私的AI研究会 > YOLOv7_Colab6
追加学習において元になる学習モデルの違いによる推論結果の相違を検証してみる。
!python train.py --workers 8 --batch-size 16 --data janken4_dataset.yaml --cfg cfg/training/yolov7.yaml --weights 'yolov7.pt' --name yolov7_custom4_60 --hyp data/hyp.scratch.p5.yaml --epochs 60 --device 0
2023-08-12 04:39:06.464026: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2023-08-12 04:39:07.386965: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
YOLOR 🚀 v0.1-122-g3b41c2c torch 2.0.1+cu118 CUDA:0 (Tesla T4, 15101.8125MB)
Namespace(weights='yolov7.pt', cfg='cfg/training/yolov7.yaml', data='janken4_dataset.yaml', hyp='data/hyp.scratch.p5.yaml', epochs=60, batch_size=16, img_size=[640, 640], rect=False, resume=False, nosave=False, notest=False, noautoanchor=False, evolve=False, bucket='', cache_images=False, image_weights=False, device='0', multi_scale=False, single_cls=False, adam=False, sync_bn=False, local_rank=-1, workers=8, project='runs/train', entity=None, name='yolov7_custom4_60', exist_ok=False, quad=False, linear_lr=False, label_smoothing=0.0, upload_dataset=False, bbox_interval=-1, save_period=-1, artifact_alias='latest', freeze=[0], v5_metric=False, world_size=1, global_rank=-1, save_dir='runs/train/yolov7_custom4_60', total_batch_size=16)
tensorboard: Start with 'tensorboard --logdir runs/train', view at http://localhost:6006/
hyperparameters: lr0=0.01, lrf=0.1, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=0.05, cls=0.3, cls_pw=1.0, obj=0.7, 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=0.2, scale=0.9, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, mosaic=1.0, mixup=0.15, copy_paste=0.0, paste_in=0.15, loss_ota=1
wandb: Install Weights & Biases for YOLOR logging with 'pip install wandb' (recommended)
Overriding model.yaml nc=80 with nc=3
from n params module arguments
0 -1 1 928 models.common.Conv [3, 32, 3, 1]
1 -1 1 18560 models.common.Conv [32, 64, 3, 2]
2 -1 1 36992 models.common.Conv [64, 64, 3, 1]
3 -1 1 73984 models.common.Conv [64, 128, 3, 2]
4 -1 1 8320 models.common.Conv [128, 64, 1, 1]
5 -2 1 8320 models.common.Conv [128, 64, 1, 1]
6 -1 1 36992 models.common.Conv [64, 64, 3, 1]
7 -1 1 36992 models.common.Conv [64, 64, 3, 1]
8 -1 1 36992 models.common.Conv [64, 64, 3, 1]
9 -1 1 36992 models.common.Conv [64, 64, 3, 1]
10 [-1, -3, -5, -6] 1 0 models.common.Concat [1]
11 -1 1 66048 models.common.Conv [256, 256, 1, 1]
12 -1 1 0 models.common.MP []
13 -1 1 33024 models.common.Conv [256, 128, 1, 1]
14 -3 1 33024 models.common.Conv [256, 128, 1, 1]
15 -1 1 147712 models.common.Conv [128, 128, 3, 2]
16 [-1, -3] 1 0 models.common.Concat [1]
17 -1 1 33024 models.common.Conv [256, 128, 1, 1]
18 -2 1 33024 models.common.Conv [256, 128, 1, 1]
19 -1 1 147712 models.common.Conv [128, 128, 3, 1]
20 -1 1 147712 models.common.Conv [128, 128, 3, 1]
21 -1 1 147712 models.common.Conv [128, 128, 3, 1]
22 -1 1 147712 models.common.Conv [128, 128, 3, 1]
23 [-1, -3, -5, -6] 1 0 models.common.Concat [1]
24 -1 1 263168 models.common.Conv [512, 512, 1, 1]
25 -1 1 0 models.common.MP []
26 -1 1 131584 models.common.Conv [512, 256, 1, 1]
27 -3 1 131584 models.common.Conv [512, 256, 1, 1]
28 -1 1 590336 models.common.Conv [256, 256, 3, 2]
29 [-1, -3] 1 0 models.common.Concat [1]
30 -1 1 131584 models.common.Conv [512, 256, 1, 1]
31 -2 1 131584 models.common.Conv [512, 256, 1, 1]
32 -1 1 590336 models.common.Conv [256, 256, 3, 1]
33 -1 1 590336 models.common.Conv [256, 256, 3, 1]
34 -1 1 590336 models.common.Conv [256, 256, 3, 1]
35 -1 1 590336 models.common.Conv [256, 256, 3, 1]
36 [-1, -3, -5, -6] 1 0 models.common.Concat [1]
37 -1 1 1050624 models.common.Conv [1024, 1024, 1, 1]
38 -1 1 0 models.common.MP []
39 -1 1 525312 models.common.Conv [1024, 512, 1, 1]
40 -3 1 525312 models.common.Conv [1024, 512, 1, 1]
41 -1 1 2360320 models.common.Conv [512, 512, 3, 2]
42 [-1, -3] 1 0 models.common.Concat [1]
43 -1 1 262656 models.common.Conv [1024, 256, 1, 1]
44 -2 1 262656 models.common.Conv [1024, 256, 1, 1]
45 -1 1 590336 models.common.Conv [256, 256, 3, 1]
46 -1 1 590336 models.common.Conv [256, 256, 3, 1]
47 -1 1 590336 models.common.Conv [256, 256, 3, 1]
48 -1 1 590336 models.common.Conv [256, 256, 3, 1]
49 [-1, -3, -5, -6] 1 0 models.common.Concat [1]
50 -1 1 1050624 models.common.Conv [1024, 1024, 1, 1]
51 -1 1 7609344 models.common.SPPCSPC [1024, 512, 1]
52 -1 1 131584 models.common.Conv [512, 256, 1, 1]
53 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
54 37 1 262656 models.common.Conv [1024, 256, 1, 1]
55 [-1, -2] 1 0 models.common.Concat [1]
56 -1 1 131584 models.common.Conv [512, 256, 1, 1]
57 -2 1 131584 models.common.Conv [512, 256, 1, 1]
58 -1 1 295168 models.common.Conv [256, 128, 3, 1]
59 -1 1 147712 models.common.Conv [128, 128, 3, 1]
60 -1 1 147712 models.common.Conv [128, 128, 3, 1]
61 -1 1 147712 models.common.Conv [128, 128, 3, 1]
62[-1, -2, -3, -4, -5, -6] 1 0 models.common.Concat [1]
63 -1 1 262656 models.common.Conv [1024, 256, 1, 1]
64 -1 1 33024 models.common.Conv [256, 128, 1, 1]
65 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
66 24 1 65792 models.common.Conv [512, 128, 1, 1]
67 [-1, -2] 1 0 models.common.Concat [1]
68 -1 1 33024 models.common.Conv [256, 128, 1, 1]
69 -2 1 33024 models.common.Conv [256, 128, 1, 1]
70 -1 1 73856 models.common.Conv [128, 64, 3, 1]
71 -1 1 36992 models.common.Conv [64, 64, 3, 1]
72 -1 1 36992 models.common.Conv [64, 64, 3, 1]
73 -1 1 36992 models.common.Conv [64, 64, 3, 1]
74[-1, -2, -3, -4, -5, -6] 1 0 models.common.Concat [1]
75 -1 1 65792 models.common.Conv [512, 128, 1, 1]
76 -1 1 0 models.common.MP []
77 -1 1 16640 models.common.Conv [128, 128, 1, 1]
78 -3 1 16640 models.common.Conv [128, 128, 1, 1]
79 -1 1 147712 models.common.Conv [128, 128, 3, 2]
80 [-1, -3, 63] 1 0 models.common.Concat [1]
81 -1 1 131584 models.common.Conv [512, 256, 1, 1]
82 -2 1 131584 models.common.Conv [512, 256, 1, 1]
83 -1 1 295168 models.common.Conv [256, 128, 3, 1]
84 -1 1 147712 models.common.Conv [128, 128, 3, 1]
85 -1 1 147712 models.common.Conv [128, 128, 3, 1]
86 -1 1 147712 models.common.Conv [128, 128, 3, 1]
87[-1, -2, -3, -4, -5, -6] 1 0 models.common.Concat [1]
88 -1 1 262656 models.common.Conv [1024, 256, 1, 1]
89 -1 1 0 models.common.MP []
90 -1 1 66048 models.common.Conv [256, 256, 1, 1]
91 -3 1 66048 models.common.Conv [256, 256, 1, 1]
92 -1 1 590336 models.common.Conv [256, 256, 3, 2]
93 [-1, -3, 51] 1 0 models.common.Concat [1]
94 -1 1 525312 models.common.Conv [1024, 512, 1, 1]
95 -2 1 525312 models.common.Conv [1024, 512, 1, 1]
96 -1 1 1180160 models.common.Conv [512, 256, 3, 1]
97 -1 1 590336 models.common.Conv [256, 256, 3, 1]
98 -1 1 590336 models.common.Conv [256, 256, 3, 1]
99 -1 1 590336 models.common.Conv [256, 256, 3, 1]
100[-1, -2, -3, -4, -5, -6] 1 0 models.common.Concat [1]
101 -1 1 1049600 models.common.Conv [2048, 512, 1, 1]
102 75 1 328704 models.common.RepConv [128, 256, 3, 1]
103 88 1 1312768 models.common.RepConv [256, 512, 3, 1]
104 101 1 5246976 models.common.RepConv [512, 1024, 3, 1]
105 [102, 103, 104] 1 44944 models.yolo.IDetect [3, [[12, 16, 19, 36, 40, 28], [36, 75, 76, 55, 72, 146], [142, 110, 192, 243, 459, 401]], [256, 512, 1024]]
Model Summary: 415 layers, 37207344 parameters, 37207344 gradients
Transferred 552/566 items from yolov7.pt
Scaled weight_decay = 0.0005
Optimizer groups: 95 .bias, 95 conv.weight, 98 other
train: Scanning 'data/janken4_dataset/train/labels.cache' images and labels... 480 found, 0 missing, 0 empty, 0 corrupted: 100% 480/480 [00:00<?, ?it/s]
val: Scanning 'data/janken4_dataset/valid/labels.cache' images and labels... 120 found, 0 missing, 0 empty, 0 corrupted: 100% 120/120 [00:00<?, ?it/s]
autoanchor: Analyzing anchors... anchors/target = 3.61, Best Possible Recall (BPR) = 1.0000
Image sizes 640 train, 640 test
Using 2 dataloader workers
Logging results to runs/train/yolov7_custom4_60
Starting training for 60 epochs...
