update model card README.md
Browse files
README.md
CHANGED
@@ -1,10 +1,9 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
tags:
|
4 |
-
- image-classification
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
-
-
|
8 |
metrics:
|
9 |
- accuracy
|
10 |
model-index:
|
@@ -14,7 +13,7 @@ model-index:
|
|
14 |
name: Image Classification
|
15 |
type: image-classification
|
16 |
dataset:
|
17 |
-
name:
|
18 |
type: imagefolder
|
19 |
config: alkzar90--croupier-mtg-dataset
|
20 |
split: train
|
@@ -22,16 +21,7 @@ model-index:
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
-
value: 0.
|
26 |
-
widget:
|
27 |
-
- src: https://huggingface.co/alkzar90/croupier-creature-classifier/resolve/main/examples/crusader_peco_peco.png
|
28 |
-
example_title: Crusader-Rangarok-Online
|
29 |
-
- src: https://huggingface.co/alkzar90/croupier-creature-classifier/resolve/main/examples/goblin_wow.png
|
30 |
-
example_title: Goblin-WoW
|
31 |
-
- src: https://huggingface.co/alkzar90/croupier-creature-classifier/resolve/main/examples/dobby_harry_potter.jpg
|
32 |
-
example_title: Dobby-Harry-Potter
|
33 |
-
- src: https://huggingface.co/alkzar90/croupier-creature-classifier/resolve/main/examples/resident_evil_nemesis.jpeg
|
34 |
-
example_title: Nemesis-Resident-Evil
|
35 |
---
|
36 |
|
37 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -39,10 +29,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
39 |
|
40 |
# croupier-creature-classifier
|
41 |
|
42 |
-
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the
|
43 |
It achieves the following results on the evaluation set:
|
44 |
-
- Loss: 0.
|
45 |
-
- Accuracy: 0.
|
46 |
|
47 |
## Model description
|
48 |
|
@@ -67,31 +57,23 @@ The following hyperparameters were used during training:
|
|
67 |
- seed: 42
|
68 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
69 |
- lr_scheduler_type: linear
|
70 |
-
- num_epochs:
|
71 |
- mixed_precision_training: Native AMP
|
72 |
|
73 |
### Training results
|
74 |
|
75 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
76 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
77 |
-
| 0.
|
78 |
-
| 0.
|
79 |
-
| 0.
|
80 |
-
| 0.
|
81 |
-
| 0.
|
82 |
-
| 0.1164 | 6.59 | 600 | 0.7493 | 0.8176 |
|
83 |
-
| 0.0518 | 7.69 | 700 | 0.8781 | 0.7765 |
|
84 |
-
| 0.0458 | 8.79 | 800 | 0.8851 | 0.7824 |
|
85 |
-
| 0.0521 | 9.89 | 900 | 0.9448 | 0.7882 |
|
86 |
-
| 0.0576 | 10.99 | 1000 | 0.8884 | 0.7824 |
|
87 |
-
| 0.0442 | 12.09 | 1100 | 0.8965 | 0.7882 |
|
88 |
-
| 0.0254 | 13.19 | 1200 | 0.9140 | 0.7882 |
|
89 |
-
| 0.0426 | 14.29 | 1300 | 0.9274 | 0.7882 |
|
90 |
|
91 |
|
92 |
### Framework versions
|
93 |
|
94 |
-
- Transformers 4.21.
|
95 |
- Pytorch 1.12.0+cu113
|
96 |
- Datasets 2.4.0
|
97 |
- Tokenizers 0.12.1
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
tags:
|
|
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
6 |
+
- imagefolder
|
7 |
metrics:
|
8 |
- accuracy
|
9 |
model-index:
|
|
|
13 |
name: Image Classification
|
14 |
type: image-classification
|
15 |
dataset:
|
16 |
+
name: imagefolder
|
17 |
type: imagefolder
|
18 |
config: alkzar90--croupier-mtg-dataset
|
19 |
split: train
|
|
|
21 |
metrics:
|
22 |
- name: Accuracy
|
23 |
type: accuracy
|
24 |
+
value: 0.7058823529411765
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
---
|
26 |
|
27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
29 |
|
30 |
# croupier-creature-classifier
|
31 |
|
32 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 0.7184
|
35 |
+
- Accuracy: 0.7059
|
36 |
|
37 |
## Model description
|
38 |
|
|
|
57 |
- seed: 42
|
58 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
- lr_scheduler_type: linear
|
60 |
+
- num_epochs: 6
|
61 |
- mixed_precision_training: Native AMP
|
62 |
|
63 |
### Training results
|
64 |
|
65 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
66 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
67 |
+
| 0.8932 | 1.1 | 100 | 0.9914 | 0.6059 |
|
68 |
+
| 0.6608 | 2.2 | 200 | 0.8645 | 0.6588 |
|
69 |
+
| 0.6084 | 3.3 | 300 | 0.7326 | 0.7294 |
|
70 |
+
| 0.5261 | 4.4 | 400 | 0.7684 | 0.6941 |
|
71 |
+
| 0.2511 | 5.49 | 500 | 0.7184 | 0.7059 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
72 |
|
73 |
|
74 |
### Framework versions
|
75 |
|
76 |
+
- Transformers 4.21.1
|
77 |
- Pytorch 1.12.0+cu113
|
78 |
- Datasets 2.4.0
|
79 |
- Tokenizers 0.12.1
|