RevYOLOv5_3 のバックアップ(No.6)

私的AI研究会 > RevYOLOv5_3

『ナンバープレート判別』「YOLO V5」３　== 編集中 == †

　物体検出の応用として車のナンバープレート識別を検討してみる

▲　目　次

『ナンバープレート判別』「YOLO V5」３　== 編集中 ==
参考資料

※ 最終更新:2024/05/23

参考サイト
・車のナンバープレート読み取りプログラム
・ YOLOv8でナンバープレートを検出してAI-OCRで読み取ってみました

手順 2ステップでナンバープレートを読み取る

Step 1: ナンバープレートの領域を調べる
・「YOLO v5」を使ってナンバープレートの追加学習を行い得られた学習済みモデルを使用しナンバープレートの領域を得る

Step 2: その領域からナンバープレートの情報を読み取る
・方法１: ランダムなナンバープレート画像を生成しデータセットとして「YOLO v5」の追加学習をして物体認識の手法で上位法を取得
・方法２: AI-OCR を使って領域を切り出したナンバープレート画像から情報を得る

↑

Step 1: ナンバープレートの領域を判別 †

↑

データセットの準備 †

Vehicle Detection Computer Vision Project のページを開く
・「Download」ボタンを押す
・ダウンロードファイル「Vehicle Detection.v7i.yolov5pytorch.zip」を解凍する
・フォルダ名を変更「Vehicle Detection.v7i.yolov5pytorch」→「vd_dataset」

「vd_dataset/」フォルダ内の「data.yaml」をコピーしてファイル「vd_data.yaml」を作成
・データセットの配置場所は「yolov5/data/」フォルダとする

train: data/vd_dataset/train/images
val: data/vd_dataset/valid/images
test: data/vd_dataset/test/images

nc: 2
names: ['licence', 'licenseplate']

roboflow:
  workspace: image-processing-u647q
  project: vehicle-detection-639on
  version: 7
  license: CC BY 4.0
  url: https://universe.roboflow.com/image-processing-u647q/vehicle-detection-639on/dataset/7

「vd_dataset/」フォルダを「yolov5/data/」内にコピー（移動）する

↑

学習の実行 †

エポック数 100 で実行する
・実行ディレクトリは「workspace_pylearn/yolov5/」
・学習モデルはデフォールト設定「yolov7s」を使用する
・学習結果フォルダ名は「vd_yolov5s_ep100」とする
```
(py_learn) python train.py --epochs 100 --data data/vd_dataset/vd_data.yaml --weights yolov5s.pt --name vd_yolov5s_ep100
```
・GPU を使用しない場合は以下のコマンドを実行する
```
(py_learn) python train.py --epochs 100 --data data/vd_dataset/vd_data.yaml --weights yolov5s.pt --name vd_yolov5s_ep100 --device cpu
```

学習の終了

(py_learn) python train.py --epochs 100 --data data/vd_dataset/vd_data.yaml --weights yolov5s.pt --name vd_yolov5s_ep100
        :

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      99/99      4.17G    0.01894   0.006213   0.000583         12        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.544        0.5      0.468      0.242

100 epochs completed in 0.107 hours.
Optimizer stripped from runs\train\vd_yolov5s_ep100\weights\last.pt, 14.4MB
Optimizer stripped from runs\train\vd_yolov5s_ep100\weights\best.pt, 14.4MB

Validating runs\train\vd_yolov5s_ep100\weights\best.pt...
Fusing layers...
Model summary: 157 layers, 7015519 parameters, 0 gradients, 15.8 GFLOPs
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:01<0
                   all        136        155      0.476       0.53      0.472       0.26
               licence        136        132      0.681      0.712      0.635      0.333
          licenseplate        136         23       0.27      0.348       0.31      0.187
Results saved to runs\train\vd_yolov5s_ep100

▼「train.py」実行ログ詳細

(py_learn) python train.py --epochs 100 --data data/vd_dataset/vd_data.yaml --weights yolov5s.pt --name vd_yolov5s_ep100
train: weights=yolov5s.pt, cfg=, data=data/vd_dataset/vd_data.yaml, hyp=data\hyps\hyp.scratch-low.yaml, epochs=100, batch_size=16, imgsz=640, rect=False, resume=False, nosave=False, noval=False, noautoanchor=False, noplots=False, evolve=None, evolve_population=data\hyps, resume_evolve=None, bucket=, cache=None, image_weights=False, device=, multi_scale=False, single_cls=False, optimizer=SGD, sync_bn=False, workers=8, project=runs\train, name=vd_yolov5s_ep100, exist_ok=False, quad=False, cos_lr=False, label_smoothing=0.0, patience=100, freeze=[0], save_period=-1, seed=0, local_rank=-1, entity=None, upload_dataset=False, bbox_interval=-1, artifact_alias=latest, ndjson_console=False, ndjson_file=False
github:  YOLOv5 is out of date by 10 commits. Use 'git pull' or 'git clone https://github.com/ultralytics/yolov5' to update.
YOLOv5  v7.0-294-gdb125a20 Python-3.11.8 torch-2.2.1+cu121 CUDA:0 (NVIDIA GeForce RTX 4070 Ti, 12282MiB)

