Hugging Face's logo

Fardan
/
c_detr_finetuned_crack

Object Detection
Transformers
Safetensors
conditional_detr
Generated from Trainer
Model card Files
xet
Community
Fardan commited on
Commit
849df2f
·
verified ·
1 Parent(s): 81deb50

End of training

Browse files
Files changed (2) hide show
  1. README.md +104 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: microsoft/conditional-detr-resnet-50
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - crack_det-single-class
9
+ model-index:
10
+ - name: c_detr_finetuned_crack
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # c_detr_finetuned_crack
18
+
19
+ This model is a fine-tuned version of [microsoft/conditional-detr-resnet-50](https://huggingface.co/microsoft/conditional-detr-resnet-50) on the crack_det-single-class dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.7720
22
+ - Map: 0.7074
23
+ - Map 50: 0.9889
24
+ - Map 75: 0.8198
25
+ - Map Small: -1.0
26
+ - Map Medium: 0.4631
27
+ - Map Large: 0.7157
28
+ - Mar 1: 0.7587
29
+ - Mar 10: 0.8086
30
+ - Mar 100: 0.8472
31
+ - Mar Small: -1.0
32
+ - Mar Medium: 0.7188
33
+ - Mar Large: 0.8516
34
+ - Map Per Class: 0.7074
35
+ - Mar 100 Per Class: 0.8472
36
+ - Classes: 0
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 5e-05
56
+ - train_batch_size: 8
57
+ - eval_batch_size: 8
58
+ - seed: 42
59
+ - optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
60
+ - lr_scheduler_type: cosine
61
+ - num_epochs: 30
62
+
63
+ ### Training results
64
+
65
+ | Training Loss | Epoch | Step | Validation Loss | Map | Map 50 | Map 75 | Map Small | Map Medium | Map Large | Mar 1 | Mar 10 | Mar 100 | Mar Small | Mar Medium | Mar Large | Map Per Class | Mar 100 Per Class | Classes |
66
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------:|:---------:|:------:|:------:|:-------:|:---------:|:----------:|:---------:|:-------------:|:-----------------:|:-------:|
67
+ | No log | 1.0 | 210 | 1.4511 | 0.1004 | 0.3026 | 0.0548 | -1.0 | 0.0077 | 0.1038 | 0.2008 | 0.4616 | 0.7195 | -1.0 | 0.1688 | 0.7386 | 0.1004 | 0.7195 | 0 |
68
+ | No log | 2.0 | 420 | 1.2516 | 0.0905 | 0.2453 | 0.0614 | -1.0 | 0.1688 | 0.093 | 0.1899 | 0.5191 | 0.7853 | -1.0 | 0.4313 | 0.7976 | 0.0905 | 0.7853 | 0 |
69
+ | 1.6634 | 3.0 | 630 | 1.1064 | 0.2139 | 0.4163 | 0.2028 | -1.0 | 0.1033 | 0.2192 | 0.413 | 0.7189 | 0.8205 | -1.0 | 0.5938 | 0.8284 | 0.2139 | 0.8205 | 0 |
70