Epoch gpu_mem box obj cls total labels img_size
0/59 12.7G 0.0655 0.01588 0.02114 0.1025 41 640: 100% 30/30 [00:54<00:00, 1.81s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 0% 0/4 [00:00<?, ?it/s]/usr/local/lib/python3.10/dist-packages/torch/functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3483.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:10<00:00, 2.60s/it]
all 120 120 0.0253 0.0833 0.0119 0.00193
Epoch gpu_mem box obj cls total labels img_size
1/59 13.7G 0.05883 0.0134 0.02144 0.09367 52 640: 100% 30/30 [00:36<00:00, 1.22s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.36it/s]
all 120 120 0.156 0.2 0.127 0.0331
Epoch gpu_mem box obj cls total labels img_size
2/59 12.2G 0.05407 0.01261 0.02084 0.08752 40 640: 100% 30/30 [00:33<00:00, 1.13s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.87it/s]
all 120 120 0.181 0.45 0.209 0.0686
Epoch gpu_mem box obj cls total labels img_size
3/59 12.2G 0.04925 0.0118 0.01848 0.07953 42 640: 100% 30/30 [00:35<00:00, 1.18s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.43it/s]
all 120 120 0.224 0.619 0.306 0.105
Epoch gpu_mem box obj cls total labels img_size
4/59 12.2G 0.0409 0.01026 0.0164 0.06756 41 640: 100% 30/30 [00:37<00:00, 1.24s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.54it/s]
all 120 120 0.354 0.529 0.366 0.187
Epoch gpu_mem box obj cls total labels img_size
5/59 12.2G 0.04628 0.009895 0.01608 0.07226 45 640: 100% 30/30 [00:33<00:00, 1.12s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00, 1.29it/s]
all 120 120 0.338 0.675 0.437 0.232
Epoch gpu_mem box obj cls total labels img_size
6/59 12.3G 0.04424 0.009543 0.01654 0.07032 38 640: 100% 30/30 [00:33<00:00, 1.13s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00, 1.21it/s]
all 120 120 0.323 0.5 0.316 0.152
Epoch gpu_mem box obj cls total labels img_size
7/59 12.3G 0.04503 0.009459 0.01842 0.07291 46 640: 100% 30/30 [00:33<00:00, 1.13s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.58it/s]
all 120 120 0.148 0.158 0.0994 0.0219
Epoch gpu_mem box obj cls total labels img_size
8/59 12.3G 0.04467 0.009455 0.01753 0.07165 46 640: 100% 30/30 [00:32<00:00, 1.10s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.57it/s]
all 120 120 0.389 0.521 0.386 0.173
Epoch gpu_mem box obj cls total labels img_size
9/59 12.3G 0.03854 0.008963 0.01559 0.06309 47 640: 100% 30/30 [00:32<00:00, 1.09s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.78it/s]
all 120 120 0.329 0.553 0.4 0.185
Epoch gpu_mem box obj cls total labels img_size
10/59 12.3G 0.04359 0.009271 0.0179 0.07076 46 640: 100% 30/30 [00:32<00:00, 1.10s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.73it/s]
all 120 120 0.463 0.667 0.543 0.284
Epoch gpu_mem box obj cls total labels img_size
11/59 12.3G 0.04083 0.008669 0.01515 0.06465 61 640: 100% 30/30 [00:35<00:00, 1.18s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.71it/s]
all 120 120 0.604 0.653 0.677 0.458
Epoch gpu_mem box obj cls total labels img_size
12/59 12.3G 0.03363 0.008123 0.01301 0.05477 39 640: 100% 30/30 [00:34<00:00, 1.16s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.65it/s]
all 120 120 0.536 0.758 0.659 0.381
Epoch gpu_mem box obj cls total labels img_size
13/59 12.3G 0.03971 0.008277 0.0134 0.06138 49 640: 100% 30/30 [00:32<00:00, 1.07s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.62it/s]
all 120 120 0.559 0.874 0.758 0.418
Epoch gpu_mem box obj cls total labels img_size
14/59 12.3G 0.0343 0.007569 0.01243 0.05429 34 640: 100% 30/30 [00:35<00:00, 1.17s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.62it/s]
all 120 120 0.361 0.507 0.435 0.246
Epoch gpu_mem box obj cls total labels img_size
15/59 12.3G 0.04379 0.007736 0.01517 0.0667 38 640: 100% 30/30 [00:32<00:00, 1.08s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00, 1.09it/s]
all 120 120 0.577 0.851 0.728 0.434
Epoch gpu_mem box obj cls total labels img_size
16/59 12.3G 0.03496 0.007798 0.01282 0.05558 54 640: 100% 30/30 [00:32<00:00, 1.09s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.45it/s]
all 120 120 0.621 0.85 0.783 0.496
Epoch gpu_mem box obj cls total labels img_size
17/59 12.3G 0.03472 0.00784 0.01268 0.05524 51 640: 100% 30/30 [00:35<00:00, 1.18s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 2.00it/s]
all 120 120 0.563 0.824 0.755 0.378
Epoch gpu_mem box obj cls total labels img_size
18/59 12.3G 0.03389 0.007578 0.01125 0.05272 46 640: 100% 30/30 [00:33<00:00, 1.11s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.47it/s]
all 120 120 0.696 0.85 0.847 0.597
Epoch gpu_mem box obj cls total labels img_size
19/59 12.3G 0.03135 0.007049 0.01091 0.04931 41 640: 100% 30/30 [00:32<00:00, 1.07s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.80it/s]
all 120 120 0.0354 0.025 0.0137 0.00365
Epoch gpu_mem box obj cls total labels img_size
20/59 12.3G 0.03758 0.007605 0.01135 0.05653 37 640: 100% 30/30 [00:34<00:00, 1.15s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.77it/s]
all 120 120 0.127 0.308 0.128 0.0368
Epoch gpu_mem box obj cls total labels img_size
21/59 12.3G 0.03337 0.008026 0.01194 0.05333 66 640: 100% 30/30 [00:32<00:00, 1.07s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00, 1.16it/s]
all 120 120 0.6 0.817 0.779 0.426
Epoch gpu_mem box obj cls total labels img_size
22/59 12.3G 0.02771 0.007421 0.009318 0.04445 57 640: 100% 30/30 [00:31<00:00, 1.05s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.61it/s]
all 120 120 0.792 0.917 0.957 0.587
Epoch gpu_mem box obj cls total labels img_size
23/59 12.3G 0.03711 0.007451 0.011 0.05556 36 640: 100% 30/30 [00:33<00:00, 1.12s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.63it/s]
all 120 120 0.883 0.838 0.931 0.611
Epoch gpu_mem box obj cls total labels img_size
24/59 12.3G 0.03473 0.008045 0.01299 0.05577 29 640: 100% 30/30 [00:34<00:00, 1.16s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.36it/s]
all 120 120 0.431 0.432 0.398 0.18
Epoch gpu_mem box obj cls total labels img_size
25/59 12.3G 0.03577 0.00824 0.01158 0.05559 39 640: 100% 30/30 [00:32<00:00, 1.08s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.53it/s]
all 120 120 0.662 0.47 0.559 0.32
Epoch gpu_mem box obj cls total labels img_size
26/59 12.3G 0.03351 0.007618 0.01082 0.05196 44 640: 100% 30/30 [00:32<00:00, 1.09s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.87it/s]
all 120 120 0.933 0.833 0.932 0.594
Epoch gpu_mem box obj cls total labels img_size
27/59 12.3G 0.03254 0.007645 0.01069 0.05088 43 640: 100% 30/30 [00:33<00:00, 1.11s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.43it/s]
all 120 120 0.848 0.868 0.895 0.494
Epoch gpu_mem box obj cls total labels img_size
28/59 12.3G 0.03056 0.007958 0.009669 0.04819 38 640: 100% 30/30 [00:32<00:00, 1.09s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.66it/s]
all 120 120 0.765 0.738 0.83 0.463
Epoch gpu_mem box obj cls total labels img_size
29/59 12.3G 0.03073 0.007189 0.008787 0.04671 48 640: 100% 30/30 [00:31<00:00, 1.06s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00, 1.12it/s]
all 120 120 0.727 0.775 0.865 0.488
Epoch gpu_mem box obj cls total labels img_size
30/59 12.3G 0.0359 0.008134 0.01183 0.05587 40 640: 100% 30/30 [00:31<00:00, 1.06s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00, 1.12it/s]
all 120 0 0 0 0 0
Epoch gpu_mem box obj cls total labels img_size
31/59 12.3G 0.05076 0.009205 0.01713 0.07709 47 640: 100% 30/30 [00:33<00:00, 1.10s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.44it/s]
all 120 120 8.7e-05 0.00833 2.39e-06 2.39e-07
Epoch gpu_mem box obj cls total labels img_size
32/59 12.3G 0.04147 0.009063 0.01496 0.06549 35 640: 100% 30/30 [00:34<00:00, 1.14s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00, 1.17it/s]
all 120 120 0.289 0.525 0.366 0.154
Epoch gpu_mem box obj cls total labels img_size
33/59 12.3G 0.03584 0.008767 0.01396 0.05857 51 640: 100% 30/30 [00:32<00:00, 1.09s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.53it/s]
all 120 120 0.663 0.547 0.539 0.352
Epoch gpu_mem box obj cls total labels img_size
34/59 12.3G 0.02592 0.008929 0.01188 0.04673 54 640: 100% 30/30 [00:35<00:00, 1.17s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.52it/s]
all 120 120 0.379 0.2 0.0352 0.0119
Epoch gpu_mem box obj cls total labels img_size
35/59 12.3G 0.03416 0.008859 0.01416 0.05719 33 640: 100% 30/30 [00:34<00:00, 1.15s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.50it/s]
all 120 120 0.0413 0.192 0.0302 0.00566
Epoch gpu_mem box obj cls total labels img_size
36/59 12.3G 0.0344 0.008209 0.01296 0.05557 47 640: 100% 30/30 [00:32<00:00, 1.09s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.74it/s]
all 120 120 0.374 0.167 0.0193 0.00409
Epoch gpu_mem box obj cls total labels img_size
37/59 12.3G 0.03576 0.008361 0.01207 0.05619 34 640: 100% 30/30 [00:35<00:00, 1.19s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.60it/s]
all 120 120 0.75 0.824 0.866 0.504
Epoch gpu_mem box obj cls total labels img_size
38/59 12.3G 0.03391 0.008713 0.01222 0.05484 47 640: 100% 30/30 [00:33<00:00, 1.12s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.47it/s]
all 120 120 0.926 0.699 0.858 0.509
Epoch gpu_mem box obj cls total labels img_size
39/59 12.3G 0.03165 0.008483 0.01224 0.05237 51 640: 100% 30/30 [00:32<00:00, 1.09s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00, 1.03it/s]
all 120 120 0.837 0.821 0.888 0.521
Epoch gpu_mem box obj cls total labels img_size
40/59 12.3G 0.03651 0.008153 0.01233 0.05699 50 640: 100% 30/30 [00:34<00:00, 1.13s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.61it/s]
all 120 120 0.964 0.791 0.931 0.627
Epoch gpu_mem box obj cls total labels img_size
41/59 12.3G 0.03448 0.008189 0.01283 0.0555 43 640: 100% 30/30 [00:33<00:00, 1.13s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.62it/s]
all 120 120 0.889 0.833 0.906 0.552
Epoch gpu_mem box obj cls total labels img_size
42/59 12.3G 0.03436 0.007916 0.0121 0.05438 54 640: 100% 30/30 [00:32<00:00, 1.09s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.35it/s]
all 120 120 0.96 0.882 0.953 0.627
Epoch gpu_mem box obj cls total labels img_size
43/59 12.3G 0.03836 0.007986 0.01204 0.05839 56 640: 100% 30/30 [00:36<00:00, 1.22s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00, 1.12it/s]
all 120 120 0.923 0.898 0.957 0.614
Epoch gpu_mem box obj cls total labels img_size
44/59 12.3G 0.03659 0.007802 0.0124 0.05679 32 640: 100% 30/30 [00:33<00:00, 1.10s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00, 1.08it/s]
all 120 120 0.934 0.917 0.946 0.634
Epoch gpu_mem box obj cls total labels img_size
45/59 12.3G 0.03852 0.007942 0.01252 0.05898 50 640: 100% 30/30 [00:36<00:00, 1.21s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00, 1.25it/s]
all 120 120 0.963 0.899 0.96 0.67
Epoch gpu_mem box obj cls total labels img_size
46/59 12.3G 0.02613 0.007814 0.009601 0.04354 28 640: 100% 30/30 [00:34<00:00, 1.15s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00, 1.08it/s]
all 120 120 0.89 0.925 0.953 0.65
Epoch gpu_mem box obj cls total labels img_size