hyperparameters: lr0=0.01, lrf=0.01, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=0.05, cls=0.5, cls_pw=1.0, obj=1.0, obj_pw=1.0, iou_t=0.2, anchor_t=4.0, fl_gamma=0.0, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, mosaic=1.0, mixup=0.0, copy_paste=0.0
Comet: run 'pip install comet_ml' to automatically track and visualize YOLOv5  runs in Comet
TensorBoard: Start with 'tensorboard --logdir runs\train', view at http://localhost:6006/
Overriding model.yaml nc=80 with nc=2

                 from  n    params  module                                  arguments
  0                -1  1      3520  models.common.Conv                      [3, 32, 6, 2, 2]
  1                -1  1     18560  models.common.Conv                      [32, 64, 3, 2]
  2                -1  1     18816  models.common.C3                        [64, 64, 1]
  3                -1  1     73984  models.common.Conv                      [64, 128, 3, 2]
  4                -1  2    115712  models.common.C3                        [128, 128, 2]
  5                -1  1    295424  models.common.Conv                      [128, 256, 3, 2]
  6                -1  3    625152  models.common.C3                        [256, 256, 3]
  7                -1  1   1180672  models.common.Conv                      [256, 512, 3, 2]
  8                -1  1   1182720  models.common.C3                        [512, 512, 1]
  9                -1  1    656896  models.common.SPPF                      [512, 512, 5]
 10                -1  1    131584  models.common.Conv                      [512, 256, 1, 1]
 11                -1  1         0  torch.nn.modules.upsampling.Upsample    [None, 2, 'nearest']
 12           [-1, 6]  1         0  models.common.Concat                    [1]
 13                -1  1    361984  models.common.C3                        [512, 256, 1, False]
 14                -1  1     33024  models.common.Conv                      [256, 128, 1, 1]
 15                -1  1         0  torch.nn.modules.upsampling.Upsample    [None, 2, 'nearest']
 16           [-1, 4]  1         0  models.common.Concat                    [1]
 17                -1  1     90880  models.common.C3                        [256, 128, 1, False]
 18                -1  1    147712  models.common.Conv                      [128, 128, 3, 2]
 19          [-1, 14]  1         0  models.common.Concat                    [1]
 20                -1  1    296448  models.common.C3                        [256, 256, 1, False]
 21                -1  1    590336  models.common.Conv                      [256, 256, 3, 2]
 22          [-1, 10]  1         0  models.common.Concat                    [1]
 23                -1  1   1182720  models.common.C3                        [512, 512, 1, False]
 24      [17, 20, 23]  1     18879  models.yolo.Detect                      [2, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [128, 256, 512]]
Model summary: 214 layers, 7025023 parameters, 7025023 gradients, 16.0 GFLOPs

Transferred 343/349 items from yolov5s.pt
AMP: checks passed
optimizer: SGD(lr=0.01) with parameter groups 57 weight(decay=0.0), 60 weight(decay=0.0005), 60 bias
train: Scanning C:\anaconda_win\workspace_pylearn\yolov5\data\vd_dataset\train\labels... 534 images, 0 backgrounds, 0 c
train: New cache created: C:\anaconda_win\workspace_pylearn\yolov5\data\vd_dataset\train\labels.cache
val: Scanning C:\anaconda_win\workspace_pylearn\yolov5\data\vd_dataset\valid\labels... 136 images, 0 backgrounds, 0 cor
val: New cache created: C:\anaconda_win\workspace_pylearn\yolov5\data\vd_dataset\valid\labels.cache

AutoAnchor: 4.49 anchors/target, 0.998 Best Possible Recall (BPR). Current anchors are a good fit to dataset
Plotting labels to runs\train\vd_yolov5s_ep100\labels.jpg...
Image sizes 640 train, 640 val
Using 8 dataloader workers
Logging results to runs\train\vd_yolov5s_ep100
Starting training for 100 epochs...

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
       0/99      3.35G     0.1077    0.02402    0.02739         10        640: 100%|██████████| 34/34 [00:03<00:00,  8.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:01<0
                   all        136        155    0.00147      0.441    0.00787     0.0015

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
       1/99      4.17G    0.07881    0.01994    0.02233          8        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155     0.0881      0.286     0.0908     0.0228

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
       2/99      4.17G    0.06813    0.01882    0.02023         11        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.124       0.14     0.0758     0.0166

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
       3/99      4.17G    0.06052    0.01907    0.02192         15        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.262       0.28      0.187     0.0507

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
       4/99      4.17G    0.05604    0.01678    0.01979          3        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.251      0.344      0.226     0.0733

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
       5/99      4.17G    0.05357    0.01453    0.01962          4        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.339      0.468      0.275        0.1

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
       6/99      4.17G    0.04962      0.013    0.01755         11        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.243      0.508      0.302      0.123

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
       7/99      4.17G    0.04819    0.01288    0.01671          8        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.286      0.573      0.324      0.141

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
       8/99      4.17G    0.04799    0.01224    0.01682          9        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155       0.41      0.496      0.403      0.141

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
       9/99      4.17G     0.0452    0.01103    0.01316         12        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.421      0.467      0.388      0.176

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      10/99      4.17G    0.04408    0.01181    0.01312         11        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.379       0.47      0.356      0.132

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      11/99      4.17G    0.04409    0.01053    0.01366         10        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.344      0.666      0.405      0.157

