Hugging Face's logo

mcity-data-engine
/
fisheye8k_microsoft_conditional-detr-resnet-50

Object Detection
Transformers
PyTorch
TensorBoard
conditional_detr
Generated from Trainer
Model card Files
xet
Metrics Community
5
Daniel Bogdoll commited on
Commit
0d2399e
·
verified ·
1 Parent(s): 5baf1c2

End of training

Browse files
Files changed (5) hide show
  1. README.md +6 -21
  2. pytorch_model.bin +1 -1
  3. runs/Feb12_11-43-31_mcity-rtx-4090/events.out.tfevents.1739378611.mcity-rtx-4090.1808996.0 +3 -0
  4. runs/Feb12_11-54-31_mcity-rtx-4090/events.out.tfevents.1739379272.mcity-rtx-4090.1816145.0 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
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 generator dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 1.4142
22
 
23
  ## Model description
24
 
@@ -38,34 +38,19 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 5e-05
41
- - train_batch_size: 32
42
  - eval_batch_size: 8
43
  - seed: 0
44
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: cosine
46
- - num_epochs: 30
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
- | Training Loss | Epoch | Step | Validation Loss |
52
- |:-------------:|:-----:|:-----:|:---------------:|
53
- | 1.1217 | 1.0 | 2644 | 1.4738 |
54
- | 0.9689 | 2.0 | 5288 | 1.4067 |
55
- | 0.9194 | 3.0 | 7932 | 1.3879 |
56
- | 0.8369 | 4.0 | 10576 | 1.3840 |
57
- | 0.8061 | 5.0 | 13220 | 1.4551 |
58
- | 0.7761 | 6.0 | 15864 | 1.4041 |
59
- | 0.7278 | 7.0 | 18508 | 1.3229 |
60
- | 0.7241 | 8.0 | 21152 | 1.4653 |
61
- | 0.7117 | 9.0 | 23796 | 1.3242 |
62
- | 0.6811 | 10.0 | 26440 | 1.3248 |
63
- | 0.6471 | 11.0 | 29084 | 1.3078 |
64
- | 0.6293 | 12.0 | 31728 | 1.3126 |
65
- | 0.638 | 13.0 | 34372 | 1.3298 |
66
- | 0.6134 | 14.0 | 37016 | 1.3913 |
67
- | 0.5773 | 15.0 | 39660 | 1.3278 |
68
- | 0.5653 | 16.0 | 42304 | 1.4142 |
69
 
70
 
71
  ### Framework versions
 
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 generator dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 1.2694
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 5e-05
41
+ - train_batch_size: 1
42
  - eval_batch_size: 8
43
  - seed: 0
44
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: cosine
46
+ - num_epochs: 1
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:-----:|:----:|:---------------:|
53
+ | 0.8592 | 1.0 | 5288 | 1.2694 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
54
 
55
 
56
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97822ecc2244d2f82fcd04da7e252d7cdd5917173f33a805534a3ae4a7f3388c
3
  size 174213178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17eee6e449d888b0ee139026a3b28c3fbadb1f49a19eadb15f38fc7483a93d4c
3
  size 174213178
runs/Feb12_11-43-31_mcity-rtx-4090/events.out.tfevents.1739378611.mcity-rtx-4090.1808996.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb765ffa2790d67dcbe573696abf535d2e92054a84b1a95bde5d78323c57248f
3
+ size 6157
runs/Feb12_11-54-31_mcity-rtx-4090/events.out.tfevents.1739379272.mcity-rtx-4090.1816145.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:912d88bdf8fb1a792eb366203f6bac720c5dfc7f4c926ad83b0fa68ac3346f2d
3
+ size 8893
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9244733d7440acb17477ba07b72211f417ccc61dd8f33f2f5b76484a6b1692d
3
  size 5624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f1df0bf996ee39e592d902ec53ad2dcad0016391ad98ede53ddc4937fac66f3
3
  size 5624