47/59 12.3G 0.02763 0.007562 0.00991 0.0451 35 640: 100% 30/30 [00:32<00:00, 1.07s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.46it/s]
all 120 120 0.937 0.841 0.954 0.643
Epoch gpu_mem box obj cls total labels img_size
48/59 12.3G 0.03783 0.007672 0.01187 0.05738 45 640: 100% 30/30 [00:33<00:00, 1.12s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.72it/s]
all 120 120 0.953 0.888 0.962 0.669
Epoch gpu_mem box obj cls total labels img_size
49/59 12.3G 0.03591 0.007994 0.01135 0.05525 53 640: 100% 30/30 [00:36<00:00, 1.20s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.74it/s]
all 120 120 0.956 0.933 0.96 0.684
Epoch gpu_mem box obj cls total labels img_size
50/59 12.3G 0.03541 0.007798 0.01175 0.05496 51 640: 100% 30/30 [00:37<00:00, 1.26s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.49it/s]
all 120 120 0.931 0.958 0.971 0.708
Epoch gpu_mem box obj cls total labels img_size
51/59 12.3G 0.03112 0.007489 0.009969 0.04858 51 640: 100% 30/30 [00:33<00:00, 1.13s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.53it/s]
all 120 120 0.911 0.917 0.95 0.664
Epoch gpu_mem box obj cls total labels img_size
52/59 12.3G 0.02915 0.007615 0.008901 0.04567 51 640: 100% 30/30 [00:34<00:00, 1.14s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.59it/s]
all 120 120 0.908 0.95 0.963 0.669
Epoch gpu_mem box obj cls total labels img_size
53/59 12.3G 0.03253 0.007544 0.01018 0.05025 56 640: 100% 30/30 [00:34<00:00, 1.16s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00, 1.14it/s]
all 120 120 0.928 0.949 0.967 0.673
Epoch gpu_mem box obj cls total labels img_size
54/59 12.3G 0.03003 0.007436 0.01009 0.04757 56 640: 100% 30/30 [00:32<00:00, 1.09s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.50it/s]
all 120 120 0.922 0.917 0.955 0.665
Epoch gpu_mem box obj cls total labels img_size
55/59 12.3G 0.02957 0.007782 0.01087 0.04822 59 640: 100% 30/30 [00:35<00:00, 1.18s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.68it/s]
all 120 120 0.912 0.946 0.955 0.675
Epoch gpu_mem box obj cls total labels img_size
56/59 12.3G 0.03473 0.007387 0.01116 0.05328 46 640: 100% 30/30 [00:36<00:00, 1.22s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.63it/s]
all 120 120 0.947 0.956 0.967 0.703
Epoch gpu_mem box obj cls total labels img_size
57/59 12.3G 0.03051 0.007138 0.00989 0.04754 44 640: 100% 30/30 [00:36<00:00, 1.21s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.52it/s]
all 120 120 0.97 0.956 0.973 0.719
Epoch gpu_mem box obj cls total labels img_size
58/59 12.3G 0.03035 0.007344 0.01042 0.04812 47 640: 100% 30/30 [00:35<00:00, 1.18s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.52it/s]
all 120 120 0.973 0.938 0.973 0.714
Epoch gpu_mem box obj cls total labels img_size
59/59 12.3G 0.03188 0.007449 0.01055 0.04988 49 640: 100% 30/30 [00:35<00:00, 1.18s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:04<00:00, 1.10s/it]
all 120 120 0.935 0.967 0.979 0.698
goo 120 40 0.952 1 0.995 0.663
choki 120 40 0.926 0.95 0.962 0.645
par 120 40 0.927 0.95 0.981 0.784
60 epochs completed in 0.674 hours.
Optimizer stripped from runs/train/yolov7_custom4_60/weights/last.pt, 74.8MB
Optimizer stripped from runs/train/yolov7_custom4_60/weights/best.pt, 74.8MB
!python train.py --workers 8 --batch-size 16 --data janken3_dataset.yaml --cfg cfg/training/yolov7.yaml --weights 'yolov7.pt' --name yolov7_custom3_60 --hyp data/hyp.scratch.p5.yaml --epochs 60 --device 0
2023-08-12 05:22:20.932544: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2023-08-12 05:22:22.698835: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
YOLOR 🚀 v0.1-122-g3b41c2c torch 2.0.1+cu118 CUDA:0 (Tesla T4, 15101.8125MB)
Namespace(weights='yolov7.pt', cfg='cfg/training/yolov7.yaml', data='janken3_dataset.yaml', hyp='data/hyp.scratch.p5.yaml', epochs=60, batch_size=16, img_size=[640, 640], rect=False, resume=False, nosave=False, notest=False, noautoanchor=False, evolve=False, bucket='', cache_images=False, image_weights=False, device='0', multi_scale=False, single_cls=False, adam=False, sync_bn=False, local_rank=-1, workers=8, project='runs/train', entity=None, name='yolov7_custom3_60', exist_ok=False, quad=False, linear_lr=False, label_smoothing=0.0, upload_dataset=False, bbox_interval=-1, save_period=-1, artifact_alias='latest', freeze=[0], v5_metric=False, world_size=1, global_rank=-1, save_dir='runs/train/yolov7_custom3_60', total_batch_size=16)
tensorboard: Start with 'tensorboard --logdir runs/train', view at http://localhost:6006/
hyperparameters: lr0=0.01, lrf=0.1, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=0.05, cls=0.3, cls_pw=1.0, obj=0.7, 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=0.2, scale=0.9, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, mosaic=1.0, mixup=0.15, copy_paste=0.0, paste_in=0.15, loss_ota=1
wandb: Install Weights & Biases for YOLOR logging with 'pip install wandb' (recommended)
Overriding model.yaml nc=80 with nc=3
from n params module arguments
0 -1 1 928 models.common.Conv [3, 32, 3, 1]
1 -1 1 18560 models.common.Conv [32, 64, 3, 2]
2 -1 1 36992 models.common.Conv [64, 64, 3, 1]
3 -1 1 73984 models.common.Conv [64, 128, 3, 2]
4 -1 1 8320 models.common.Conv [128, 64, 1, 1]
5 -2 1 8320 models.common.Conv [128, 64, 1, 1]
6 -1 1 36992 models.common.Conv [64, 64, 3, 1]
7 -1 1 36992 models.common.Conv [64, 64, 3, 1]
8 -1 1 36992 models.common.Conv [64, 64, 3, 1]
9 -1 1 36992 models.common.Conv [64, 64, 3, 1]
10 [-1, -3, -5, -6] 1 0 models.common.Concat [1]
11 -1 1 66048 models.common.Conv [256, 256, 1, 1]
12 -1 1 0 models.common.MP []
13 -1 1 33024 models.common.Conv [256, 128, 1, 1]
14 -3 1 33024 models.common.Conv [256, 128, 1, 1]
15 -1 1 147712 models.common.Conv [128, 128, 3, 2]
16 [-1, -3] 1 0 models.common.Concat [1]
17 -1 1 33024 models.common.Conv [256, 128, 1, 1]
18 -2 1 33024 models.common.Conv [256, 128, 1, 1]
19 -1 1 147712 models.common.Conv [128, 128, 3, 1]
20 -1 1 147712 models.common.Conv [128, 128, 3, 1]
21 -1 1 147712 models.common.Conv [128, 128, 3, 1]
22 -1 1 147712 models.common.Conv [128, 128, 3, 1]
23 [-1, -3, -5, -6] 1 0 models.common.Concat [1]
24 -1 1 263168 models.common.Conv [512, 512, 1, 1]
25 -1 1 0 models.common.MP []
26 -1 1 131584 models.common.Conv [512, 256, 1, 1]
27 -3 1 131584 models.common.Conv [512, 256, 1, 1]
28 -1 1 590336 models.common.Conv [256, 256, 3, 2]
29 [-1, -3] 1 0 models.common.Concat [1]
30 -1 1 131584 models.common.Conv [512, 256, 1, 1]
31 -2 1 131584 models.common.Conv [512, 256, 1, 1]
32 -1 1 590336 models.common.Conv [256, 256, 3, 1]
33 -1 1 590336 models.common.Conv [256, 256, 3, 1]
34 -1 1 590336 models.common.Conv [256, 256, 3, 1]
35 -1 1 590336 models.common.Conv [256, 256, 3, 1]
36 [-1, -3, -5, -6] 1 0 models.common.Concat [1]
37 -1 1 1050624 models.common.Conv [1024, 1024, 1, 1]
38 -1 1 0 models.common.MP []
39 -1 1 525312 models.common.Conv [1024, 512, 1, 1]
40 -3 1 525312 models.common.Conv [1024, 512, 1, 1]
41 -1 1 2360320 models.common.Conv [512, 512, 3, 2]
42 [-1, -3] 1 0 models.common.Concat [1]
43 -1 1 262656 models.common.Conv [1024, 256, 1, 1]
44 -2 1 262656 models.common.Conv [1024, 256, 1, 1]
45 -1 1 590336 models.common.Conv [256, 256, 3, 1]
46 -1 1 590336 models.common.Conv [256, 256, 3, 1]
47 -1 1 590336 models.common.Conv [256, 256, 3, 1]
48 -1 1 590336 models.common.Conv [256, 256, 3, 1]
49 [-1, -3, -5, -6] 1 0 models.common.Concat [1]
50 -1 1 1050624 models.common.Conv [1024, 1024, 1, 1]
51 -1 1 7609344 models.common.SPPCSPC [1024, 512, 1]
52 -1 1 131584 models.common.Conv [512, 256, 1, 1]
53 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
54 37 1 262656 models.common.Conv [1024, 256, 1, 1]
55 [-1, -2] 1 0 models.common.Concat [1]
56 -1 1 131584 models.common.Conv [512, 256, 1, 1]
57 -2 1 131584 models.common.Conv [512, 256, 1, 1]
58 -1 1 295168 models.common.Conv [256, 128, 3, 1]
59 -1 1 147712 models.common.Conv [128, 128, 3, 1]
60 -1 1 147712 models.common.Conv [128, 128, 3, 1]
61 -1 1 147712 models.common.Conv [128, 128, 3, 1]
62[-1, -2, -3, -4, -5, -6] 1 0 models.common.Concat [1]
63 -1 1 262656 models.common.Conv [1024, 256, 1, 1]
64 -1 1 33024 models.common.Conv [256, 128, 1, 1]
65 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
66 24 1 65792 models.common.Conv [512, 128, 1, 1]
67 [-1, -2] 1 0 models.common.Concat [1]
68 -1 1 33024 models.common.Conv [256, 128, 1, 1]
69 -2 1 33024 models.common.Conv [256, 128, 1, 1]
70 -1 1 73856 models.common.Conv [128, 64, 3, 1]
71 -1 1 36992 models.common.Conv [64, 64, 3, 1]
72 -1 1 36992 models.common.Conv [64, 64, 3, 1]
73 -1 1 36992 models.common.Conv [64, 64, 3, 1]
74[-1, -2, -3, -4, -5, -6] 1 0 models.common.Concat [1]
75 -1 1 65792 models.common.Conv [512, 128, 1, 1]
76 -1 1 0 models.common.MP []
77 -1 1 16640 models.common.Conv [128, 128, 1, 1]
78 -3 1 16640 models.common.Conv [128, 128, 1, 1]
79 -1 1 147712 models.common.Conv [128, 128, 3, 2]
80 [-1, -3, 63] 1 0 models.common.Concat [1]
81 -1 1 131584 models.common.Conv [512, 256, 1, 1]
82 -2 1 131584 models.common.Conv [512, 256, 1, 1]
83 -1 1 295168 models.common.Conv [256, 128, 3, 1]
84 -1 1 147712 models.common.Conv [128, 128, 3, 1]
85 -1 1 147712 models.common.Conv [128, 128, 3, 1]
86 -1 1 147712 models.common.Conv [128, 128, 3, 1]
87[-1, -2, -3, -4, -5, -6] 1 0 models.common.Concat [1]
88 -1 1 262656 models.common.Conv [1024, 256, 1, 1]
89 -1 1 0 models.common.MP []
90 -1 1 66048 models.common.Conv [256, 256, 1, 1]
91 -3 1 66048 models.common.Conv [256, 256, 1, 1]
92 -1 1 590336 models.common.Conv [256, 256, 3, 2]
93 [-1, -3, 51] 1 0 models.common.Concat [1]
94 -1 1 525312 models.common.Conv [1024, 512, 1, 1]
95 -2 1 525312 models.common.Conv [1024, 512, 1, 1]
96 -1 1 1180160 models.common.Conv [512, 256, 3, 1]
97 -1 1 590336 models.common.Conv [256, 256, 3, 1]
98 -1 1 590336 models.common.Conv [256, 256, 3, 1]
99 -1 1 590336 models.common.Conv [256, 256, 3, 1]
100[-1, -2, -3, -4, -5, -6] 1 0 models.common.Concat [1]
101 -1 1 1049600 models.common.Conv [2048, 512, 1, 1]
102 75 1 328704 models.common.RepConv [128, 256, 3, 1]
103 88 1 1312768 models.common.RepConv [256, 512, 3, 1]
104 101 1 5246976 models.common.RepConv [512, 1024, 3, 1]
105 [102, 103, 104] 1 44944 models.yolo.IDetect [3, [[12, 16, 19, 36, 40, 28], [36, 75, 76, 55, 72, 146], [142, 110, 192, 243, 459, 401]], [256, 512, 1024]]
Model Summary: 415 layers, 37207344 parameters, 37207344 gradients
Transferred 552/566 items from yolov7.pt
Scaled weight_decay = 0.0005
Optimizer groups: 95 .bias, 95 conv.weight, 98 other
train: Scanning 'data/janken3_dataset/train/labels.cache' images and labels... 480 found, 0 missing, 0 empty, 0 corrupted: 100% 480/480 [00:00<?, ?it/s]
val: Scanning 'data/janken3_dataset/valid/labels.cache' images and labels... 120 found, 0 missing, 0 empty, 0 corrupted: 100% 120/120 [00:00<?, ?it/s]
autoanchor: Analyzing anchors... anchors/target = 3.23, Best Possible Recall (BPR) = 1.0000
Image sizes 640 train, 640 test
Using 2 dataloader workers
Logging results to runs/train/yolov7_custom3_60
Starting training for 60 epochs...