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      12/99      4.17G     0.0436    0.01069     0.0119          7        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.353      0.678      0.364      0.157

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      13/99      4.17G    0.04195    0.01045    0.01321          9        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.338      0.536      0.373      0.147

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      14/99      4.17G    0.04161    0.01003    0.01148         10        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.384      0.519      0.392       0.17

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      15/99      4.17G    0.04152     0.0105    0.01172         11        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155        0.4      0.604      0.398      0.156

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      16/99      4.17G    0.04103    0.01077   0.009728         16        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.398      0.691      0.403      0.183

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      17/99      4.17G    0.04067    0.01022   0.009083         10        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.329      0.525      0.309      0.136

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      18/99      4.17G    0.03998    0.01104   0.008598         12        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.463      0.597       0.44      0.182

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      19/99      4.17G    0.03857    0.01019   0.008915         10        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.431       0.55      0.395      0.175

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      20/99      4.17G     0.0397    0.01049   0.008228          8        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.407      0.478      0.389      0.173

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      21/99      4.17G     0.0381    0.01013    0.00713         11        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155       0.41      0.598       0.38      0.158

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      22/99      4.17G    0.03814    0.01021   0.007856          9        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.395      0.479      0.375      0.167

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      23/99      4.17G    0.03744   0.009726   0.008886         13        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.407      0.475      0.366      0.179

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      24/99      4.17G    0.03816   0.009636   0.007989         10        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.348      0.614      0.383      0.183

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      25/99      4.17G     0.0362   0.009729   0.006832          7        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.381      0.549      0.388      0.163

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      26/99      4.17G    0.03631    0.00967   0.006515         10        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.464      0.691      0.438      0.199

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      27/99      4.17G    0.03671   0.009812   0.006551         19        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.419      0.558      0.364      0.161

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      28/99      4.17G    0.03558   0.009518   0.008033         17        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.446      0.502      0.422      0.187

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      29/99      4.17G    0.03544   0.009402   0.006808          9        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.456      0.449      0.448       0.21

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      30/99      4.17G    0.03582   0.008926   0.004771          9        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.382      0.568      0.401      0.196

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      31/99      4.17G     0.0351   0.009278   0.006837         11        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.338      0.568      0.345      0.149

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      32/99      4.17G    0.03559   0.008784   0.006162          8        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.399      0.638      0.389      0.146

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      33/99      4.17G    0.03339   0.009218   0.006279          9        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.378      0.414      0.343      0.153

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      34/99      4.17G    0.03328   0.009094   0.005969         11        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.486      0.511      0.407      0.178

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      35/99      4.17G    0.03212   0.008869   0.004334          9        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155       0.44      0.464      0.381      0.185

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      36/99      4.17G    0.03479   0.008576   0.004585          7        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155       0.46      0.576      0.433      0.207

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      37/99      4.17G    0.03282   0.008963   0.004829          7        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.554      0.538      0.481      0.238

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      38/99      4.17G    0.03182   0.008006   0.005745          7        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.509      0.579      0.462      0.222

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      39/99      4.17G    0.03272    0.00886   0.004122         11        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.503      0.522      0.457      0.214

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      40/99      4.17G    0.03229   0.008904   0.004129          8        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.479      0.424      0.449      0.205

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      41/99      4.17G    0.03179   0.009141   0.004667         35        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.512        0.4      0.402      0.177

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      42/99      4.17G    0.03232   0.008642   0.004059          6        640: 100%|██████████| 34/34 [00:03<00:00, 10.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.466      0.466      0.436      0.214

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      43/99      4.17G    0.03252   0.008401   0.004131         11        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.477      0.515      0.453      0.231

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      44/99      4.17G    0.03102   0.008662   0.003599          8        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.535      0.496      0.487      0.233

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      45/99      4.17G    0.03094   0.008696   0.003257         12        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.546      0.531      0.509      0.231

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      46/99      4.17G     0.0311   0.008247   0.003277          9        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.554      0.476      0.452       0.22

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      47/99      4.17G    0.03009   0.008467   0.003349          9        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.403      0.504      0.408      0.208

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      48/99      4.17G    0.02996   0.007897   0.003302         11        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.493      0.556      0.467      0.231

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      49/99      4.17G    0.02982   0.008305     0.0032         13        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.487      0.522      0.478      0.252

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      50/99      4.17G    0.02879   0.007663   0.002992         12        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.433      0.498      0.449      0.217

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      51/99      4.17G    0.02883   0.007434   0.002397         12        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.498       0.47      0.434      0.208

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      52/99      4.17G     0.0286   0.007931   0.003441          8        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.404      0.608      0.421      0.208

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      53/99      4.17G    0.02858   0.007742   0.002966          7        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.414      0.442      0.429       0.21

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      54/99      4.17G      0.029   0.007838   0.002552          9        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.455      0.459      0.434       0.21

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      55/99      4.17G    0.02779   0.007517   0.003272          6        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.449      0.596      0.425      0.201

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      56/99      4.17G    0.02813   0.007328   0.002441          6        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.344      0.454      0.356      0.165

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      57/99      4.17G    0.02872   0.008069   0.002178         13        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.448      0.473      0.395       0.19

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      58/99      4.17G    0.02734   0.007133   0.001701         12        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155       0.46       0.58      0.459      0.221

