Commit
·
d8b6c6f
1
Parent(s):
a09a9f1
update model card README.md
Browse files
README.md
CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [facebook/detr-resnet-101](https://huggingface.co/facebook/detr-resnet-101) on the cd45rb dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 1.
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
|
|
41 |
- seed: 42
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: linear
|
44 |
-
- num_epochs:
|
45 |
- mixed_precision_training: Native AMP
|
46 |
|
47 |
### Training results
|
@@ -58,6 +58,16 @@ The following hyperparameters were used during training:
|
|
58 |
| 2.009 | 8.0 | 18424 | 1.6401 |
|
59 |
| 1.9923 | 9.0 | 20727 | 1.6319 |
|
60 |
| 1.9802 | 10.0 | 23030 | 1.6264 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
61 |
|
62 |
|
63 |
### Framework versions
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [facebook/detr-resnet-101](https://huggingface.co/facebook/detr-resnet-101) on the cd45rb dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.5962
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
41 |
- seed: 42
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: linear
|
44 |
+
- num_epochs: 20
|
45 |
- mixed_precision_training: Native AMP
|
46 |
|
47 |
### Training results
|
|
|
58 |
| 2.009 | 8.0 | 18424 | 1.6401 |
|
59 |
| 1.9923 | 9.0 | 20727 | 1.6319 |
|
60 |
| 1.9802 | 10.0 | 23030 | 1.6264 |
|
61 |
+
| 2.0027 | 11.0 | 25333 | 1.6539 |
|
62 |
+
| 2.0005 | 12.0 | 27636 | 1.6564 |
|
63 |
+
| 1.9861 | 13.0 | 29939 | 1.6383 |
|
64 |
+
| 1.9778 | 14.0 | 32242 | 1.6246 |
|
65 |
+
| 1.9602 | 15.0 | 34545 | 1.6119 |
|
66 |
+
| 1.9599 | 16.0 | 36848 | 1.6097 |
|
67 |
+
| 1.9464 | 17.0 | 39151 | 1.6115 |
|
68 |
+
| 1.9376 | 18.0 | 41454 | 1.6018 |
|
69 |
+
| 1.9273 | 19.0 | 43757 | 1.5967 |
|
70 |
+
| 1.928 | 20.0 | 46060 | 1.5962 |
|
71 |
|
72 |
|
73 |
### Framework versions
|