Model save
Browse files
README.md
CHANGED
@@ -2,28 +2,12 @@
|
|
2 |
license: apache-2.0
|
3 |
base_model: google/vit-base-patch16-224-in21k
|
4 |
tags:
|
5 |
-
- image-classification
|
6 |
- generated_from_trainer
|
7 |
-
datasets:
|
8 |
-
- imagefolder
|
9 |
metrics:
|
10 |
- accuracy
|
11 |
model-index:
|
12 |
- name: Action_all_10_class
|
13 |
-
results:
|
14 |
-
- task:
|
15 |
-
name: Image Classification
|
16 |
-
type: image-classification
|
17 |
-
dataset:
|
18 |
-
name: Action_small_dataset
|
19 |
-
type: imagefolder
|
20 |
-
config: default
|
21 |
-
split: train
|
22 |
-
args: default
|
23 |
-
metrics:
|
24 |
-
- name: Accuracy
|
25 |
-
type: accuracy
|
26 |
-
value: 0.8646723646723646
|
27 |
---
|
28 |
|
29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -31,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
31 |
|
32 |
# Action_all_10_class
|
33 |
|
34 |
-
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on
|
35 |
It achieves the following results on the evaluation set:
|
36 |
-
- Loss: 0.
|
37 |
-
- Accuracy: 0.
|
38 |
|
39 |
## Model description
|
40 |
|
@@ -59,50 +43,25 @@ The following hyperparameters were used during training:
|
|
59 |
- seed: 42
|
60 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
61 |
- lr_scheduler_type: linear
|
62 |
-
- num_epochs:
|
63 |
- mixed_precision_training: Native AMP
|
64 |
|
65 |
### Training results
|
66 |
|
67 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
68 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
69 |
-
| 1.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.
|
79 |
-
| 0.
|
80 |
-
| 0.
|
81 |
-
| 0.4021 | 5.22 | 1300 | 0.5220 | 0.8447 |
|
82 |
-
| 0.6442 | 5.62 | 1400 | 0.7222 | 0.7849 |
|
83 |
-
| 0.4539 | 6.02 | 1500 | 0.5616 | 0.8348 |
|
84 |
-
| 0.4256 | 6.43 | 1600 | 0.6622 | 0.8020 |
|
85 |
-
| 0.2839 | 6.83 | 1700 | 0.6048 | 0.8262 |
|
86 |
-
| 0.4236 | 7.23 | 1800 | 0.5745 | 0.8262 |
|
87 |
-
| 0.3371 | 7.63 | 1900 | 0.5558 | 0.8447 |
|
88 |
-
| 0.2564 | 8.03 | 2000 | 0.5993 | 0.8376 |
|
89 |
-
| 0.2802 | 8.43 | 2100 | 0.5202 | 0.8590 |
|
90 |
-
| 0.2938 | 8.84 | 2200 | 0.6191 | 0.8177 |
|
91 |
-
| 0.2777 | 9.24 | 2300 | 0.5119 | 0.8504 |
|
92 |
-
| 0.1851 | 9.64 | 2400 | 0.5541 | 0.8547 |
|
93 |
-
| 0.2274 | 10.04 | 2500 | 0.5599 | 0.8433 |
|
94 |
-
| 0.3051 | 10.44 | 2600 | 0.5281 | 0.8504 |
|
95 |
-
| 0.2368 | 10.84 | 2700 | 0.5056 | 0.8647 |
|
96 |
-
| 0.2029 | 11.24 | 2800 | 0.5582 | 0.8390 |
|
97 |
-
| 0.1971 | 11.65 | 2900 | 0.5440 | 0.8433 |
|
98 |
-
| 0.2014 | 12.05 | 3000 | 0.5088 | 0.8618 |
|
99 |
-
| 0.1458 | 12.45 | 3100 | 0.5539 | 0.8618 |
|
100 |
-
| 0.139 | 12.85 | 3200 | 0.5866 | 0.8433 |
|
101 |
-
| 0.2202 | 13.25 | 3300 | 0.5248 | 0.8590 |
|
102 |
-
| 0.1421 | 13.65 | 3400 | 0.5548 | 0.8476 |
|
103 |
-
| 0.211 | 14.06 | 3500 | 0.5502 | 0.8490 |
|
104 |
-
| 0.2106 | 14.46 | 3600 | 0.5413 | 0.8504 |
|
105 |
-
| 0.1716 | 14.86 | 3700 | 0.5398 | 0.8462 |
|
106 |
|
107 |
|
108 |
### Framework versions
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: google/vit-base-patch16-224-in21k
|
4 |
tags:
|
|
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
metrics:
|
7 |
- accuracy
|
8 |
model-index:
|
9 |
- name: Action_all_10_class
|
10 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
15 |
|
16 |
# Action_all_10_class
|
17 |
|
18 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.4417
|
21 |
+
- Accuracy: 0.8604
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 5
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
53 |
+
| 1.0772 | 0.4 | 100 | 1.0525 | 0.6738 |
|
54 |
+
| 0.9054 | 0.8 | 200 | 0.7350 | 0.8006 |
|
55 |
+
| 0.9093 | 1.2 | 300 | 0.6519 | 0.8162 |
|
56 |
+
| 0.6264 | 1.61 | 400 | 0.6052 | 0.8105 |
|
57 |
+
| 0.9279 | 2.01 | 500 | 0.6442 | 0.7934 |
|
58 |
+
| 0.5023 | 2.41 | 600 | 0.5365 | 0.8262 |
|
59 |
+
| 0.4644 | 2.81 | 700 | 0.5505 | 0.8305 |
|
60 |
+
| 0.4217 | 3.21 | 800 | 0.5024 | 0.8433 |
|
61 |
+
| 0.4447 | 3.61 | 900 | 0.4700 | 0.8533 |
|
62 |
+
| 0.4073 | 4.02 | 1000 | 0.4605 | 0.8632 |
|
63 |
+
| 0.2679 | 4.42 | 1100 | 0.4259 | 0.8661 |
|
64 |
+
| 0.262 | 4.82 | 1200 | 0.4417 | 0.8604 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
65 |
|
66 |
|
67 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 343248584
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34e1cfa7797145f1c25d3c840bac272746df8ef711d3524f49fce68e738f00b6
|
3 |
size 343248584
|
runs/Nov19_09-32-04_09d27efa0afa/events.out.tfevents.1700386331.09d27efa0afa.31695.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17f5889510ecc5b69ef86f01dc954f2469224d2017442a19d0a179e75d89d697
|
3 |
+
size 28930
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4536
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:434dd799703ae323e5941aeab3788e86a13846a561573b1eff1abf901d280417
|
3 |
size 4536
|