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      59/99      4.17G    0.02736   0.007516   0.002258          4        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.436      0.544      0.437      0.217

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      60/99      4.17G    0.02616   0.007238   0.002091          7        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.456      0.427      0.435      0.212

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      61/99      4.17G    0.02666   0.007796   0.001681          8        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.522      0.445       0.44      0.227

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      62/99      4.17G    0.02614   0.007259   0.002317          7        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.447      0.581      0.472      0.236

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      63/99      4.17G    0.02614    0.00749   0.001597          9        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.447      0.602      0.464      0.213

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      64/99      4.17G    0.02571   0.007683   0.001898         12        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155        0.5       0.48      0.428      0.207

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      65/99      4.17G    0.02528   0.007227   0.002234         14        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.555      0.537      0.458      0.236

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      66/99      4.17G    0.02516   0.007606   0.001728         11        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.569       0.46      0.446      0.239

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      67/99      4.17G    0.02534   0.006963   0.001995         14        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.478       0.53      0.471      0.259

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      68/99      4.17G    0.02417   0.006699   0.001296          6        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.527      0.503      0.468      0.252

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      69/99      4.17G    0.02451   0.006508  0.0008484          6        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.464       0.52      0.443      0.229

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      70/99      4.17G    0.02485   0.007124   0.001725         11        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.451      0.469      0.445      0.229

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      71/99      4.17G     0.0237   0.006755   0.001088         10        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.444      0.529      0.431      0.214

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      72/99      4.17G    0.02346   0.006891   0.001379         15        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.445      0.537      0.436      0.222

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      73/99      4.17G    0.02407   0.007179   0.001141         17        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.496      0.488      0.418      0.221

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      74/99      4.17G    0.02253   0.006743   0.001067          9        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.449      0.508      0.408      0.209

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      75/99      4.17G    0.02311   0.006914  0.0009088         12        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155       0.51      0.457      0.426      0.214

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      76/99      4.17G    0.02289   0.006651   0.001182         10        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.538      0.448      0.439      0.228

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      77/99      4.17G    0.02306   0.006418  0.0007185         13        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.513      0.525      0.446      0.235

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      78/99      4.17G    0.02275   0.006783  0.0009759         11        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.518      0.492      0.436      0.221

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      79/99      4.17G    0.02272   0.006716   0.001041         17        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.475      0.515      0.444      0.224

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      80/99      4.17G    0.02203   0.006576   0.001053         12        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.511      0.445      0.451      0.234

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      81/99      4.17G    0.02181   0.006566  0.0006471         10        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.535      0.444      0.431      0.223

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      82/99      4.17G    0.02159   0.006546  0.0006951         11        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.488      0.515      0.463       0.24

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      83/99      4.17G    0.02111   0.006619  0.0008768         26        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.475      0.511      0.454      0.232

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      84/99      4.17G    0.02119    0.00669   0.001046          8        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.492      0.502      0.435      0.225

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      85/99      4.17G    0.02142   0.006132  0.0004634          5        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.468      0.548      0.436      0.229

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      86/99      4.17G    0.02127   0.006663    0.00109         12        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.508      0.534      0.462       0.24

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      87/99      4.17G    0.02075   0.006554  0.0009801         10        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.572      0.547      0.479      0.245

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      88/99      4.17G    0.02098   0.006237  0.0008284          9        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.549      0.558      0.475      0.244

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      89/99      4.17G    0.02011   0.006429  0.0008699          9        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.576      0.492      0.463      0.242

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      90/99      4.17G    0.02069   0.006413  0.0009655         11        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.538      0.492      0.452      0.235

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      91/99      4.17G    0.02029   0.006122  0.0006603         11        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.545      0.548      0.465      0.235

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      92/99      4.17G    0.01956   0.006109  0.0006611         11        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.528      0.541       0.48      0.248

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      93/99      4.17G    0.01998   0.006234  0.0005419         13        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.501      0.565      0.481      0.253

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      94/99      4.17G    0.01997   0.005772  0.0007185          9        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.536      0.518      0.468      0.248

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      95/99      4.17G    0.01924   0.006182  0.0006602          8        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.589      0.488      0.474      0.243

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      96/99      4.17G     0.0196   0.006417   0.001518         11        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.595      0.478      0.471      0.239

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      97/99      4.17G    0.01935   0.006105  0.0005842         14        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.486      0.562      0.465      0.244

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      98/99      4.17G     0.0186   0.006031  0.0004643         12        640: 100%|██████████| 34/34 [00:02<00:00, 11.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.473       0.57      0.469      0.243

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
      99/99      4.17G    0.01894   0.006213   0.000583         12        640: 100%|██████████| 34/34 [00:02<00:00, 12.
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:00<0
                   all        136        155      0.544        0.5      0.468      0.242

100 epochs completed in 0.107 hours.
Optimizer stripped from runs\train\vd_yolov5s_ep100\weights\last.pt, 14.4MB
Optimizer stripped from runs\train\vd_yolov5s_ep100\weights\best.pt, 14.4MB

Validating runs\train\vd_yolov5s_ep100\weights\best.pt...
Fusing layers...
Model summary: 157 layers, 7015519 parameters, 0 gradients, 15.8 GFLOPs
                 Class     Images  Instances          P          R      mAP50   mAP50-95: 100%|██████████| 5/5 [00:01<0
                   all        136        155      0.476       0.53      0.472       0.26
               licence        136        132      0.681      0.712      0.635      0.333
          licenseplate        136         23       0.27      0.348       0.31      0.187
Results saved to runs\train\vd_yolov5s_ep100

