tontokoton
commited on
Commit
•
a1e047b
1
Parent(s):
7b95302
End of training
Browse files- README.md +2 -28
- training_args.bin +1 -1
README.md
CHANGED
@@ -16,32 +16,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
# segformer-b0-finetuned-v0
|
17 |
|
18 |
This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the tontokoton/artery-ultrasound-siit dataset.
|
19 |
-
It achieves the following results on the evaluation set:
|
20 |
-
- eval_loss: 1.4971
|
21 |
-
- eval_mean_iou: 0.1068
|
22 |
-
- eval_mean_accuracy: 0.2327
|
23 |
-
- eval_overall_accuracy: 0.8437
|
24 |
-
- eval_accuracy_artery: nan
|
25 |
-
- eval_accuracy_vein: 0.0062
|
26 |
-
- eval_accuracy_nerve: 0.0022
|
27 |
-
- eval_accuracy_muscle1: 0.0
|
28 |
-
- eval_accuracy_muscle2: 0.9224
|
29 |
-
- eval_accuracy_muscle3: nan
|
30 |
-
- eval_accuracy_muscle4: nan
|
31 |
-
- eval_accuracy_unknown: nan
|
32 |
-
- eval_iou_artery: 0.0
|
33 |
-
- eval_iou_vein: 0.0061
|
34 |
-
- eval_iou_nerve: 0.0021
|
35 |
-
- eval_iou_muscle1: 0.0
|
36 |
-
- eval_iou_muscle2: 0.8458
|
37 |
-
- eval_iou_muscle3: 0.0
|
38 |
-
- eval_iou_muscle4: 0.0
|
39 |
-
- eval_iou_unknown: 0.0
|
40 |
-
- eval_runtime: 11.3293
|
41 |
-
- eval_samples_per_second: 1.765
|
42 |
-
- eval_steps_per_second: 0.883
|
43 |
-
- epoch: 2.25
|
44 |
-
- step: 90
|
45 |
|
46 |
## Model description
|
47 |
|
@@ -61,8 +35,8 @@ More information needed
|
|
61 |
|
62 |
The following hyperparameters were used during training:
|
63 |
- learning_rate: 1e-05
|
64 |
-
- train_batch_size:
|
65 |
-
- eval_batch_size:
|
66 |
- seed: 42
|
67 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
68 |
- lr_scheduler_type: linear
|
|
|
16 |
# segformer-b0-finetuned-v0
|
17 |
|
18 |
This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the tontokoton/artery-ultrasound-siit dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
- learning_rate: 1e-05
|
38 |
+
- train_batch_size: 24
|
39 |
+
- eval_batch_size: 24
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4091
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3766a4330ba2d7df21ccd03f8c51fa61b91624920249c6068c1c5ee30ed13ab9
|
3 |
size 4091
|