Epoch gpu_mem box obj cls total labels img_size
0/59 12.6G 0.06392 0.01608 0.02108 0.1011 41 640: 100% 30/30 [00:53<00:00, 1.79s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 0% 0/4 [00:00<?, ?it/s]/usr/local/lib/python3.10/dist-packages/torch/functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3483.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:10<00:00, 2.54s/it]
all 120 120 0.0135 0.2 0.00994 0.00177
Epoch gpu_mem box obj cls total labels img_size
1/59 13.7G 0.05595 0.01398 0.02087 0.09079 55 640: 100% 30/30 [00:33<00:00, 1.12s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.75it/s]
all 120 120 0.0545 0.258 0.0456 0.0105
Epoch gpu_mem box obj cls total labels img_size
2/59 11.6G 0.05177 0.01314 0.01907 0.08398 44 640: 100% 30/30 [00:31<00:00, 1.04s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.57it/s]
all 120 120 0.1 0.525 0.108 0.031
Epoch gpu_mem box obj cls total labels img_size
3/59 11.6G 0.04776 0.01193 0.01787 0.07757 44 640: 100% 30/30 [00:31<00:00, 1.05s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:01<00:00, 2.02it/s]
all 120 120 0.209 0.483 0.253 0.0867
Epoch gpu_mem box obj cls total labels img_size
4/59 11.6G 0.04004 0.01061 0.01551 0.06617 46 640: 100% 30/30 [00:33<00:00, 1.12s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.41it/s]
all 120 120 0.318 0.665 0.312 0.163
Epoch gpu_mem box obj cls total labels img_size
5/59 11.6G 0.04804 0.01025 0.01631 0.0746 51 640: 100% 30/30 [00:31<00:00, 1.05s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:01<00:00, 2.33it/s]
all 120 120 0.294 0.642 0.339 0.112
Epoch gpu_mem box obj cls total labels img_size
6/59 11.6G 0.04171 0.01043 0.01615 0.06829 43 640: 100% 30/30 [00:30<00:00, 1.01s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:01<00:00, 2.29it/s]
all 120 120 0.43 0.631 0.51 0.265
Epoch gpu_mem box obj cls total labels img_size
7/59 11.6G 0.04038 0.01014 0.01685 0.06737 46 640: 100% 30/30 [00:30<00:00, 1.02s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.50it/s]
all 120 120 0.188 0.292 0.166 0.0383
Epoch gpu_mem box obj cls total labels img_size
8/59 11.6G 0.04188 0.0104 0.017 0.06928 50 640: 100% 30/30 [00:31<00:00, 1.06s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:01<00:00, 2.03it/s]
all 120 120 0.547 0.64 0.571 0.367
Epoch gpu_mem box obj cls total labels img_size
9/59 11.6G 0.03696 0.009458 0.0157 0.06211 57 640: 100% 30/30 [00:31<00:00, 1.05s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:01<00:00, 2.35it/s]
all 120 120 0.56 0.751 0.629 0.346
Epoch gpu_mem box obj cls total labels img_size
10/59 11.6G 0.04637 0.0103 0.01737 0.07403 53 640: 100% 30/30 [00:30<00:00, 1.01s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.56it/s]
all 120 120 0.439 0.699 0.522 0.268
Epoch gpu_mem box obj cls total labels img_size
11/59 11.6G 0.04121 0.009586 0.0154 0.06619 66 640: 100% 30/30 [00:30<00:00, 1.01s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00, 1.33it/s]
all 120 120 0.634 0.696 0.668 0.429
Epoch gpu_mem box obj cls total labels img_size
12/59 11.6G 0.03737 0.009223 0.01519 0.06179 42 640: 100% 30/30 [00:31<00:00, 1.04s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:01<00:00, 2.07it/s]
all 120 120 0.448 0.649 0.53 0.342
Epoch gpu_mem box obj cls total labels img_size
13/59 11.6G 0.03515 0.009031 0.01313 0.05731 47 640: 100% 30/30 [00:30<00:00, 1.02s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.73it/s]
all 120 120 0.501 0.683 0.657 0.396
Epoch gpu_mem box obj cls total labels img_size
14/59 11.6G 0.03449 0.008316 0.01299 0.0558 39 640: 100% 30/30 [00:30<00:00, 1.01s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.80it/s]
all 120 120 0.63 0.89 0.729 0.466
Epoch gpu_mem box obj cls total labels img_size
15/59 11.6G 0.04258 0.008812 0.01531 0.0667 41 640: 100% 30/30 [00:31<00:00, 1.04s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:01<00:00, 2.16it/s]
all 120 120 0.102 0.607 0.103 0.0211
Epoch gpu_mem box obj cls total labels img_size
16/59 11.6G 0.03593 0.009303 0.01429 0.05952 60 640: 100% 30/30 [00:30<00:00, 1.03s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:01<00:00, 2.28it/s]
all 120 120 0.318 0.45 0.369 0.214
Epoch gpu_mem box obj cls total labels img_size
17/59 11.6G 0.04171 0.00861 0.01399 0.06432 49 640: 100% 30/30 [00:29<00:00, 1.01it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.54it/s]
all 120 120 0.572 0.697 0.631 0.399
Epoch gpu_mem box obj cls total labels img_size
18/59 12.7G 0.03829 0.008912 0.01394 0.06114 48 640: 100% 30/30 [00:30<00:00, 1.02s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:01<00:00, 2.20it/s]
all 120 120 0.61 0.0417 0.0585 0.0207
Epoch gpu_mem box obj cls total labels img_size
19/59 12.7G 0.0433 0.00849 0.01423 0.06602 46 640: 100% 30/30 [00:31<00:00, 1.05s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:01<00:00, 2.22it/s]
all 120 120 0.557 0.767 0.648 0.406
Epoch gpu_mem box obj cls total labels img_size
20/59 12.7G 0.03898 0.008777 0.01423 0.06199 41 640: 100% 30/30 [00:30<00:00, 1.02s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.76it/s]
all 120 120 0.66 0.883 0.78 0.533
Epoch gpu_mem box obj cls total labels img_size
21/59 12.7G 0.03935 0.008717 0.01359 0.06165 74 640: 100% 30/30 [00:30<00:00, 1.03s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.91it/s]
all 120 120 0.666 0.908 0.802 0.569
Epoch gpu_mem box obj cls total labels img_size
22/59 12.7G 0.03176 0.008584 0.01214 0.05249 59 640: 100% 30/30 [00:30<00:00, 1.02s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:01<00:00, 2.13it/s]
all 120 120 0.269 0.458 0.295 0.15
Epoch gpu_mem box obj cls total labels img_size
23/59 12.7G 0.03309 0.008728 0.0126 0.05442 43 640: 100% 30/30 [00:32<00:00, 1.08s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.50it/s]
all 120 120 0.683 0.632 0.672 0.411
Epoch gpu_mem box obj cls total labels img_size
24/59 12.7G 0.04358 0.00911 0.01483 0.06752 34 640: 100% 30/30 [00:29<00:00, 1.00it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.80it/s]
all 120 120 0.503 0.736 0.608 0.355
Epoch gpu_mem box obj cls total labels img_size
25/59 12.7G 0.0357 0.009229 0.01314 0.05807 39 640: 100% 30/30 [00:30<00:00, 1.03s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:01<00:00, 2.30it/s]
all 120 120 0.446 0.283 0.123 0.0195
Epoch gpu_mem box obj cls total labels img_size
26/59 12.7G 0.03058 0.008919 0.01234 0.05184 54 640: 100% 30/30 [00:31<00:00, 1.05s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00, 1.17it/s]
all 120 120 0.604 0.85 0.808 0.62
Epoch gpu_mem box obj cls total labels img_size
27/59 12.7G 0.03078 0.009411 0.01305 0.05324 42 640: 100% 30/30 [00:30<00:00, 1.03s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.99it/s]
all 120 120 0.766 0.478 0.662 0.316
Epoch gpu_mem box obj cls total labels img_size
28/59 12.7G 0.02816 0.009119 0.01116 0.04843 44 640: 100% 30/30 [00:30<00:00, 1.02s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.92it/s]
all 120 120 0.889 0.808 0.904 0.684
Epoch gpu_mem box obj cls total labels img_size
29/59 12.7G 0.02871 0.00854 0.01069 0.04793 49 640: 100% 30/30 [00:30<00:00, 1.02s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.74it/s]
all 120 120 0.853 0.882 0.933 0.679