メッセージ「Results saved to runs\train\vd_yolov5s_ep30」のファイルを確認
・学習結果モデルは「runs/train/vd_yolov5s_ep100/weights」評価指標は「runs/train/vd_yolov5s_ep100/」

F1 curve P curve PR curve R curve

↑

実行結果を使って推論 †

ラベルファイルを作成する
・「vd_names_jp」日本語ファイル
```
ナンバー
ナンバープレート
```
・「vd_names」英語ファイル
```
licence
licenseplate
```

「detect2.py」で推論実行（静止画をフォルダごとまとめて）
・学習結果モデルを指定する

(py_learn) python detect2.py --weights runs/train/vd_yolov5s_ep100/weights/best.pt --source ../number/test_data/

・実行ログ（結果は「runs/detect/exp*」*は順次更新）

(py_learn) python detect2.py --weights runs/train/vd_yolov5s_ep100/weights/best.pt --source ../number/test_data/
detect2: weights=['runs/train/vd_yolov5s_ep100/weights/best.pt'], source=../number/test_data/, data=data\coco128.yaml, imgsz=[640, 640], conf_thres=0.25, iou_thres=0.45, max_det=1000, device=, view_img=False, save_txt=False, save_csv=False, save_conf=False, save_crop=False, nosave=False, classes=None, agnostic_nms=False, augment=False, visualize=False, update=False, project=runs\detect, name=exp, exist_ok=False, line_thickness=3, hide_labels=False, hide_conf=False, half=False, dnn=False, vid_stride=1
YOLOv5  v7.0-294-gdb125a20 Python-3.11.8 torch-2.2.1+cu121 CUDA:0 (NVIDIA GeForce RTX 4070 Ti, 12282MiB)

Fusing layers...
Model summary: 157 layers, 7015519 parameters, 0 gradients, 15.8 GFLOPs
Speed: 0.2ms pre-process, 5.4ms inference, 1.2ms NMS per image at shape (1, 3, 640, 640)
Results saved to runs\detect\exp43

「detect3_yolov5.py」で推論実行（静止画）
・学習結果モデルを指定する

(py_learn) python detect3_yolov5.py -m runs/train/vd_yolov5s_ep100/weights/best.pt -i ../number/test_data/japan69.jpg -l ./data/vd_dataset/vd_names_jp

・実行ログ

(py_learn) python detect3_yolov5.py -m runs/train/vd_yolov5s_ep100/weights/best.pt -i ../number/test_data/japan69.jpg -l ./data/vd_dataset/vd_names_jp
 Starting..

Object detection+ YoloV5 Ver. 0.08: Starting application...
   OpenCV virsion : 4.9.0

   - Image File   :  ../number/test_data/japan69.jpg
   - YOLO v5      :  ultralytics/yolov5
   - Pretrained   :  runs/train/vd_yolov5s_ep100/weights/best.pt
   - Confidence lv:  0.25
   - Label file   :  ./data/vd_dataset/vd_names_jp
   - Program Title:  y
   - Speed flag   :  y
   - Processed out:  non
   - Use device   :  cuda:0
   - Log Level    :  3

Using cache found in C:\Users\izuts/.cache\torch\hub\ultralytics_yolov5_master
YOLOv5  2024-4-9 Python-3.11.8 torch-2.2.1+cu121 CUDA:0 (NVIDIA GeForce RTX 4070 Ti, 12282MiB)

Fusing layers...
Model summary: 157 layers, 7015519 parameters, 0 gradients, 15.8 GFLOPs
Adding AutoShape...

FPS average:       8.90

 Finished.

↑

Step 2: ナンバープレートの情報を識別 †

↑

データセットの準備 †

ナンバープレートのフォント

生成したナンバープレートの例

↑

学習の実行 †

エポック数 30/50/100 で実行する
・実行ディレクトリは「workspace_pylearn/yolov5/」
・学習モデルはデフォールト設定「yolov7s」を使用する
・学習結果フォルダ名は「nm_yolov5s_ep50」とする

(py_learn) python train.py --data data/nm_dataset/nm_dataset.yaml --weights yolov5s.pt --epochs 30 --name nm_yolov5s_ep50

(py_learn) python train.py --data data/nm_dataset/nm_dataset.yaml --weights yolov5s.pt --epochs 50 --name nm_yolov5s_ep50

(py_learn) python train.py --data data/nm_dataset/nm_dataset.yaml --weights yolov5s.pt --epochs 100 --name nm_yolov5s_ep50

学習回数の違いによる結果を比較する

学習回数	30	50	100
バッチ数	16
学習モデル	yolov5s.pt
データセット	nm_dataset
学習結果	nm_yolov5s_ep30	nm_yolov5s_ep50	nm_yolov5s_ep100
F1 curve
P curve
PR curve
R curve
混同行列 Confusion Matrix
評価指標
学習時間	23分20秒	38分31秒	1時間16分19秒

↑

実行結果を使って推論 †

「detect3_yolov5.py」で推論実行
・学習結果モデルを指定（ログレベルを'0'として識別経過を表示）

(py_learn) python detect3_yolov5.py -m ./runs/train/vd_yolov5s_ep100/weights/best.pt -ms ./runs/train/nm_yolov5s_ep50/weights/best.pt -l ./data/nm_dataset/vd_names_jp -i ../number/test_data/japan79.jpg --log 0

・実行ログ

(py_learn) python detect3_yolov5.py -m ./runs/train/vd_yolov5s_ep100/weights/best.pt -ms ./runs/train/nm_yolov5s_ep50/weights/best.pt -l ./data/nm_dataset/vd_names_jp -i ../number/test_data/japan79.jpg --log 0
 Starting..

