Model save
Browse files- README.md +93 -0
- pytorch_model.bin +1 -1
README.md
ADDED
|
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: google/vit-base-patch16-224
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- image_folder
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: AnimeCharacterClassifierMark1
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Image Classification
|
| 15 |
+
type: image-classification
|
| 16 |
+
dataset:
|
| 17 |
+
name: image_folder
|
| 18 |
+
type: image_folder
|
| 19 |
+
config: default
|
| 20 |
+
split: train
|
| 21 |
+
args: default
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Accuracy
|
| 24 |
+
type: accuracy
|
| 25 |
+
value: 0.864476386036961
|
| 26 |
+
---
|
| 27 |
+
|
| 28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 29 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 30 |
+
|
| 31 |
+
# AnimeCharacterClassifierMark1
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the image_folder dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.6515
|
| 36 |
+
- Accuracy: 0.8645
|
| 37 |
+
|
| 38 |
+
## Model description
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Intended uses & limitations
|
| 43 |
+
|
| 44 |
+
More information needed
|
| 45 |
+
|
| 46 |
+
## Training and evaluation data
|
| 47 |
+
|
| 48 |
+
More information needed
|
| 49 |
+
|
| 50 |
+
## Training procedure
|
| 51 |
+
|
| 52 |
+
### Training hyperparameters
|
| 53 |
+
|
| 54 |
+
The following hyperparameters were used during training:
|
| 55 |
+
- learning_rate: 5e-05
|
| 56 |
+
- train_batch_size: 128
|
| 57 |
+
- eval_batch_size: 128
|
| 58 |
+
- seed: 42
|
| 59 |
+
- gradient_accumulation_steps: 4
|
| 60 |
+
- total_train_batch_size: 512
|
| 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: 42
|
| 65 |
+
|
| 66 |
+
### Training results
|
| 67 |
+
|
| 68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
+
| 5.0145 | 0.99 | 17 | 4.9303 | 0.0092 |
|
| 71 |
+
| 4.8416 | 1.97 | 34 | 4.7487 | 0.0287 |
|
| 72 |
+
| 4.4383 | 2.96 | 51 | 4.3597 | 0.1170 |
|
| 73 |
+
| 4.0762 | 4.0 | 69 | 3.6419 | 0.3224 |
|
| 74 |
+
| 3.108 | 4.99 | 86 | 2.8574 | 0.5246 |
|
| 75 |
+
| 2.1571 | 5.97 | 103 | 2.2129 | 0.6653 |
|
| 76 |
+
| 1.4685 | 6.96 | 120 | 1.7290 | 0.7495 |
|
| 77 |
+
| 1.1649 | 8.0 | 138 | 1.3862 | 0.7977 |
|
| 78 |
+
| 0.7905 | 8.99 | 155 | 1.1589 | 0.8214 |
|
| 79 |
+
| 0.5549 | 9.97 | 172 | 1.0263 | 0.8296 |
|
| 80 |
+
| 0.4577 | 10.96 | 189 | 0.8994 | 0.8368 |
|
| 81 |
+
| 0.2964 | 12.0 | 207 | 0.8086 | 0.8552 |
|
| 82 |
+
| 0.194 | 12.99 | 224 | 0.7446 | 0.8583 |
|
| 83 |
+
| 0.1358 | 13.97 | 241 | 0.7064 | 0.8573 |
|
| 84 |
+
| 0.1116 | 14.96 | 258 | 0.6720 | 0.8655 |
|
| 85 |
+
| 0.0811 | 16.0 | 276 | 0.6515 | 0.8645 |
|
| 86 |
+
|
| 87 |
+
|
| 88 |
+
### Framework versions
|
| 89 |
+
|
| 90 |
+
- Transformers 4.33.0
|
| 91 |
+
- Pytorch 2.0.0
|
| 92 |
+
- Datasets 2.1.0
|
| 93 |
+
- Tokenizers 0.13.3
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343662445
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f6be57a3a6d275388da2ec761d09c9bf2aa1037042c8f4ac544ba4be48db72d
|
| 3 |
size 343662445
|