surajjoshi
commited on
Commit
•
effe261
1
Parent(s):
c1d0e65
Model save
Browse files- .DS_Store +2 -2
- README.md +43 -10
- training_args.bin +1 -1
.DS_Store
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:827885eac2cd840b1f6eb85bb715d9f94710f281d55af24c8c6248c00d7e2419
|
3 |
+
size 6148
|
README.md
CHANGED
@@ -4,9 +4,36 @@ tags:
|
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
6 |
- imagefolder
|
|
|
|
|
|
|
|
|
|
|
7 |
model-index:
|
8 |
- name: swin-tiny-patch4-window7-224-finetuned-brainTumorData
|
9 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
---
|
11 |
|
12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -16,15 +43,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
-
|
20 |
-
-
|
21 |
-
-
|
22 |
-
-
|
23 |
-
-
|
24 |
-
- eval_runtime: 69.1743
|
25 |
-
- eval_samples_per_second: 19.574
|
26 |
-
- eval_steps_per_second: 0.622
|
27 |
-
- step: 0
|
28 |
|
29 |
## Model description
|
30 |
|
@@ -54,6 +77,16 @@ The following hyperparameters were used during training:
|
|
54 |
- lr_scheduler_warmup_ratio: 0.1
|
55 |
- num_epochs: 4
|
56 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
57 |
### Framework versions
|
58 |
|
59 |
- Transformers 4.23.1
|
|
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
6 |
- imagefolder
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
- f1
|
10 |
+
- recall
|
11 |
+
- precision
|
12 |
model-index:
|
13 |
- name: swin-tiny-patch4-window7-224-finetuned-brainTumorData
|
14 |
+
results:
|
15 |
+
- task:
|
16 |
+
name: Image Classification
|
17 |
+
type: image-classification
|
18 |
+
dataset:
|
19 |
+
name: imagefolder
|
20 |
+
type: imagefolder
|
21 |
+
config: default
|
22 |
+
split: train
|
23 |
+
args: default
|
24 |
+
metrics:
|
25 |
+
- name: Accuracy
|
26 |
+
type: accuracy
|
27 |
+
value: 0.9977843426883308
|
28 |
+
- name: F1
|
29 |
+
type: f1
|
30 |
+
value: 0.9984067976633033
|
31 |
+
- name: Recall
|
32 |
+
type: recall
|
33 |
+
value: 0.9978768577494692
|
34 |
+
- name: Precision
|
35 |
+
type: precision
|
36 |
+
value: 0.9989373007438895
|
37 |
---
|
38 |
|
39 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
43 |
|
44 |
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
|
45 |
It achieves the following results on the evaluation set:
|
46 |
+
- Loss: 0.0101
|
47 |
+
- Accuracy: 0.9978
|
48 |
+
- F1: 0.9984
|
49 |
+
- Recall: 0.9979
|
50 |
+
- Precision: 0.9989
|
|
|
|
|
|
|
|
|
51 |
|
52 |
## Model description
|
53 |
|
|
|
77 |
- lr_scheduler_warmup_ratio: 0.1
|
78 |
- num_epochs: 4
|
79 |
|
80 |
+
### Training results
|
81 |
+
|
82 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Recall | Precision |
|
83 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:---------:|
|
84 |
+
| 0.1884 | 1.0 | 95 | 0.0706 | 0.9705 | 0.9787 | 0.9756 | 0.9818 |
|
85 |
+
| 0.1134 | 2.0 | 190 | 0.0364 | 0.9889 | 0.9920 | 0.9883 | 0.9957 |
|
86 |
+
| 0.1031 | 3.0 | 285 | 0.0116 | 0.9963 | 0.9973 | 0.9947 | 1.0 |
|
87 |
+
| 0.0746 | 4.0 | 380 | 0.0101 | 0.9978 | 0.9984 | 0.9979 | 0.9989 |
|
88 |
+
|
89 |
+
|
90 |
### Framework versions
|
91 |
|
92 |
- Transformers 4.23.1
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3439
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:389e0478e824940000d81b8917ec2e0cbc60acada58430ec0beb900a1665d9c6
|
3 |
size 3439
|