+ | 1.6634 | 4.0 | 840 | 0.9684 | 0.4121 | 0.6299 | 0.4671 | -1.0 | 0.1894 | 0.4219 | 0.5736 | 0.782 | 0.8398 | -1.0 | 0.7625 | 0.8425 | 0.4121 | 0.8398 | 0 |
71
+ | 1.0881 | 5.0 | 1050 | 0.8984 | 0.4627 | 0.6658 | 0.5446 | -1.0 | 0.2979 | 0.4723 | 0.6428 | 0.8143 | 0.86 | -1.0 | 0.7937 | 0.8623 | 0.4627 | 0.86 | 0 |
72
+ | 1.0881 | 6.0 | 1260 | 1.0028 | 0.4664 | 0.7552 | 0.5139 | -1.0 | 0.2459 | 0.4754 | 0.5501 | 0.783 | 0.8325 | -1.0 | 0.6875 | 0.8375 | 0.4664 | 0.8325 | 0 |
73
+ | 1.0881 | 7.0 | 1470 | 0.8905 | 0.5262 | 0.8111 | 0.6015 | -1.0 | 0.371 | 0.5339 | 0.6394 | 0.8321 | 0.8658 | -1.0 | 0.7625 | 0.8694 | 0.5262 | 0.8658 | 0 |
74
+ | 0.992 | 8.0 | 1680 | 0.8781 | 0.618 | 0.9105 | 0.6986 | -1.0 | 0.3757 | 0.6277 | 0.6853 | 0.8124 | 0.8564 | -1.0 | 0.7125 | 0.8614 | 0.618 | 0.8564 | 0 |
75
+ | 0.992 | 9.0 | 1890 | 0.8787 | 0.6643 | 0.9763 | 0.7691 | -1.0 | 0.3965 | 0.6742 | 0.7086 | 0.8017 | 0.8457 | -1.0 | 0.725 | 0.8499 | 0.6643 | 0.8457 | 0 |
76
+ | 0.9551 | 10.0 | 2100 | 0.8690 | 0.6572 | 0.9679 | 0.737 | -1.0 | 0.392 | 0.6665 | 0.713 | 0.8082 | 0.852 | -1.0 | 0.7937 | 0.854 | 0.6572 | 0.852 | 0 |
77
+ | 0.9551 | 11.0 | 2310 | 0.8356 | 0.6543 | 0.9343 | 0.7416 | -1.0 | 0.414 | 0.6633 | 0.7109 | 0.8172 | 0.8648 | -1.0 | 0.7125 | 0.8701 | 0.6543 | 0.8648 | 0 |
78
+ | 0.9588 | 12.0 | 2520 | 0.8476 | 0.6492 | 0.956 | 0.7496 | -1.0 | 0.4645 | 0.6562 | 0.6971 | 0.8109 | 0.8486 | -1.0 | 0.7375 | 0.8525 | 0.6492 | 0.8486 | 0 |
79
+ | 0.9588 | 13.0 | 2730 | 0.9063 | 0.6379 | 0.9608 | 0.7469 | -1.0 | 0.4929 | 0.644 | 0.6956 | 0.7706 | 0.8096 | -1.0 | 0.7125 | 0.813 | 0.6379 | 0.8096 | 0 |
80
+ | 0.9588 | 14.0 | 2940 | 0.8993 | 0.647 | 0.9674 | 0.7443 | -1.0 | 0.4055 | 0.6558 | 0.7013 | 0.7897 | 0.8283 | -1.0 | 0.7188 | 0.8321 | 0.647 | 0.8283 | 0 |
81
+ | 0.944 | 15.0 | 3150 | 0.8545 | 0.6804 | 0.9804 | 0.7761 | -1.0 | 0.4121 | 0.6895 | 0.7268 | 0.7874 | 0.8038 | -1.0 | 0.7063 | 0.8072 | 0.6804 | 0.8038 | 0 |
82
+ | 0.944 | 16.0 | 3360 | 0.8423 | 0.6671 | 0.9738 | 0.7776 | -1.0 | 0.4201 | 0.6762 | 0.7243 | 0.8109 | 0.8514 | -1.0 | 0.7375 | 0.8553 | 0.6671 | 0.8514 | 0 |
83
+ | 0.9288 | 17.0 | 3570 | 0.8323 | 0.6785 | 0.9845 | 0.7896 | -1.0 | 0.4709 | 0.6854 | 0.7302 | 0.7975 | 0.8392 | -1.0 | 0.7563 | 0.8421 | 0.6785 | 0.8392 | 0 |
84
+ | 0.9288 | 18.0 | 3780 | 0.8367 | 0.6676 | 0.9833 | 0.7846 | -1.0 | 0.5013 | 0.6744 | 0.7233 | 0.792 | 0.8444 | -1.0 | 0.6875 | 0.8499 | 0.6676 | 0.8444 | 0 |