Object detection+ YoloV5 Ver. 0.08: Starting application...
   OpenCV virsion : 4.9.0

   - Image File   :  ../number/test_data/japan79.jpg
   - YOLO v5      :  ultralytics/yolov5
   - Pretrained   :  ./runs/train/vd_yolov5s_ep100/weights/best.pt
   - Pretrained 2 :  ./runs/train/nm_yolov5s_ep50/weights/best.pt
   - Confidence lv:  0.25
   - Label file   :  ./data/nm_dataset/vd_names_jp
   - Program Title:  y
   - Speed flag   :  y
   - Processed out:  non
   - Use device   :  cuda:0
   - Log Level    :  0

Using cache found in C:\Users\izuts/.cache\torch\hub\ultralytics_yolov5_master
YOLOv5  2024-4-9 Python-3.11.8 torch-2.2.1+cu121 CUDA:0 (NVIDIA GeForce RTX 4070 Ti, 12282MiB)

Fusing layers...
Model summary: 157 layers, 7015519 parameters, 0 gradients, 15.8 GFLOPs
Adding AutoShape...
Using cache found in C:\Users\izuts/.cache\torch\hub\ultralytics_yolov5_master
YOLOv5  2024-4-9 Python-3.11.8 torch-2.2.1+cu121 CUDA:0 (NVIDIA GeForce RTX 4070 Ti, 12282MiB)

Fusing layers...
Model summary: 157 layers, 7182733 parameters, 0 gradients, 16.3 GFLOPs
Adding AutoShape...

** Bounding Box:
[[     117.31      68.326       463.6      223.57     0.85471           0]
 [     185.14         145      247.09      238.57     0.98435          11]
 [     237.82      146.53      309.99      238.75     0.97927           6]
 [     334.89      149.99      398.25      241.71     0.97658           7]
 [     395.26       148.3      456.66      245.42     0.96122           6]
 [     311.43      83.831       349.9      137.64     0.90122           9]
 [      351.6      84.356         392      136.87     0.86674          11]
 [     350.22      85.405      391.93      136.08     0.47585           7]]

(117, 68)-(463, 223)    ナンバー: 0.85
(185, 144)-(247, 238)   9: 0.98
(237, 146)-(309, 238)   4: 0.98
(334, 149)-(398, 241)   5: 0.98
(395, 148)-(456, 245)   4: 0.96
(311, 83)-(349, 137)    7: 0.90
(351, 84)-(392, 136)    9: 0.87
(350, 85)-(391, 136)    5: 0.48

FPS average:       6.90

 Finished.

「detect3_number.py」で推論実行
・学習結果モデルを指定（ログレベルを'0'として識別経過を表示）

(py_learn) python detect3_number.py --log 0

・実行ログ

(py_learn) python detect3_number.py --log 0
 Starting..

Number plate detection YOLOv5 Ver. 0.08: Starting application...
   OpenCV virsion : 4.9.0

   - Image File   :  ../number/test_data/japan78.jpg
   - YOLO v5      :  ultralytics/yolov5
   - Pretrained   :  ./runs/train/vd_yolov5s_ep100/weights/best.pt
   - Pretrained 2 :  ./runs/train/nm_yolov5s_ep50/weights/best.pt
   - Confidence lv:  0.25
   - Label file   :  ./data/nm_dataset/vd_names_jp
   - Program Title:  y
   - Speed flag   :  y
   - Processed out:  non
   - Use device   :  cuda:0
   - Log Level    :  0

Using cache found in C:\Users\izuts/.cache\torch\hub\ultralytics_yolov5_master
YOLOv5  2024-4-9 Python-3.11.8 torch-2.2.1+cu121 CUDA:0 (NVIDIA GeForce RTX 4070 Ti, 12282MiB)

Fusing layers...
Model summary: 157 layers, 7015519 parameters, 0 gradients, 15.8 GFLOPs
Adding AutoShape...
Using cache found in C:\Users\izuts/.cache\torch\hub\ultralytics_yolov5_master
YOLOv5  2024-4-9 Python-3.11.8 torch-2.2.1+cu121 CUDA:0 (NVIDIA GeForce RTX 4070 Ti, 12282MiB)

Fusing layers...
Model summary: 157 layers, 7182733 parameters, 0 gradients, 16.3 GFLOPs
Adding AutoShape...

