlock(
(conv1): Conv2d(
512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv2): Conv2d(
128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv3): Conv2d(
128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
)
(2): BottleneckBlock(
(conv1): Conv2d(
512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv2): Conv2d(
128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv3): Conv2d(
128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
)
(3): BottleneckBlock(
(conv1): Conv2d(
512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv2): Conv2d(
128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv3): Conv2d(
128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
)
)
(res4): Sequential(
(0): BottleneckBlock(
(shortcut): Conv2d(
512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv1): Conv2d(
512, 256, kernel_size=(1, 1), stride=(2, 2), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2): Conv2d(
256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv3): Conv2d(
256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(1): BottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2): Conv2d(
256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv3): Conv2d(
256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(2): BottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2): Conv2d(
256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv3): Conv2d(
256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(3): BottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2): Conv2d(
256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv3): Conv2d(
256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(4): BottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2): Conv2d(
256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv3): Conv2d(
256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(5): BottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2): Conv2d(
256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv3): Conv2d(
256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
)
(res5): Sequential(
(0): BottleneckBlock(
(shortcut): Conv2d(
1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False
(norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
)
(conv1): Conv2d(
1024, 512, kernel_size=(1, 1), stride=(2, 2), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv2): Conv2d(
512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv3): Conv2d(
512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
)
)
(1): BottleneckBlock(
(conv1): Conv2d(
2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv2): Conv2d(
512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv3): Conv2d(
512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
)
)
(2): BottleneckBlock(
(conv1): Conv2d(
2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv2): Conv2d(
512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv3): Conv2d(
512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
)
)
)
)
(encoder): DilatedEncoder(
(lateral_conv): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1))
(lateral_norm): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(fpn_conv): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(fpn_norm): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(dilated_encoder_blocks): Sequential(
(0): Bottleneck(
(conv1): Sequential(
(0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(2, 2), dilation=(2, 2))
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv3): Sequential(
(0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
)
(1): Bottleneck(
(conv1): Sequential(
(0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(4, 4), dilation=(4, 4))
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv3): Sequential(
(0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
)
(2): Bottleneck(
(conv1): Sequential(
(0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(6, 6), dilation=(6, 6))
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv3): Sequential(
(0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
)
(3): Bottleneck(
(conv1): Sequential(
(0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(8, 8), dilation=(8, 8))
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv3): Sequential(
(0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
)
)
)
(decoder): Decoder(
(cls_subnet): Sequential(
(0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): ReLU(inplace=True)
)
(bbox_subnet): Sequential(
(0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): ReLU(inplace=True)
(6): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(7): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(8): ReLU(inplace=True)
(9): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(10): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(11): ReLU(inplace=True)
)
(cls_score): Conv2d(512, 400, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(bbox_pred): Conv2d(512, 20, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(object_pred): Conv2d(512, 5, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(anchor_generator): DefaultAnchorGenerator(
return self.load(path, checkpointables=[])
File “e:\anacondalib\detectron2-master\detectron2-master\detectron2\checkpoint\detection_checkpoint.py”, line 53, in load
ret = super().load(path, *args, **kwargs)
File “D:\Anaconda3\envs\detectron2\lib\site-packages\fvcore\common\checkpoint.py”, line 153, in load
assert os.path.isfile(path), “Checkpoint {} not found!”.format(path)
AssertionError: Checkpoint /path/to/checkpoint_file not found!
接下来我们逐步实现yolof能够跑起来
首先我们安装labelme
这一部分参考来自(84条消息) Labelme安装及使用教程_Marlowee的博客-CSDN博客_labelme安装 https://blog.csdn.net/weixin_43427721/article/details/107122775 “(84条消息) Labelme安装及使用教程_Marlowee的博客-CSDN博客_labelme安装”