Epoch gpu_mem box obj cls total labels img_size
30/59 12.7G 0.03509 0.008991 0.01122 0.0553 42 640: 100% 30/30 [00:31<00:00, 1.07s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.84it/s]
all 120 120 0.935 0.843 0.941 0.711
Epoch gpu_mem box obj cls total labels img_size
31/59 12.7G 0.02851 0.008321 0.01069 0.04752 47 640: 100% 30/30 [00:30<00:00, 1.03s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:01<00:00, 2.17it/s]
all 120 120 0.825 0.836 0.915 0.677
Epoch gpu_mem box obj cls total labels img_size
32/59 12.7G 0.03077 0.008652 0.01101 0.05043 39 640: 100% 30/30 [00:30<00:00, 1.03s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.58it/s]
all 120 120 0.929 0.883 0.966 0.704
Epoch gpu_mem box obj cls total labels img_size
33/59 12.7G 0.02479 0.008295 0.009527 0.04261 54 640: 100% 30/30 [00:30<00:00, 1.03s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.40it/s]
all 120 120 0.997 0.939 0.978 0.731
Epoch gpu_mem box obj cls total labels img_size
34/59 12.7G 0.03003 0.008686 0.01057 0.04928 57 640: 100% 30/30 [00:31<00:00, 1.05s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.52it/s]
all 120 120 0.882 0.9 0.968 0.748
Epoch gpu_mem box obj cls total labels img_size
35/59 12.7G 0.03529 0.00881 0.01252 0.05661 37 640: 100% 30/30 [00:31<00:00, 1.04s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:01<00:00, 2.27it/s]
all 120 120 0.92 0.958 0.972 0.737
Epoch gpu_mem box obj cls total labels img_size
36/59 12.7G 0.02979 0.008072 0.01026 0.04813 51 640: 100% 30/30 [00:29<00:00, 1.01it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.84it/s]
all 120 120 0.941 0.889 0.965 0.721
Epoch gpu_mem box obj cls total labels img_size
37/59 12.7G 0.02517 0.008415 0.009834 0.04342 35 640: 100% 30/30 [00:31<00:00, 1.04s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:01<00:00, 2.29it/s]
all 120 120 0.91 0.958 0.979 0.767
Epoch gpu_mem box obj cls total labels img_size
38/59 12.7G 0.02472 0.008819 0.01013 0.04367 51 640: 100% 30/30 [00:30<00:00, 1.02s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:01<00:00, 2.13it/s]
all 120 120 0.403 0.474 0.44 0.311
Epoch gpu_mem box obj cls total labels img_size
39/59 12.7G 0.02786 0.008483 0.01069 0.04704 57 640: 100% 30/30 [00:29<00:00, 1.03it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:01<00:00, 2.15it/s]
all 120 120 0.687 0.717 0.834 0.592
Epoch gpu_mem box obj cls total labels img_size
40/59 12.7G 0.03067 0.008423 0.01033 0.04943 51 640: 100% 30/30 [00:31<00:00, 1.04s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00, 1.24it/s]
all 120 120 0.874 0.83 0.91 0.702
Epoch gpu_mem box obj cls total labels img_size
41/59 12.7G 0.02497 0.008397 0.009489 0.04285 42 640: 100% 30/30 [00:29<00:00, 1.03it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.91it/s]
all 120 120 0.939 0.942 0.973 0.702
Epoch gpu_mem box obj cls total labels img_size
42/59 12.7G 0.0359 0.008098 0.01275 0.05675 60 640: 100% 30/30 [00:28<00:00, 1.03it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:01<00:00, 2.02it/s]
all 120 120 0.927 0.926 0.982 0.785
Epoch gpu_mem box obj cls total labels img_size
43/59 12.7G 0.03463 0.008174 0.01061 0.05342 55 640: 100% 30/30 [00:30<00:00, 1.03s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.95it/s]
all 120 120 0.983 0.951 0.981 0.79
Epoch gpu_mem box obj cls total labels img_size
44/59 12.7G 0.03099 0.008286 0.01069 0.04996 37 640: 100% 30/30 [00:31<00:00, 1.07s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.91it/s]
all 120 120 0.897 0.933 0.954 0.703
Epoch gpu_mem box obj cls total labels img_size
45/59 12.7G 0.03582 0.008721 0.01145 0.05599 51 640: 100% 30/30 [00:30<00:00, 1.00s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:01<00:00, 2.00it/s]
all 120 120 0.932 0.813 0.909 0.616
Epoch gpu_mem box obj cls total labels img_size
46/59 12.7G 0.02606 0.008103 0.009442 0.0436 34 640: 100% 30/30 [00:29<00:00, 1.02it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:01<00:00, 2.16it/s]
all 120 120 0.952 0.942 0.98 0.788
Epoch gpu_mem box obj cls total labels img_size
47/59 12.7G 0.03226 0.007976 0.01042 0.05066 42 640: 100% 30/30 [00:29<00:00, 1.03it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.70it/s]
all 120 120 0.983 0.967 0.99 0.79
Epoch gpu_mem box obj cls total labels img_size
48/59 12.7G 0.03126 0.00772 0.009925 0.04891 49 640: 100% 30/30 [00:32<00:00, 1.08s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:01<00:00, 2.18it/s]
all 120 120 0.934 0.975 0.984 0.791
Epoch gpu_mem box obj cls total labels img_size
49/59 12.7G 0.03024 0.008196 0.009821 0.04826 58 640: 100% 30/30 [00:29<00:00, 1.00it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:01<00:00, 2.33it/s]
all 120 120 0.767 0.821 0.871 0.534
Epoch gpu_mem box obj cls total labels img_size
50/59 12.7G 0.03229 0.008107 0.01037 0.05077 50 640: 100% 30/30 [00:30<00:00, 1.01s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:01<00:00, 2.05it/s]
all 120 120 0.945 0.939 0.987 0.799
Epoch gpu_mem box obj cls total labels img_size
51/59 12.7G 0.03327 0.008078 0.01024 0.05159 57 640: 100% 30/30 [00:31<00:00, 1.05s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.62it/s]
all 120 120 0.959 0.964 0.991 0.792
Epoch gpu_mem box obj cls total labels img_size
52/59 12.7G 0.0292 0.008027 0.009851 0.04708 56 640: 100% 30/30 [00:29<00:00, 1.03it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.78it/s]
all 120 120 0.973 0.932 0.992 0.814
Epoch gpu_mem box obj cls total labels img_size
53/59 12.7G 0.02977 0.008009 0.009735 0.04751 61 640: 100% 30/30 [00:30<00:00, 1.01s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.66it/s]
all 120 120 0.945 0.767 0.925 0.652
Epoch gpu_mem box obj cls total labels img_size
54/59 12.7G 0.02548 0.008127 0.00901 0.04261 60 640: 100% 30/30 [00:29<00:00, 1.03it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.55it/s]
all 120 120 0.973 0.942 0.984 0.8
Epoch gpu_mem box obj cls total labels img_size
55/59 12.7G 0.02712 0.007881 0.008697 0.0437 61 640: 100% 30/30 [00:31<00:00, 1.06s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.96it/s]
all 120 120 0.975 0.961 0.99 0.811
Epoch gpu_mem box obj cls total labels img_size
56/59 12.7G 0.03204 0.007758 0.009953 0.04975 50 640: 100% 30/30 [00:30<00:00, 1.02s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.53it/s]
all 120 120 0.981 0.991 0.994 0.816
Epoch gpu_mem box obj cls total labels img_size
57/59 12.7G 0.02626 0.007599 0.009218 0.04308 51 640: 100% 30/30 [00:31<00:00, 1.05s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:01<00:00, 2.27it/s]
all 120 120 0.966 0.986 0.993 0.821
Epoch gpu_mem box obj cls total labels img_size
58/59 12.7G 0.02802 0.00765 0.009315 0.04499 48 640: 100% 30/30 [00:33<00:00, 1.10s/it]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.58it/s]
all 120 120 0.982 0.99 0.994 0.82
Epoch gpu_mem box obj cls total labels img_size
59/59 12.7G 0.02941 0.007589 0.009346 0.04634 49 640: 100% 30/30 [00:29<00:00, 1.00it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00, 1.32it/s]
all 120 120 0.967 0.99 0.993 0.808
goo 120 40 0.975 0.994 0.994 0.809
choki 120 40 0.952 1 0.993 0.781
par 120 40 0.973 0.975 0.993 0.833
60 epochs completed in 0.619 hours.