85
+ | 0.9288 | 19.0 | 3990 | 0.8186 | 0.6799 | 0.9815 | 0.7832 | -1.0 | 0.454 | 0.6882 | 0.7262 | 0.8004 | 0.8438 | -1.0 | 0.7312 | 0.8477 | 0.6799 | 0.8438 | 0 |
86
+ | 0.8787 | 20.0 | 4200 | 0.8029 | 0.6936 | 0.9888 | 0.8104 | -1.0 | 0.4717 | 0.7014 | 0.7419 | 0.8063 | 0.8457 | -1.0 | 0.7 | 0.8508 | 0.6936 | 0.8457 | 0 |
87
+ | 0.8787 | 21.0 | 4410 | 0.7984 | 0.6925 | 0.9848 | 0.8231 | -1.0 | 0.4922 | 0.6996 | 0.7472 | 0.8015 | 0.8405 | -1.0 | 0.7063 | 0.8451 | 0.6925 | 0.8405 | 0 |
88
+ | 0.871 | 22.0 | 4620 | 0.7899 | 0.6954 | 0.9894 | 0.81 | -1.0 | 0.444 | 0.7039 | 0.7562 | 0.8099 | 0.8447 | -1.0 | 0.7437 | 0.8482 | 0.6954 | 0.8447 | 0 |
89
+ | 0.871 | 23.0 | 4830 | 0.7953 | 0.6981 | 0.9873 | 0.8177 | -1.0 | 0.4464 | 0.7065 | 0.7528 | 0.804 | 0.8367 | -1.0 | 0.7 | 0.8414 | 0.6981 | 0.8367 | 0 |
90
+ | 0.8376 | 24.0 | 5040 | 0.7875 | 0.697 | 0.9881 | 0.8162 | -1.0 | 0.4791 | 0.7054 | 0.7553 | 0.805 | 0.8405 | -1.0 | 0.725 | 0.8445 | 0.697 | 0.8405 | 0 |
91
+ | 0.8376 | 25.0 | 5250 | 0.7761 | 0.7021 | 0.9876 | 0.8154 | -1.0 | 0.4685 | 0.7104 | 0.7543 | 0.8099 | 0.8472 | -1.0 | 0.7375 | 0.851 | 0.7021 | 0.8472 | 0 |
92
+ | 0.8376 | 26.0 | 5460 | 0.7657 | 0.7044 | 0.9875 | 0.8291 | -1.0 | 0.48 | 0.7122 | 0.7532 | 0.8128 | 0.8507 | -1.0 | 0.7312 | 0.8549 | 0.7044 | 0.8507 | 0 |
93
+ | 0.8359 | 27.0 | 5670 | 0.7697 | 0.7052 | 0.9883 | 0.8224 | -1.0 | 0.4599 | 0.7137 | 0.7553 | 0.8088 | 0.8465 | -1.0 | 0.7188 | 0.851 | 0.7052 | 0.8465 | 0 |
94
+ | 0.8359 | 28.0 | 5880 | 0.7708 | 0.7072 | 0.9879 | 0.8273 | -1.0 | 0.4554 | 0.716 | 0.7574 | 0.8096 | 0.8493 | -1.0 | 0.7 | 0.8544 | 0.7072 | 0.8493 | 0 |
95
+ | 0.8179 | 29.0 | 6090 | 0.7714 | 0.7076 | 0.9887 | 0.8244 | -1.0 | 0.4626 | 0.7161 | 0.7589 | 0.8082 | 0.8463 | -1.0 | 0.725 | 0.8505 | 0.7076 | 0.8463 | 0 |
96
+ | 0.8179 | 30.0 | 6300 | 0.7720 | 0.7074 | 0.9889 | 0.8198 | -1.0 | 0.4631 | 0.7157 | 0.7587 | 0.8086 | 0.8472 | -1.0 | 0.7188 | 0.8516 | 0.7074 | 0.8472 | 0 |
97
+
98
+
99
+ ### Framework versions
100
+
101
+ - Transformers 4.55.4
102
+ - Pytorch 2.8.0+cu128
103
+ - Datasets 3.6.0
104
+ - Tokenizers 0.21.4
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55bb1f6ecd55fd71a04e813f916670c6a562db01b319039163ce85ac5a992081
3
  size 174075684
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3742e31bb215aa46b59138ca41859bd0a42dfbdfc10033f2b7778e90b779c95a
3
  size 174075684