7.1报错与解决

报错：KeyError: “Dataset ‘test’ is not registered! Available datasets are: coco_2014_train, coco_2014_val, coco_2014_minival, coco_2014_minival_100, coco_2014_valminusminival, coco_2017_tra
in, coco_2017_val, coco_2017_test, coco_2017_test-dev, coco_2017_val_100, keypoints_coco_2014_train, keypoints_coco_2014_val, keypoints_coco_2014_minival, keypoints_coco_2014_valminus
minival, keypoints_coco_2014_minival_100, keypoints_coco_2017_train, keypoints_coco_2017_val, keypoints_coco_2017_val_100, coco_2017_train_panoptic_separated, coco_2017_train_panoptic
_stuffonly, coco_2017_train_panoptic, coco_2017_val_panoptic_separated, coco_2017_val_panoptic_stuffonly, coco_2017_val_panoptic, coco_2017_val_100_panoptic_separated, coco_2017_val_1
00_panoptic_stuffonly, coco_2017_val_100_panoptic, lvis_v1_train, lvis_v1_val, lvis_v1_test_dev, lvis_v1_test_challenge, lvis_v0.5_train, lvis_v0.5_val, lvis_v0.5_val_rand_100, lvis_v
0.5_test, lvis_v0.5_train_cocofied, lvis_v0.5_val_cocofied, cityscapes_fine_instance_seg_train, cityscapes_fine_sem_seg_train, cityscapes_fine_instance_seg_val, cityscapes_fine_sem_se
g_val, cityscapes_fine_instance_seg_test, cityscapes_fine_sem_seg_test, cityscapes_fine_panoptic_train, cityscapes_fine_panoptic_val, voc_2007_trainval, voc_2007_train, voc_2007_val, voc_2007_test, voc_2012_trainval, voc_2012_train, voc_2012_val, ade20k_sem_seg_train, ade20k_sem_seg_val”

报错OS Error
OSError: [WinError 1455] 页面文件太小，无法完成操作。

解决方法：
dataloader.test = L(build_data_loader)(
dataset=L(torchvision.datasets.ImageNet)(
root=”${…train.dataset.root}”,
split=”val”,
transform=L(T.Compose)(
transforms=[
L(T.Resize)(size=256),
L(T.CenterCrop)(size=224),
T.ToTensor(),
L(T.Normalize)(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)),
]
),
),
batch_size=256 // 8,
num_workers=4, #修改此处的num_workers=0即可
training=False,
)

其他报错：
[04/25 16:25:24 d2.engine.train_loop]: Starting training from iteration 0
Install mish-cuda to speed up training and inference. More importantly, replace the naive Mish with MishCuda will give a ~1.5G memory saving during training.
Traceback (most recent call last):
File ““, line 1, in
File “D:\Anaconda3\envs\detectron2\lib\multiprocessing\spawn.py”, line 116, in spawn_main
exitcode = _main(fd, parent_sentinel)
File “D:\Anaconda3\envs\detectron2\lib\multiprocessing\spawn.py”, line 125, in _main
prepare(preparation_data)
File “D:\Anaconda3\envs\detectron2\lib\multiprocessing\spawn.py”, line 236, in prepare
_fixup_main_from_path(data[‘init_main_from_path’])
File “D:\Anaconda3\envs\detectron2\lib\multiprocessing\spawn.py”, line 287, in _fixup_main_from_path
main_content = runpy.run_path(main_path,
File “D:\Anaconda3\envs\detectron2\lib\runpy.py”, line 265, in run_path
return _run_module_code(code, init_globals, run_name,
File “D:\Anaconda3\envs\detectron2\lib\runpy.py”, line 97, in _run_module_code
_run_code(code, mod_globals, init_globals,
File “D:\Anaconda3\envs\detectron2\lib\runpy.py”, line 87, in _run_code
exec(code, run_globals)
File “E:\anacondalib\detectron2\YOLOF-master\YOLOF-master\tools\train_net.py”, line 47, in
from torch.contrib._tensorboard_vis import visualize
File “D:\Anaconda3\envs\detectron2\lib\site-packages\torch\contrib_tensorboard_vis.py”, line 17, in
raise ImportError(“TensorBoard visualization of GraphExecutors requires having “
ImportError: TensorBoard visualization of GraphExecutors requires having TensorFlow installed

现阶段(当前)遇到的问题：

yolof可以跑起来，但是目前的问题在于识别结果框的visualize可视化出了一些问题，yolof这一块跑起来以后目前无法做出成功的可视化框。