Optimizer stripped from runs/train/yolov7_custom3_60/weights/last.pt, 74.8MB
Optimizer stripped from runs/train/yolov7_custom3_60/weights/best.pt, 74.8MB
| 元モデル | yolov7 | yolov7x | yolov7 | yolov7x |
| データ | ④ janken4_dataset | ③ janken3_dataset | ||
| pixel: 640x480 train: 480 valid: 120 |  |  | ||
| バッチ数 | 16 | 16 | 18 | 18 |
| 学習回数 | 60 | 60 | 60 | 50 |
| 学習結果 | yolov7_custom4_60 | yolov7x_custom4_60 | yolov7_custom3_60 | yolov7x_custom3_60 |
| 混同行列 Confusion Matrix |  |  |  |  |
| 評価指標 |  |  |  |  |
| yolov7_custom4_60 | yolov7x_custom4_60 | yolov7_custom3_60 | yolov7x_custom3_60 | |
| janken3 .jpg |  |  |  |  |
| janken2 .jpg |  |  |  |  |
| janken .jpg |  |  |  |  |
| janken _test .mp4 | ||||
| janken _test2 .mp4 | ||||
| 実行速度 fps※1 | 2.36 | 1.44 | 2.48 | 1.44 |
| 実行速度 fps※2 | 7.06 | 4.62 | 7.42 | 4.62 |
| 実行速度 fps※3 | 5.20 | 3.30 | 5.73 | 3.62 |
| 実行速度 fps※4 | 2.26 | 1.30 | 2.20 | 1.26 |
| ※ | GPU | CPU | 実行マシン |
| 1 | Intel® HD Graphics 530 | Intel® Core™ i7-6700 | HP EliteDesk800 G2 SFF (第6世代 Core™ i7 CPU搭載 デスクトップ) |
| 2 | Intel® Iris® Xe Graphics | Intel® Core™ i7-1260P | DELL XPS Plus 9320 (第12世代 Core™ i7 CPU搭載 ノート) |
| 3 | Intel® Iris® Xe Graphics | Intel® Core™ i7-1185G7 | DELL Latitude 7520 (第11世代 Core™ i7 CPU搭載 ノート) |
| 4 | Intel® UHD Graphics | Intel® Core™ i5-10210U | Intel® NUC BXNUC10I5FNH (第10世代 Core™ i5 CPU搭載 ミニPC) |
(py38a) PS > cd /anaconda_win/work/yolov7・学習済みモデル「yolov7_custom4_60/weights/best.onnx」
| 入力ソース | コマンド |
| カメラ画像 | python object_detect_yolo7.py -m ../yolov7-main/runs/train/yolov7_custom4_60/weights/best.onnx -l janken.names_jp -i cam -d GPU |
| janken3.jpg | python object_detect_yolo7.py -m ../yolov7-main/runs/train/yolov7_custom4_60/weights/best.onnx -l janken.names_jp -i ../../Images/janken3.jpg -d GPU |
| janken2.jpg | python object_detect_yolo7.py -m ../yolov7-main/runs/train/yolov7_custom4_60/weights/best.onnx -l janken.names_jp -i ../../Images/janken2.jpg -d GPU |
| janken.jpg | python object_detect_yolo7.py -m ../yolov7-main/runs/train/yolov7_custom4_60/weights/best.onnx -l janken.names_jp -i ../../Images/janken.jpg -d GPU |
| janken_test.mp4 | python object_detect_yolo7.py -m ../yolov7-main/runs/train/yolov7_custom4_60/weights/best.onnx -l janken.names_jp -i ../../Videos/janken_test.mp4 -d GPU |
| janken_test2.mp4 | python object_detect_yolo7.py -m ../yolov7-main/runs/train/yolov7_custom4_60/weights/best.onnx -l janken.names_jp -i ../../Videos/janken_test2.mp4 -d GPU |
| 入力ソース | コマンド |
| カメラ画像 | python object_detect_yolo7.py -m ../yolov7-main/runs/train/yolov7x_custom4_60/weights/best.onnx -l janken.names_jp -i cam -d GPU |
| janken3.jpg | python object_detect_yolo7.py -m ../yolov7-main/runs/train/yolov7x_custom4_60/weights/best.onnx -l janken.names_jp -i ../../Images/janken3.jpg -d GPU |
| janken2.jpg | python object_detect_yolo7.py -m ../yolov7-main/runs/train/yolov7x_custom4_60/weights/best.onnx -l janken.names_jp -i ../../Images/janken2.jpg -d GPU |
| janken.jpg | python object_detect_yolo7.py -m ../yolov7-main/runs/train/yolov7x_custom4_60/weights/best.onnx -l janken.names_jp -i ../../Images/janken.jpg -d GPU |
| janken_test.mp4 | python object_detect_yolo7.py -m ../yolov7-main/runs/train/yolov7x_custom4_60/weights/best.onnx -l janken.names_jp -i ../../Videos/janken_test.mp4 -d GPU |
| janken_test2.mp4 | python object_detect_yolo7.py -m ../yolov7-main/runs/train/yolov7x_custom4_60/weights/best.onnx -l janken.names_jp -i ../../Videos/janken_test2.mp4 -d GPU |
| 入力ソース | コマンド |
| カメラ画像 | python object_detect_yolo7.py -m ../yolov7-main/runs/train/yolov7_custom3_60/weights/best.onnx -l janken.names_jp -i cam -d GPU |
| janken3.jpg | python object_detect_yolo7.py -m ../yolov7-main/runs/train/yolov7_custom3_60/weights/best.onnx -l janken.names_jp -i ../../Images/janken3.jpg -d GPU |
| janken2.jpg | python object_detect_yolo7.py -m ../yolov7-main/runs/train/yolov7_custom3_60/weights/best.onnx -l janken.names_jp -i ../../Images/janken2.jpg -d GPU |
| janken.jpg | python object_detect_yolo7.py -m ../yolov7-main/runs/train/yolov7_custom3_60/weights/best.onnx -l janken.names_jp -i ../../Images/janken.jpg -d GPU |
| janken_test.mp4 | python object_detect_yolo7.py -m ../yolov7-main/runs/train/yolov7_custom3_60/weights/best.onnx -l janken.names_jp -i ../../Videos/janken_test.mp4 -d GPU |
| janken_test2.mp4 | python object_detect_yolo7.py -m ../yolov7-main/runs/train/yolov7_custom3_60/weights/best.onnx -l janken.names_jp -i ../../Videos/janken_test2.mp4 -d GPU |
| 入力ソース | コマンド |
| カメラ画像 | python object_detect_yolo7.py -m ../yolov7-main/runs/train/yolov7x_custom3_60/weights/best.onnx -l janken.names_jp -i cam -d GPU |
| janken3.jpg | python object_detect_yolo7.py -m ../yolov7-main/runs/train/yolov7x_custom3_60/weights/best.onnx -l janken.names_jp -i ../../Images/janken3.jpg -d GPU |
| janken2.jpg | python object_detect_yolo7.py -m ../yolov7-main/runs/train/yolov7x_custom3_60/weights/best.onnx -l janken.names_jp -i ../../Images/janken2.jpg -d GPU |
| janken.jpg | python object_detect_yolo7.py -m ../yolov7-main/runs/train/yolov7x_custom3_60/weights/best.onnx -l janken.names_jp -i ../../Images/janken.jpg -d GPU |
| janken_test.mp4 | python object_detect_yolo7.py -m ../yolov7-main/runs/train/yolov7x_custom3_60/weights/best.onnx -l janken.names_jp -i ../../Videos/janken_test.mp4 -d GPU |
| janken_test2.mp4 | python object_detect_yolo7.py -m ../yolov7-main/runs/train/yolov7x_custom3_60/weights/best.onnx -l janken.names_jp -i ../../Videos/janken_test2.mp4 -d GPU |
matching_matrix = torch.zeros_like(cost, device=device) → matching_matrix = torch.zeros_like(cost, device="cpu") matching_matrix = torch.zeros_like(cost) → matching_matrix = torch.zeros_like(cost, device="cpu")
!python train_aux.py --workers 8 --batch-size 4 --data janken4_dataset.yaml --img 1280 1280 --cfg cfg/training/yolov7-w6.yaml --weights 'yolov7-w6.pt' --name yolov7-w6_custom4_60 --hyp data/hyp.scratch.p6.yaml --epochs 60 --device 0
2023-08-12 10:42:36.275029: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2023-08-12 10:42:37.465947: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
YOLOR 🚀 v0.1-122-g3b41c2c torch 2.0.1+cu118 CUDA:0 (Tesla T4, 15101.8125MB)
Namespace(weights='yolov7-w6.pt', cfg='cfg/training/yolov7-w6.yaml', data='janken4_dataset.yaml', hyp='data/hyp.scratch.p6.yaml', epochs=60, batch_size=4, img_size=[1280, 1280], rect=False, resume=False, nosave=False, notest=False, noautoanchor=False, evolve=False, bucket='', cache_images=False, image_weights=False, device='0', multi_scale=False, single_cls=False, adam=False, sync_bn=False, local_rank=-1, workers=8, project='runs/train', entity=None, name='yolov7-w6_custom4_60', exist_ok=False, quad=False, linear_lr=False, label_smoothing=0.0, upload_dataset=False, bbox_interval=-1, save_period=-1, artifact_alias='latest', v5_metric=False, world_size=1, global_rank=-1, save_dir='runs/train/yolov7-w6_custom4_604', total_batch_size=4)
tensorboard: Start with 'tensorboard --logdir runs/train', view at http://localhost:6006/
hyperparameters: lr0=0.01, lrf=0.2, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=0.05, cls=0.3, cls_pw=1.0, obj=0.7, 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=0.2, scale=0.9, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, mosaic=1.0, mixup=0.15, copy_paste=0.0, paste_in=0.15, loss_ota=1
wandb: Install Weights & Biases for YOLOR logging with 'pip install wandb' (recommended)
Overriding model.yaml nc=80 with nc=3
from n params module arguments
0 -1 1 0 models.common.ReOrg []
1 -1 1 7040 models.common.Conv [12, 64, 3, 1]
2 -1 1 73984 models.common.Conv [64, 128, 3, 2]
3 -1 1 8320 models.common.Conv [128, 64, 1, 1]
4 -2 1 8320 models.common.Conv [128, 64, 1, 1]
5 -1 1 36992 models.common.Conv [64, 64, 3, 1]
6 -1 1 36992 models.common.Conv [64, 64, 3, 1]
7 -1 1 36992 models.common.Conv [64, 64, 3, 1]
8 -1 1 36992 models.common.Conv [64, 64, 3, 1]
9 [-1, -3, -5, -6] 1 0 models.common.Concat [1]
10 -1 1 33024 models.common.Conv [256, 128, 1, 1]
11 -1 1 295424 models.common.Conv [128, 256, 3, 2]
12 -1 1 33024 models.common.Conv [256, 128, 1, 1]
13 -2 1 33024 models.common.Conv [256, 128, 1, 1]
14 -1 1 147712 models.common.Conv [128, 128, 3, 1]
15 -1 1 147712 models.common.Conv [128, 128, 3, 1]
16 -1 1 147712 models.common.Conv [128, 128, 3, 1]
17 -1 1 147712 models.common.Conv [128, 128, 3, 1]
18 [-1, -3, -5, -6] 1 0 models.common.Concat [1]
19 -1 1 131584 models.common.Conv [512, 256, 1, 1]
20 -1 1 1180672 models.common.Conv [256, 512, 3, 2]
21 -1 1 131584 models.common.Conv [512, 256, 1, 1]
22 -2 1 131584 models.common.Conv [512, 256, 1, 1]
23 -1 1 590336 models.common.Conv [256, 256, 3, 1]
24 -1 1 590336 models.common.Conv [256, 256, 3, 1]
25 -1 1 590336 models.common.Conv [256, 256, 3, 1]
26 -1 1 590336 models.common.Conv [256, 256, 3, 1]
27 [-1, -3, -5, -6] 1 0 models.common.Concat [1]
28 -1 1 525312 models.common.Conv [1024, 512, 1, 1]
29 -1 1 3540480 models.common.Conv [512, 768, 3, 2]
30 -1 1 295680 models.common.Conv [768, 384, 1, 1]
31 -2 1 295680 models.common.Conv [768, 384, 1, 1]
32 -1 1 1327872 models.common.Conv [384, 384, 3, 1]
33 -1 1 1327872 models.common.Conv [384, 384, 3, 1]
34 -1 1 1327872 models.common.Conv [384, 384, 3, 1]
35 -1 1 1327872 models.common.Conv [384, 384, 3, 1]
36 [-1, -3, -5, -6] 1 0 models.common.Concat [1]
37 -1 1 1181184 models.common.Conv [1536, 768, 1, 1]
38 -1 1 7079936 models.common.Conv [768, 1024, 3, 2]
39 -1 1 525312 models.common.Conv [1024, 512, 1, 1]
40 -2 1 525312 models.common.Conv [1024, 512, 1, 1]
41 -1 1 2360320 models.common.Conv [512, 512, 3, 1]
42 -1 1 2360320 models.common.Conv [512, 512, 3, 1]
43 -1 1 2360320 models.common.Conv [512, 512, 3, 1]
44 -1 1 2360320 models.common.Conv [512, 512, 3, 1]
45 [-1, -3, -5, -6] 1 0 models.common.Concat [1]
46 -1 1 2099200 models.common.Conv [2048, 1024, 1, 1]
