songthienll/ai_image_generator_detect
Browse files- README.md +80 -0
- config.json +54 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: other
|
| 4 |
+
base_model: apple/mobilevit-small
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
datasets:
|
| 8 |
+
- imagefolder
|
| 9 |
+
metrics:
|
| 10 |
+
- accuracy
|
| 11 |
+
model-index:
|
| 12 |
+
- name: mobilevit_ai_real_classifier
|
| 13 |
+
results:
|
| 14 |
+
- task:
|
| 15 |
+
name: Image Classification
|
| 16 |
+
type: image-classification
|
| 17 |
+
dataset:
|
| 18 |
+
name: imagefolder
|
| 19 |
+
type: imagefolder
|
| 20 |
+
config: default
|
| 21 |
+
split: train
|
| 22 |
+
args: default
|
| 23 |
+
metrics:
|
| 24 |
+
- name: Accuracy
|
| 25 |
+
type: accuracy
|
| 26 |
+
value: 0.93875
|
| 27 |
+
---
|
| 28 |
+
|
| 29 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 30 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 31 |
+
|
| 32 |
+
# mobilevit_ai_real_classifier
|
| 33 |
+
|
| 34 |
+
This model is a fine-tuned version of [apple/mobilevit-small](https://huggingface.co/apple/mobilevit-small) on the imagefolder dataset.
|
| 35 |
+
It achieves the following results on the evaluation set:
|
| 36 |
+
- Loss: 0.1560
|
| 37 |
+
- Accuracy: 0.9387
|
| 38 |
+
|
| 39 |
+
## Model description
|
| 40 |
+
|
| 41 |
+
More information needed
|
| 42 |
+
|
| 43 |
+
## Intended uses & limitations
|
| 44 |
+
|
| 45 |
+
More information needed
|
| 46 |
+
|
| 47 |
+
## Training and evaluation data
|
| 48 |
+
|
| 49 |
+
More information needed
|
| 50 |
+
|
| 51 |
+
## Training procedure
|
| 52 |
+
|
| 53 |
+
### Training hyperparameters
|
| 54 |
+
|
| 55 |
+
The following hyperparameters were used during training:
|
| 56 |
+
- learning_rate: 0.0003
|
| 57 |
+
- train_batch_size: 64
|
| 58 |
+
- eval_batch_size: 64
|
| 59 |
+
- seed: 42
|
| 60 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 61 |
+
- lr_scheduler_type: linear
|
| 62 |
+
- num_epochs: 5
|
| 63 |
+
|
| 64 |
+
### Training results
|
| 65 |
+
|
| 66 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 67 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 68 |
+
| 0.2392 | 1.0 | 219 | 0.2392 | 0.9115 |
|
| 69 |
+
| 0.1804 | 2.0 | 438 | 0.1905 | 0.9295 |
|
| 70 |
+
| 0.1611 | 3.0 | 657 | 0.1772 | 0.935 |
|
| 71 |
+
| 0.1225 | 4.0 | 876 | 0.1784 | 0.938 |
|
| 72 |
+
| 0.0955 | 5.0 | 1095 | 0.2000 | 0.9325 |
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
### Framework versions
|
| 76 |
+
|
| 77 |
+
- Transformers 4.51.3
|
| 78 |
+
- Pytorch 2.6.0+cu124
|
| 79 |
+
- Datasets 3.6.0
|
| 80 |
+
- Tokenizers 0.21.1
|
config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"MobileViTForImageClassification"
|
| 4 |
+
],
|
| 5 |
+
"aspp_dropout_prob": 0.1,
|
| 6 |
+
"aspp_out_channels": 256,
|
| 7 |
+
"atrous_rates": [
|
| 8 |
+
6,
|
| 9 |
+
12,
|
| 10 |
+
18
|
| 11 |
+
],
|
| 12 |
+
"attention_probs_dropout_prob": 0.0,
|
| 13 |
+
"classifier_dropout_prob": 0.1,
|
| 14 |
+
"conv_kernel_size": 3,
|
| 15 |
+
"expand_ratio": 4.0,
|
| 16 |
+
"hidden_act": "silu",
|
| 17 |
+
"hidden_dropout_prob": 0.1,
|
| 18 |
+
"hidden_sizes": [
|
| 19 |
+
144,
|
| 20 |
+
192,
|
| 21 |
+
240
|
| 22 |
+
],
|
| 23 |
+
"id2label": {
|
| 24 |
+
"0": "fake",
|
| 25 |
+
"1": "real"
|
| 26 |
+
},
|
| 27 |
+
"image_size": 256,
|
| 28 |
+
"initializer_range": 0.02,
|
| 29 |
+
"label2id": {
|
| 30 |
+
"fake": 0,
|
| 31 |
+
"real": 1
|
| 32 |
+
},
|
| 33 |
+
"layer_norm_eps": 1e-05,
|
| 34 |
+
"mlp_ratio": 2.0,
|
| 35 |
+
"model_type": "mobilevit",
|
| 36 |
+
"neck_hidden_sizes": [
|
| 37 |
+
16,
|
| 38 |
+
32,
|
| 39 |
+
64,
|
| 40 |
+
96,
|
| 41 |
+
128,
|
| 42 |
+
160,
|
| 43 |
+
640
|
| 44 |
+
],
|
| 45 |
+
"num_attention_heads": 4,
|
| 46 |
+
"num_channels": 3,
|
| 47 |
+
"output_stride": 32,
|
| 48 |
+
"patch_size": 2,
|
| 49 |
+
"problem_type": "single_label_classification",
|
| 50 |
+
"qkv_bias": true,
|
| 51 |
+
"semantic_loss_ignore_index": 255,
|
| 52 |
+
"torch_dtype": "float32",
|
| 53 |
+
"transformers_version": "4.51.3"
|
| 54 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d397284d44f0f8e38d09f81dcb5ed7eac05f6298ef0d7d518f304d60c699135a
|
| 3 |
+
size 19851560
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:22b9609afa5564f86bdf12a345dfccb536bf900d30bdcd4e7119cf7f5b654997
|
| 3 |
+
size 5304
|