Commit
•
6369b8c
1
Parent(s):
d7b3060
End of training
Browse files
README.md
CHANGED
@@ -1,12 +1,13 @@
|
|
1 |
---
|
2 |
-
license: apache-2.0
|
3 |
-
base_model: microsoft/swinv2-tiny-patch4-window8-256
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- imagefolder
|
8 |
metrics:
|
9 |
- accuracy
|
|
|
|
|
|
|
10 |
model-index:
|
11 |
- name: msi-swinv2-tiny
|
12 |
results:
|
@@ -22,7 +23,16 @@ model-index:
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
-
value: 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -30,10 +40,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
30 |
|
31 |
# msi-swinv2-tiny
|
32 |
|
33 |
-
This model
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss:
|
36 |
-
- Accuracy: 0.
|
|
|
|
|
|
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -61,22 +74,17 @@ The following hyperparameters were used during training:
|
|
61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
- lr_scheduler_type: linear
|
63 |
- lr_scheduler_warmup_ratio: 0.1
|
64 |
-
- num_epochs:
|
65 |
|
66 |
### Training results
|
67 |
|
68 |
-
| Training Loss | Epoch | Step
|
69 |
-
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.1716 | 6.0 | 12094 | 1.4758 | 0.6136 |
|
76 |
-
| 0.1742 | 7.0 | 14110 | 1.4332 | 0.6274 |
|
77 |
-
| 0.1653 | 8.0 | 16126 | 1.4940 | 0.6247 |
|
78 |
-
| 0.1429 | 9.0 | 18141 | 1.6058 | 0.6236 |
|
79 |
-
| 0.1546 | 10.0 | 20150 | 1.5764 | 0.6274 |
|
80 |
|
81 |
|
82 |
### Framework versions
|
|
|
1 |
---
|
|
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
datasets:
|
5 |
- imagefolder
|
6 |
metrics:
|
7 |
- accuracy
|
8 |
+
- f1
|
9 |
+
- precision
|
10 |
+
- recall
|
11 |
model-index:
|
12 |
- name: msi-swinv2-tiny
|
13 |
results:
|
|
|
23 |
metrics:
|
24 |
- name: Accuracy
|
25 |
type: accuracy
|
26 |
+
value: 0.9253901789113057
|
27 |
+
- name: F1
|
28 |
+
type: f1
|
29 |
+
value: 0.9052377115229654
|
30 |
+
- name: Precision
|
31 |
+
type: precision
|
32 |
+
value: 0.9233171693926194
|
33 |
+
- name: Recall
|
34 |
+
type: recall
|
35 |
+
value: 0.8878526831581444
|
36 |
---
|
37 |
|
38 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
40 |
|
41 |
# msi-swinv2-tiny
|
42 |
|
43 |
+
This model was trained from scratch on the imagefolder dataset.
|
44 |
It achieves the following results on the evaluation set:
|
45 |
+
- Loss: 0.1768
|
46 |
+
- Accuracy: 0.9254
|
47 |
+
- F1: 0.9052
|
48 |
+
- Precision: 0.9233
|
49 |
+
- Recall: 0.8879
|
50 |
|
51 |
## Model description
|
52 |
|
|
|
74 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
75 |
- lr_scheduler_type: linear
|
76 |
- lr_scheduler_warmup_ratio: 0.1
|
77 |
+
- num_epochs: 5
|
78 |
|
79 |
### Training results
|
80 |
|
81 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
82 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
83 |
+
| 0.3786 | 1.0 | 1970 | 0.3166 | 0.8590 | 0.8184 | 0.8469 | 0.7917 |
|
84 |
+
| 0.2976 | 2.0 | 3941 | 0.2426 | 0.8952 | 0.8621 | 0.9138 | 0.8159 |
|
85 |
+
| 0.2525 | 3.0 | 5911 | 0.2015 | 0.9144 | 0.8908 | 0.9132 | 0.8694 |
|
86 |
+
| 0.2319 | 4.0 | 7882 | 0.1859 | 0.9216 | 0.9026 | 0.8996 | 0.9056 |
|
87 |
+
| 0.206 | 5.0 | 9850 | 0.1768 | 0.9254 | 0.9052 | 0.9233 | 0.8879 |
|
|
|
|
|
|
|
|
|
|
|
88 |
|
89 |
|
90 |
### Framework versions
|