47 -1 1 7609344 models.common.SPPCSPC [1024, 512, 1]
48 -1 1 197376 models.common.Conv [512, 384, 1, 1]
49 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
50 37 1 295680 models.common.Conv [768, 384, 1, 1]
51 [-1, -2] 1 0 models.common.Concat [1]
52 -1 1 295680 models.common.Conv [768, 384, 1, 1]
53 -2 1 295680 models.common.Conv [768, 384, 1, 1]
54 -1 1 663936 models.common.Conv [384, 192, 3, 1]
55 -1 1 332160 models.common.Conv [192, 192, 3, 1]
56 -1 1 332160 models.common.Conv [192, 192, 3, 1]
57 -1 1 332160 models.common.Conv [192, 192, 3, 1]
58[-1, -2, -3, -4, -5, -6] 1 0 models.common.Concat [1]
59 -1 1 590592 models.common.Conv [1536, 384, 1, 1]
60 -1 1 98816 models.common.Conv [384, 256, 1, 1]
61 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
62 28 1 131584 models.common.Conv [512, 256, 1, 1]
63 [-1, -2] 1 0 models.common.Concat [1]
64 -1 1 131584 models.common.Conv [512, 256, 1, 1]
65 -2 1 131584 models.common.Conv [512, 256, 1, 1]
66 -1 1 295168 models.common.Conv [256, 128, 3, 1]
67 -1 1 147712 models.common.Conv [128, 128, 3, 1]
68 -1 1 147712 models.common.Conv [128, 128, 3, 1]
69 -1 1 147712 models.common.Conv [128, 128, 3, 1]
70[-1, -2, -3, -4, -5, -6] 1 0 models.common.Concat [1]
71 -1 1 262656 models.common.Conv [1024, 256, 1, 1]
72 -1 1 33024 models.common.Conv [256, 128, 1, 1]
73 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
74 19 1 33024 models.common.Conv [256, 128, 1, 1]
75 [-1, -2] 1 0 models.common.Concat [1]
76 -1 1 33024 models.common.Conv [256, 128, 1, 1]
77 -2 1 33024 models.common.Conv [256, 128, 1, 1]
78 -1 1 73856 models.common.Conv [128, 64, 3, 1]
79 -1 1 36992 models.common.Conv [64, 64, 3, 1]
80 -1 1 36992 models.common.Conv [64, 64, 3, 1]
81 -1 1 36992 models.common.Conv [64, 64, 3, 1]
82[-1, -2, -3, -4, -5, -6] 1 0 models.common.Concat [1]
83 -1 1 65792 models.common.Conv [512, 128, 1, 1]
84 -1 1 295424 models.common.Conv [128, 256, 3, 2]
85 [-1, 71] 1 0 models.common.Concat [1]
86 -1 1 131584 models.common.Conv [512, 256, 1, 1]
87 -2 1 131584 models.common.Conv [512, 256, 1, 1]
88 -1 1 295168 models.common.Conv [256, 128, 3, 1]
89 -1 1 147712 models.common.Conv [128, 128, 3, 1]
90 -1 1 147712 models.common.Conv [128, 128, 3, 1]
91 -1 1 147712 models.common.Conv [128, 128, 3, 1]
92[-1, -2, -3, -4, -5, -6] 1 0 models.common.Concat [1]
93 -1 1 262656 models.common.Conv [1024, 256, 1, 1]
94 -1 1 885504 models.common.Conv [256, 384, 3, 2]
95 [-1, 59] 1 0 models.common.Concat [1]
96 -1 1 295680 models.common.Conv [768, 384, 1, 1]
97 -2 1 295680 models.common.Conv [768, 384, 1, 1]
98 -1 1 663936 models.common.Conv [384, 192, 3, 1]
99 -1 1 332160 models.common.Conv [192, 192, 3, 1]
100 -1 1 332160 models.common.Conv [192, 192, 3, 1]
101 -1 1 332160 models.common.Conv [192, 192, 3, 1]
102[-1, -2, -3, -4, -5, -6] 1 0 models.common.Concat [1]
103 -1 1 590592 models.common.Conv [1536, 384, 1, 1]
104 -1 1 1770496 models.common.Conv [384, 512, 3, 2]
105 [-1, 47] 1 0 models.common.Concat [1]
106 -1 1 525312 models.common.Conv [1024, 512, 1, 1]
107 -2 1 525312 models.common.Conv [1024, 512, 1, 1]
108 -1 1 1180160 models.common.Conv [512, 256, 3, 1]
109 -1 1 590336 models.common.Conv [256, 256, 3, 1]
110 -1 1 590336 models.common.Conv [256, 256, 3, 1]
111 -1 1 590336 models.common.Conv [256, 256, 3, 1]
112[-1, -2, -3, -4, -5, -6] 1 0 models.common.Concat [1]
113 -1 1 1049600 models.common.Conv [2048, 512, 1, 1]
114 83 1 295424 models.common.Conv [128, 256, 3, 1]
115 93 1 1180672 models.common.Conv [256, 512, 3, 1]
116 103 1 2655744 models.common.Conv [384, 768, 3, 1]
117 113 1 4720640 models.common.Conv [512, 1024, 3, 1]
118 83 1 369280 models.common.Conv [128, 320, 3, 1]
119 71 1 1475840 models.common.Conv [256, 640, 3, 1]
120 59 1 3319680 models.common.Conv [384, 960, 3, 1]
121 47 1 5900800 models.common.Conv [512, 1280, 3, 1]
122[114, 115, 116, 117, 118, 119, 120, 121] 1 141088 models.yolo.IAuxDetect [3, [[19, 27, 44, 40, 38, 94], [96, 68, 86, 152, 180, 137], [140, 301, 303, 264, 238, 542], [436, 615, 739, 380, 925, 792]], [256, 512, 768, 1024, 320, 640, 960, 1280]]
Model Summary: 477 layers, 80979104 parameters, 80979104 gradients
Transferred 618/668 items from yolov7-w6.pt
Scaled weight_decay = 0.0005
Optimizer groups: 115 .bias, 115 conv.weight, 115 other
train: Scanning 'data/janken4_dataset/train/labels.cache' images and labels... 480 found, 0 missing, 0 empty, 0 corrupted: 100% 480/480 [00:00<?, ?it/s]
val: Scanning 'data/janken4_dataset/valid/labels.cache' images and labels... 120 found, 0 missing, 0 empty, 0 corrupted: 100% 120/120 [00:00<?, ?it/s]
autoanchor: Analyzing anchors... anchors/target = 5.81, Best Possible Recall (BPR) = 1.0000
Image sizes 1280 train, 1280 test
Using 2 dataloader workers
Logging results to runs/train/yolov7-w6_custom4_604
Starting training for 60 epochs...
Epoch gpu_mem box obj cls total labels img_size
0/59 8.92G 0.07193 0.05038 0.02343 0.1457 6 1280: 100% 120/120 [01:36<00:00, 1.25it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 0% 0/15 [00:00<?, ?it/s]/usr/local/lib/python3.10/dist-packages/torch/functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3483.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:13<00:00, 1.08it/s]
all 120 120 0.0351 0.367 0.0358 0.00549
Epoch gpu_mem box obj cls total labels img_size
1/59 8.85G 0.06132 0.02975 0.02315 0.1142 10 1280: 100% 120/120 [01:29<00:00, 1.34it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:05<00:00, 2.98it/s]
all 120 120 0.201 0.525 0.176 0.0499
Epoch gpu_mem box obj cls total labels img_size
2/59 8.85G 0.05102 0.02268 0.02054 0.09424 4 1280: 100% 120/120 [01:29<00:00, 1.34it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:05<00:00, 2.68it/s]
all 120 120 0.191 0.567 0.229 0.0714
Epoch gpu_mem box obj cls total labels img_size
3/59 8.85G 0.05071 0.01989 0.02076 0.09136 12 1280: 100% 120/120 [01:27<00:00, 1.37it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.26it/s]
all 120 120 0.335 0.492 0.371 0.181
Epoch gpu_mem box obj cls total labels img_size
4/59 8.85G 0.04434 0.01715 0.01972 0.0812 19 1280: 100% 120/120 [01:25<00:00, 1.40it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.27it/s]
all 120 120 0.276 0.582 0.323 0.134
Epoch gpu_mem box obj cls total labels img_size
5/59 8.85G 0.04004 0.01502 0.01873 0.07378 9 1280: 100% 120/120 [01:25<00:00, 1.41it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:05<00:00, 2.86it/s]
all 120 120 0.296 0.672 0.409 0.177
Epoch gpu_mem box obj cls total labels img_size
6/59 8.85G 0.03984 0.01412 0.01886 0.07282 5 1280: 100% 120/120 [01:24<00:00, 1.42it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.32it/s]
all 120 120 0.308 0.889 0.461 0.247
Epoch gpu_mem box obj cls total labels img_size
7/59 8.85G 0.0434 0.0126 0.01879 0.0748 9 1280: 100% 120/120 [01:24<00:00, 1.42it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.26it/s]
all 120 120 0.22 0.783 0.266 0.0967
Epoch gpu_mem box obj cls total labels img_size
8/59 8.85G 0.04369 0.01102 0.01832 0.07303 5 1280: 100% 120/120 [01:26<00:00, 1.39it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.18it/s]
all 120 120 0.337 0.624 0.413 0.215
Epoch gpu_mem box obj cls total labels img_size
9/59 8.85G 0.03473 0.01087 0.01714 0.06274 10 1280: 100% 120/120 [01:22<00:00, 1.45it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:05<00:00, 2.88it/s]
all 120 120 0.366 0.783 0.449 0.152
Epoch gpu_mem box obj cls total labels img_size
10/59 8.85G 0.03986 0.01053 0.01824 0.06863 8 1280: 100% 120/120 [01:26<00:00, 1.38it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.24it/s]
all 120 120 0.402 0.843 0.524 0.307
Epoch gpu_mem box obj cls total labels img_size
11/59 8.85G 0.0349 0.01096 0.0181 0.06397 19 1280: 100% 120/120 [01:27<00:00, 1.37it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:05<00:00, 2.76it/s]
all 120 120 0.377 0.914 0.491 0.292
Epoch gpu_mem box obj cls total labels img_size
12/59 8.85G 0.03348 0.01093 0.01796 0.06237 10 1280: 100% 120/120 [01:25<00:00, 1.41it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.29it/s]
all 120 120 0.414 0.7 0.513 0.318
Epoch gpu_mem box obj cls total labels img_size
13/59 8.85G 0.03596 0.01072 0.01884 0.06552 11 1280: 100% 120/120 [01:27<00:00, 1.37it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.31it/s]
all 120 120 0.382 0.815 0.57 0.39
Epoch gpu_mem box obj cls total labels img_size
14/59 8.85G 0.03398 0.0101 0.0182 0.06228 7 1280: 100% 120/120 [01:26<00:00, 1.38it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:05<00:00, 2.91it/s]
all 120 120 0.354 0.898 0.598 0.425
Epoch gpu_mem box obj cls total labels img_size
15/59 8.85G 0.03744 0.01164 0.01922 0.0683 7 1280: 100% 120/120 [01:29<00:00, 1.35it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.28it/s]
all 120 120 0.355 0.913 0.556 0.367
Epoch gpu_mem box obj cls total labels img_size
16/59 8.85G 0.03361 0.01138 0.01874 0.06373 11 1280: 100% 120/120 [01:24<00:00, 1.42it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:05<00:00, 2.90it/s]
all 120 120 0.399 0.717 0.531 0.345
Epoch gpu_mem box obj cls total labels img_size
17/59 8.85G 0.03469 0.01107 0.01951 0.06527 12 1280: 100% 120/120 [01:24<00:00, 1.43it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.30it/s]
all 120 120 0.373 0.892 0.609 0.409
Epoch gpu_mem box obj cls total labels img_size
18/59 8.85G 0.03235 0.01084 0.01942 0.06262 13 1280: 100% 120/120 [01:26<00:00, 1.38it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:05<00:00, 2.93it/s]
all 120 120 0.394 0.942 0.646 0.484
Epoch gpu_mem box obj cls total labels img_size
19/59 8.85G 0.0285 0.01026 0.01884 0.0576 10 1280: 100% 120/120 [01:25<00:00, 1.40it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.15it/s]
all 120 120 0.396 0.853 0.601 0.456
Epoch gpu_mem box obj cls total labels img_size