** プレートラベル:
['ナンバー', 'ナンバープレート', '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'あ', 'い', 'う', 'え', 'か', 'き', 'く', 'け', 'こ', 'さ', 'す', 'せ', 'そ', 'た', 'ち', 'つ', 'て', 'と', 'な', 'に', 'ぬ', 'ね', 'の', 'は', 'ひ', 'ふ', 'ほ', 'ま', 'み', 'む', 'め', 'も', 'や', 'ゆ', 'よ', 'ら', 'り', 'る', 'れ', 'ろ', 'わ', 'を', '京都', 'なにわ', '大阪', '和泉', '堺', '奈良', '和歌山', '神戸', '徳島', '香川', '愛媛', '千葉']

** Bounding Box:
[[     61.591      38.322      510.12      262.66      0.4888           0]
 [     352.12      59.349      392.61      129.97     0.98521           2]
 [     315.72      59.296      354.99      131.48     0.98443           3]
 [     391.33      60.289       431.3      129.43     0.98215           2]
 [      344.3      148.63      433.98      289.92      0.9785           7]
 [     426.44      146.62      513.85      303.11     0.96134          10]
 [     84.134      152.66      159.09      231.37     0.58646          22]
 [     1.3103      181.38      54.892      325.32     0.57503          60]
 [     156.16      49.026      321.75      166.41     0.35428          55]]

Y** 最小値 を昇順にソートX:
[[     61.591      38.322      510.12      262.66      0.4888           0]
 [     156.16      49.026      321.75      166.41     0.35428          55]
 [     315.72      59.296      354.99      131.48     0.98443           3]
 [     352.12      59.349      392.61      129.97     0.98521           2]
 [     391.33      60.289       431.3      129.43     0.98215           2]
 [     426.44      146.62      513.85      303.11     0.96134          10]
 [      344.3      148.63      433.98      289.92      0.9785           7]
 [     84.134      152.66      159.09      231.37     0.58646          22]
 [     1.3103      181.38      54.892      325.32     0.57503          60]]

** 上下を分割する場所:
bbox = (61.59,38.32)-(510.12,262.66)  ylimit = 106.30  index = 5

** ナンバープレートの上部:
[[     61.591      38.322      510.12      262.66      0.4888           0]
 [     156.16      49.026      321.75      166.41     0.35428          55]
 [     315.72      59.296      354.99      131.48     0.98443           3]
 [     352.12      59.349      392.61      129.97     0.98521           2]
 [     391.33      60.289       431.3      129.43     0.98215           2]]

** ナンバープレートの下部:
[[     426.44      146.62      513.85      303.11     0.96134          10]
 [      344.3      148.63      433.98      289.92      0.9785           7]
 [     84.134      152.66      159.09      231.37     0.58646          22]
 [     1.3103      181.38      54.892      325.32     0.57503          60]]

** 上部 X最小値) を昇順にソート:
[[     61.591      38.322      510.12      262.66      0.4888           0]
 [     156.16      49.026      321.75      166.41     0.35428          55]
 [     315.72      59.296      354.99      131.48     0.98443           3]
 [     352.12      59.349      392.61      129.97     0.98521           2]
 [     391.33      60.289       431.3      129.43     0.98215           2]]

** 下部 X最小値) を昇順にソート:
[[     1.3103      181.38      54.892      325.32     0.57503          60]
 [     84.134      152.66      159.09      231.37     0.58646          22]
 [      344.3      148.63      433.98      289.92      0.9785           7]
 [     426.44      146.62      513.85      303.11     0.96134          10]]

** 上部下部を一つにする:
[[     61.591      38.322      510.12      262.66      0.4888           0]
 [     156.16      49.026      321.75      166.41     0.35428          55]
 [     315.72      59.296      354.99      131.48     0.98443           3]
 [     352.12      59.349      392.61      129.97     0.98521           2]
 [     391.33      60.289       431.3      129.43     0.98215           2]
 [     1.3103      181.38      54.892      325.32     0.57503          60]
 [     84.134      152.66      159.09      231.37     0.58646          22]
 [      344.3      148.63      433.98      289.92      0.9785           7]
 [     426.44      146.62      513.85      303.11     0.96134          10]]

** ナンバープレート解析結果: なにわ100 す58

FPS average:       7.80

 Finished.

「detect_number.py」で推論実行
・学習結果モデルを指定（ログレベルを'0'として識別経過を表示）

(py_learn) python detect_number.py --log 0

・実行ログ

(py_learn) python detect_number.py --log 0
 Starting..

Number plate detection Ver. 0.09: Starting application...
   OpenCV virsion : 4.9.0

   - Image File   :  ../number/test_data/japan74.jpg
   - YOLO v5      :  ultralytics/yolov5
   - Pretrained   :  ./runs/train/vd_yolov5s_ep100/weights/best.pt
   - Pretrained 2 :  ./runs/train/nm_yolov5s_ep50/weights/best.pt
   - Confidence lv:  0.4
   - Label file   :  ./data/nm_dataset/names_jp
   - Program Title:  y
   - Speed flag   :  y
   - Processed out:  non
   - Use device   :  cuda:0
   - Log Level    :  0

Using cache found in C:\Users\izuts/.cache\torch\hub\ultralytics_yolov5_master
YOLOv5  2024-4-9 Python-3.11.8 torch-2.2.1+cu121 CUDA:0 (NVIDIA GeForce RTX 4070 Ti, 12282MiB)

Fusing layers...
Model summary: 157 layers, 7015519 parameters, 0 gradients, 15.8 GFLOPs
Adding AutoShape...

