jongkook90 commited on
Commit
dfae973
β€’
1 Parent(s): e4eefda

Added files

Browse files
Files changed (5) hide show
  1. manga109.yaml +9 -0
  2. train_log.txt +25 -0
  3. weights/README.md +3 -0
  4. weights/best.pt +3 -0
  5. weights/last.pt +3 -0
manga109.yaml ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ names:
2
+ 0: frame
3
+ 1: face
4
+ 2: body
5
+ 3: text
6
+ path: ../datasets/manga109
7
+ test: null
8
+ train: images/train
9
+ val: images/train
train_log.txt ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
2
+ 1/3 2.56G 1.26 1.267 1.016 122 640: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 533/533 [01:08<00:00, 7.75it/s]^
3
+ Class Images Instances Box(P R mAP50 mAP50-95): 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 267/267 [01:07<00:00, 3.93it/s]
4
+ all 8519 114053 0.97 0.282 0.306 0.216
5
+
6
+ Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
7
+ 2/3 3.36G 1.001 0.7182 0.9132 154 640: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 533/533 [00:59<00:00, 8.92it/s]
8
+ Class Images Instances Box(P R mAP50 mAP50-95): 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 267/267 [01:07<00:00, 3.93it/s] all 8519 114053 0.969 0.288 0.31 0.225
9
+
10
+ Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
11
+ 3/3 3.37G 0.9513 0.6483 0.9023 127 640: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 533/533 [00:59<00:00, 8.93it/s]
12
+ Class Images Instances Box(P R mAP50 mAP50-95): 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 267/267 [01:21<00:00, 3.28it/s]
13
+ all 8519 114053 0.973 0.294 0.323 0.233
14
+ 3 epochs completed in 0.116 hours.
15
+ Optimizer stripped from runs/detect/train3/weights/last.pt, 6.2MB Optimizer stripped from runs/detect/train3/weights/best.pt, 6.2MB
16
+
17
+ Validating runs/detect/train3/weights/best.pt...
18
+ Ultralytics YOLOv8.0.120 πŸš€ Python-3.9.7 torch-2.0.0+cu118 CUDA:0 (NVIDIA GeForce RTX 3090, 24265MiB)
19
+ Model summary (fused): 168 layers, 3006428 parameters, 0 gradients
20
+ Class Images Instances Box(P R mAP50 mAP50-95): 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 267/267 [01:19<00:00, 3.37it/s]
21
+ all 8519 114053 0.973 0.294 0.323 0.233
22
+ frame 8519 36 1 0 0.000451 0.000198
23
+ body 8519 403 1 0 0.0344 0.0144
24
+ text 8519 113614 0.919 0.882 0.933 0.686
25
+ Speed: 0.1ms preprocess, 0.4ms inference, 0.0ms loss, 1.0ms postprocess per image
weights/README.md ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ yolov8 3epoch training
2
+
3
+ TODO: data augmentation, train result check
weights/best.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10e3090dc0b887a2a795a69ce69441b4051fabec43e62d4a4b32d196cad19c6e
3
+ size 6229166
weights/last.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3a27fcc2c2394ab27786eed38b07fcbabfa06983554e430fc9dd5240f5aa80a
3
+ size 6229166