20/59 8.85G 0.0313 0.01091 0.01926 0.06147 11 1280: 100% 120/120 [01:24<00:00, 1.42it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.05it/s]
all 120 120 0.359 0.932 0.662 0.481
Epoch gpu_mem box obj cls total labels img_size
21/59 8.85G 0.02865 0.01078 0.01944 0.05886 14 1280: 100% 120/120 [01:26<00:00, 1.39it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.30it/s]
all 120 120 0.425 0.833 0.711 0.507
Epoch gpu_mem box obj cls total labels img_size
22/59 8.85G 0.03151 0.01096 0.0195 0.06197 7 1280: 100% 120/120 [01:25<00:00, 1.40it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.34it/s]
all 120 120 0.517 0.848 0.741 0.551
Epoch gpu_mem box obj cls total labels img_size
23/59 8.85G 0.02962 0.01058 0.01921 0.05942 17 1280: 100% 120/120 [01:27<00:00, 1.38it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.02it/s]
all 120 120 0.571 0.886 0.769 0.557
Epoch gpu_mem box obj cls total labels img_size
24/59 8.85G 0.02797 0.01027 0.01908 0.05733 16 1280: 100% 120/120 [01:27<00:00, 1.37it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:05<00:00, 2.96it/s]
all 120 120 0.634 0.9 0.789 0.576
Epoch gpu_mem box obj cls total labels img_size
25/59 8.85G 0.02549 0.009864 0.01722 0.05257 13 1280: 100% 120/120 [01:28<00:00, 1.36it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:05<00:00, 2.94it/s]
all 120 120 0.628 0.956 0.797 0.58
Epoch gpu_mem box obj cls total labels img_size
26/59 8.85G 0.03115 0.009762 0.01782 0.05873 8 1280: 100% 120/120 [01:28<00:00, 1.36it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:05<00:00, 2.86it/s]
all 120 120 0.62 0.966 0.801 0.593
Epoch gpu_mem box obj cls total labels img_size
27/59 8.85G 0.02908 0.01015 0.01732 0.05655 9 1280: 100% 120/120 [01:28<00:00, 1.36it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.34it/s]
all 120 120 0.651 0.967 0.811 0.609
Epoch gpu_mem box obj cls total labels img_size
28/59 8.85G 0.02722 0.009631 0.01656 0.05341 12 1280: 100% 120/120 [01:26<00:00, 1.39it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.22it/s]
all 120 120 0.615 1 0.794 0.591
Epoch gpu_mem box obj cls total labels img_size
29/59 8.85G 0.02681 0.01002 0.01635 0.05318 7 1280: 100% 120/120 [01:27<00:00, 1.36it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:05<00:00, 2.89it/s]
all 120 120 0.657 0.986 0.812 0.611
Epoch gpu_mem box obj cls total labels img_size
30/59 8.85G 0.02727 0.009484 0.01679 0.05355 8 1280: 100% 120/120 [01:28<00:00, 1.36it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.07it/s]
all 120 120 0.652 1 0.818 0.602
Epoch gpu_mem box obj cls total labels img_size
31/59 8.85G 0.02733 0.009465 0.01619 0.05298 5 1280: 100% 120/120 [01:23<00:00, 1.43it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.28it/s]
all 120 120 0.639 0.997 0.811 0.599
Epoch gpu_mem box obj cls total labels img_size
32/59 8.85G 0.02681 0.008779 0.01627 0.05185 19 1280: 100% 120/120 [01:25<00:00, 1.40it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.28it/s]
all 120 120 0.659 0.997 0.818 0.616
Epoch gpu_mem box obj cls total labels img_size
33/59 8.85G 0.02612 0.009449 0.01593 0.0515 12 1280: 100% 120/120 [01:26<00:00, 1.39it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.22it/s]
all 120 120 0.649 0.992 0.823 0.635
Epoch gpu_mem box obj cls total labels img_size
34/59 8.85G 0.02528 0.008885 0.01521 0.04937 7 1280: 100% 120/120 [01:26<00:00, 1.39it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.33it/s]
all 120 120 0.653 1 0.803 0.625
Epoch gpu_mem box obj cls total labels img_size
35/59 8.85G 0.03001 0.009354 0.01686 0.05623 8 1280: 100% 120/120 [01:26<00:00, 1.39it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.09it/s]
all 120 120 0.651 1 0.82 0.622
Epoch gpu_mem box obj cls total labels img_size
36/59 8.85G 0.02564 0.009036 0.01529 0.04997 17 1280: 100% 120/120 [01:24<00:00, 1.42it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.14it/s]
all 120 120 0.643 1 0.817 0.624
Epoch gpu_mem box obj cls total labels img_size
37/59 8.85G 0.02765 0.009619 0.01618 0.05345 11 1280: 100% 120/120 [01:26<00:00, 1.38it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.23it/s]
all 120 120 0.652 0.965 0.818 0.632
Epoch gpu_mem box obj cls total labels img_size
38/59 8.85G 0.02639 0.009675 0.016 0.05206 10 1280: 100% 120/120 [01:24<00:00, 1.41it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:05<00:00, 2.58it/s]
all 120 120 0.654 1 0.849 0.666
Epoch gpu_mem box obj cls total labels img_size
39/59 8.85G 0.02614 0.0103 0.01617 0.05261 12 1280: 100% 120/120 [01:28<00:00, 1.36it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.13it/s]
all 120 120 0.698 0.915 0.86 0.655
Epoch gpu_mem box obj cls total labels img_size
40/59 8.85G 0.0247 0.009746 0.0149 0.04934 6 1280: 100% 120/120 [01:26<00:00, 1.38it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.26it/s]
all 120 120 0.782 0.857 0.892 0.687
Epoch gpu_mem box obj cls total labels img_size
41/59 8.85G 0.02454 0.009114 0.01487 0.04852 9 1280: 100% 120/120 [01:26<00:00, 1.38it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:05<00:00, 2.89it/s]
all 120 120 0.73 0.95 0.939 0.726
Epoch gpu_mem box obj cls total labels img_size
42/59 8.85G 0.02538 0.01016 0.01585 0.05139 20 1280: 100% 120/120 [01:30<00:00, 1.33it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:05<00:00, 2.84it/s]
all 120 120 0.808 0.925 0.949 0.737
Epoch gpu_mem box obj cls total labels img_size
43/59 8.85G 0.02543 0.01007 0.01576 0.05126 10 1280: 100% 120/120 [01:27<00:00, 1.36it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.31it/s]
all 120 120 0.826 0.95 0.967 0.747
Epoch gpu_mem box obj cls total labels img_size
44/59 8.85G 0.02414 0.009589 0.0145 0.04823 7 1280: 100% 120/120 [01:26<00:00, 1.39it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.29it/s]
all 120 120 0.853 0.939 0.963 0.738
Epoch gpu_mem box obj cls total labels img_size
45/59 8.85G 0.02389 0.009356 0.01378 0.04703 19 1280: 100% 120/120 [01:28<00:00, 1.36it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:05<00:00, 2.85it/s]
all 120 120 0.869 0.982 0.974 0.758
Epoch gpu_mem box obj cls total labels img_size
46/59 8.85G 0.02464 0.009571 0.01408 0.04829 12 1280: 100% 120/120 [01:29<00:00, 1.34it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:05<00:00, 2.95it/s]
all 120 120 0.898 0.975 0.988 0.743
Epoch gpu_mem box obj cls total labels img_size
47/59 8.85G 0.02323 0.009343 0.01312 0.0457 7 1280: 100% 120/120 [01:25<00:00, 1.40it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.31it/s]
all 120 120 0.885 0.983 0.977 0.743
Epoch gpu_mem box obj cls total labels img_size
48/59 8.85G 0.02214 0.008673 0.0117 0.04252 6 1280: 100% 120/120 [01:24<00:00, 1.41it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.12it/s]
all 120 120 0.909 0.958 0.97 0.755
Epoch gpu_mem box obj cls total labels img_size
49/59 8.85G 0.02403 0.00917 0.01216 0.04537 13 1280: 100% 120/120 [01:24<00:00, 1.41it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.07it/s]
all 120 120 0.945 0.977 0.989 0.75
Epoch gpu_mem box obj cls total labels img_size
50/59 8.85G 0.02422 0.009305 0.01206 0.04558 9 1280: 100% 120/120 [01:28<00:00, 1.35it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.06it/s]
all 120 120 0.964 0.984 0.993 0.756
Epoch gpu_mem box obj cls total labels img_size
51/59 8.85G 0.0243 0.009152 0.01185 0.0453 5 1280: 100% 120/120 [01:27<00:00, 1.37it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.20it/s]
all 120 120 0.943 0.999 0.994 0.76
Epoch gpu_mem box obj cls total labels img_size
52/59 8.85G 0.02312 0.008929 0.01093 0.04297 13 1280: 100% 120/120 [01:27<00:00, 1.38it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.12it/s]
all 120 120 0.964 0.992 0.996 0.75
Epoch gpu_mem box obj cls total labels img_size
53/59 8.85G 0.02246 0.009356 0.00974 0.04156 6 1280: 100% 120/120 [01:26<00:00, 1.39it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.30it/s]
all 120 120 0.967 0.994 0.996 0.755
Epoch gpu_mem box obj cls total labels img_size
54/59 8.85G 0.02408 0.00926 0.01121 0.04456 9 1280: 100% 120/120 [01:26<00:00, 1.39it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:05<00:00, 2.87it/s]
all 120 120 0.962 1 0.996 0.751
Epoch gpu_mem box obj cls total labels img_size
55/59 8.85G 0.02279 0.009419 0.01005 0.04226 13 1280: 100% 120/120 [01:25<00:00, 1.40it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.27it/s]
all 120 120 0.997 0.982 0.996 0.775
Epoch gpu_mem box obj cls total labels img_size
56/59 8.85G 0.02372 0.009141 0.01047 0.04333 5 1280: 100% 120/120 [01:30<00:00, 1.33it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.12it/s]
all 120 120 0.988 1 0.996 0.771
Epoch gpu_mem box obj cls total labels img_size
57/59 8.85G 0.02274 0.00875 0.009518 0.04101 13 1280: 100% 120/120 [01:27<00:00, 1.37it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.02it/s]
all 120 120 0.965 0.992 0.995 0.767
Epoch gpu_mem box obj cls total labels img_size
58/59 8.85G 0.02321 0.008917 0.01005 0.04217 7 1280: 100% 120/120 [01:27<00:00, 1.37it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:04<00:00, 3.30it/s]
all 120 120 0.974 0.97 0.99 0.762
Epoch gpu_mem box obj cls total labels img_size
59/59 8.85G 0.02205 0.008874 0.009621 0.04054 5 1280: 100% 120/120 [01:27<00:00, 1.37it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 15/15 [00:05<00:00, 2.62it/s]
all 120 120 0.987 0.992 0.996 0.747
goo 120 40 0.973 1 0.997 0.674
choki 120 40 1 0.975 0.996 0.732
par 120 40 0.988 1 0.997 0.836
60 epochs completed in 1.632 hours.
Optimizer stripped from runs/train/yolov7-w6_custom4_604/weights/last.pt, 162.6MB
Optimizer stripped from runs/train/yolov7-w6_custom4_604/weights/best.pt, 162.6MB
!python export.py --weights runs/train/yolov7-w6_custom4_60/weights/best.pt --img 1280 1280
PukiWiki 1.5.2 © 2001-2019 PukiWiki Development Team. Powered by PHP 7.4.3-4ubuntu2.20. HTML convert time: 0.374 sec.