** プレートラベル:
['0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'あ', 'い', 'う', 'え', 'か', 'き', 'く', 'け', 'こ', 'さ', 'す', 'せ', 'そ', 'た', 'ち', 'つ', 'て', 'と', 'な', 'に', 'ぬ', 'ね', 'の', 'は', 'ひ', 'ふ', 'ほ', 'ま', 'み', 'む', 'め', 'も', 'や', 'ゆ', 'よ', 'ら', 'り', 'る', 'れ', 'ろ', 'わ', 'を', '京都', 'なにわ', '大阪', '和泉', '堺', '奈良', '和歌山', '神戸', '徳島', '香川', '愛媛', '千葉']
Using cache found in C:\Users\izuts/.cache\torch\hub\ultralytics_yolov5_master
YOLOv5  2024-4-9 Python-3.11.8 torch-2.2.1+cu121 CUDA:0 (NVIDIA GeForce RTX 4070 Ti, 12282MiB)

Fusing layers...
Model summary: 157 layers, 7182733 parameters, 0 gradients, 16.3 GFLOPs
Adding AutoShape...

** プレートの Bounding Box:
[[     168.33       60.04      414.33      173.39     0.85431           0]]

** プレート画像 Bounding Box:
[[     174.72       13.63      194.84      47.704     0.98788           0]
 [     155.33      12.984      175.65       47.85     0.98763           0]
 [      136.1      12.444      156.45       47.14     0.98613           3]
 [     92.386      54.675      140.81         113     0.98496           0]
 [     56.594      53.658      97.797         113     0.98449           7]
 [      153.8      56.805      193.96         113     0.98116           4]
 [     193.16      57.049      234.76         113     0.98103           5]
 [     21.854      59.884       55.78      93.946     0.58157          30]
 [     57.435      5.9446      138.67      45.611     0.57542          53]
 [     193.21           0       243.2      11.105     0.41337           2]
 [     61.161      10.435      133.51      45.012     0.38094          54]]

Y** 最小値 を昇順にソートX:
[[     193.21           0       243.2      11.105     0.41337           2]
 [     57.435      5.9446      138.67      45.611     0.57542          53]
 [     61.161      10.435      133.51      45.012     0.38094          54]
 [      136.1      12.444      156.45       47.14     0.98613           3]
 [     155.33      12.984      175.65       47.85     0.98763           0]
 [     174.72       13.63      194.84      47.704     0.98788           0]
 [     56.594      53.658      97.797         113     0.98449           7]
 [     92.386      54.675      140.81         113     0.98496           0]
 [      153.8      56.805      193.96         113     0.98116           4]
 [     193.16      57.049      234.76         113     0.98103           5]
 [     21.854      59.884       55.78      93.946     0.58157          30]]

** 上下を分割する場所:
bbox = (0.00,0.00)-(246.00,113.00)  ylimit = 34.24  index = 6

** ナンバープレートの上部:
[[     193.21           0       243.2      11.105     0.41337           2]
 [     57.435      5.9446      138.67      45.611     0.57542          53]
 [     61.161      10.435      133.51      45.012     0.38094          54]
 [      136.1      12.444      156.45       47.14     0.98613           3]
 [     155.33      12.984      175.65       47.85     0.98763           0]
 [     174.72       13.63      194.84      47.704     0.98788           0]]

** ナンバープレートの下部:
[[     56.594      53.658      97.797         113     0.98449           7]
 [     92.386      54.675      140.81         113     0.98496           0]
 [      153.8      56.805      193.96         113     0.98116           4]
 [     193.16      57.049      234.76         113     0.98103           5]
 [     21.854      59.884       55.78      93.946     0.58157          30]]

** 上部 X最小値) を昇順にソート:
[[     57.435      5.9446      138.67      45.611     0.57542          53]
 [     61.161      10.435      133.51      45.012     0.38094          54]
 [      136.1      12.444      156.45       47.14     0.98613           3]
 [     155.33      12.984      175.65       47.85     0.98763           0]
 [     174.72       13.63      194.84      47.704     0.98788           0]
 [     193.21           0       243.2      11.105     0.41337           2]]

** 下部 X最小値) を昇順にソート:
[[     21.854      59.884       55.78      93.946     0.58157          30]
 [     56.594      53.658      97.797         113     0.98449           7]
 [     92.386      54.675      140.81         113     0.98496           0]
 [      153.8      56.805      193.96         113     0.98116           4]
 [     193.16      57.049      234.76         113     0.98103           5]]

** 上部下部を一つにする:
[[     57.435      5.9446      138.67      45.611     0.57542          53]
 [     61.161      10.435      133.51      45.012     0.38094          54]
 [      136.1      12.444      156.45       47.14     0.98613           3]
 [     155.33      12.984      175.65       47.85     0.98763           0]
 [     174.72       13.63      194.84      47.704     0.98788           0]
 [     193.21           0       243.2      11.105     0.41337           2]
 [     21.854      59.884       55.78      93.946     0.58157          30]
 [     56.594      53.658      97.797         113     0.98449           7]
 [     92.386      54.675      140.81         113     0.98496           0]
 [      153.8      56.805      193.96         113     0.98116           4]
 [     193.16      57.049      234.76         113     0.98103           5]]

** ナンバープレート解析結果: なにわ300 ぬ7045

FPS average:       5.90

 Finished.