Image Classification
Transformers
Safetensors
PyTorch
English
Chinese
beit
ai-detection
ai-image-detection
deepfake-detection
fake-image-detection
ai-art-detection
stable-diffusion-detection
midjourney-detection
dall-e-detection
flux-detection
image-forensics
digital-art-verification
vit
computer-vision
dual-head
Eval Results (legacy)
Upload folder using huggingface_hub
Browse files- binary_head.pt +3 -0
- config.json +95 -0
- model.safetensors +3 -0
- preprocessor_config.json +28 -0
- source_meta.json +26 -0
binary_head.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b796598326f992086278cf910ecd4d9f67480f028a4eb1edadb8596067a2bb63
|
| 3 |
+
size 10181
|
config.json
ADDED
|
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_fpn": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BeitForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"auxiliary_channels": 256,
|
| 8 |
+
"auxiliary_concat_input": false,
|
| 9 |
+
"auxiliary_loss_weight": 0.4,
|
| 10 |
+
"auxiliary_num_convs": 1,
|
| 11 |
+
"drop_path_rate": 0.1,
|
| 12 |
+
"dtype": "float32",
|
| 13 |
+
"hidden_act": "gelu",
|
| 14 |
+
"hidden_dropout_prob": 0.0,
|
| 15 |
+
"hidden_size": 1024,
|
| 16 |
+
"id2label": {
|
| 17 |
+
"0": "LABEL_0",
|
| 18 |
+
"1": "LABEL_1",
|
| 19 |
+
"2": "LABEL_2",
|
| 20 |
+
"3": "LABEL_3",
|
| 21 |
+
"4": "LABEL_4",
|
| 22 |
+
"5": "LABEL_5",
|
| 23 |
+
"6": "LABEL_6",
|
| 24 |
+
"7": "LABEL_7"
|
| 25 |
+
},
|
| 26 |
+
"image_size": 224,
|
| 27 |
+
"initializer_range": 0.02,
|
| 28 |
+
"intermediate_size": 4096,
|
| 29 |
+
"label2id": {
|
| 30 |
+
"LABEL_0": 0,
|
| 31 |
+
"LABEL_1": 1,
|
| 32 |
+
"LABEL_2": 2,
|
| 33 |
+
"LABEL_3": 3,
|
| 34 |
+
"LABEL_4": 4,
|
| 35 |
+
"LABEL_5": 5,
|
| 36 |
+
"LABEL_6": 6,
|
| 37 |
+
"LABEL_7": 7
|
| 38 |
+
},
|
| 39 |
+
"layer_norm_eps": 1e-12,
|
| 40 |
+
"layer_scale_init_value": 0.1,
|
| 41 |
+
"model_type": "beit",
|
| 42 |
+
"num_attention_heads": 16,
|
| 43 |
+
"num_channels": 3,
|
| 44 |
+
"num_hidden_layers": 24,
|
| 45 |
+
"out_features": [
|
| 46 |
+
"stage24"
|
| 47 |
+
],
|
| 48 |
+
"out_indices": [
|
| 49 |
+
24
|
| 50 |
+
],
|
| 51 |
+
"patch_size": 16,
|
| 52 |
+
"pool_scales": [
|
| 53 |
+
1,
|
| 54 |
+
2,
|
| 55 |
+
3,
|
| 56 |
+
6
|
| 57 |
+
],
|
| 58 |
+
"reshape_hidden_states": true,
|
| 59 |
+
"semantic_loss_ignore_index": 255,
|
| 60 |
+
"stage_names": [
|
| 61 |
+
"stem",
|
| 62 |
+
"stage1",
|
| 63 |
+
"stage2",
|
| 64 |
+
"stage3",
|
| 65 |
+
"stage4",
|
| 66 |
+
"stage5",
|
| 67 |
+
"stage6",
|
| 68 |
+
"stage7",
|
| 69 |
+
"stage8",
|
| 70 |
+
"stage9",
|
| 71 |
+
"stage10",
|
| 72 |
+
"stage11",
|
| 73 |
+
"stage12",
|
| 74 |
+
"stage13",
|
| 75 |
+
"stage14",
|
| 76 |
+
"stage15",
|
| 77 |
+
"stage16",
|
| 78 |
+
"stage17",
|
| 79 |
+
"stage18",
|
| 80 |
+
"stage19",
|
| 81 |
+
"stage20",
|
| 82 |
+
"stage21",
|
| 83 |
+
"stage22",
|
| 84 |
+
"stage23",
|
| 85 |
+
"stage24"
|
| 86 |
+
],
|
| 87 |
+
"transformers_version": "4.57.6",
|
| 88 |
+
"use_absolute_position_embeddings": false,
|
| 89 |
+
"use_auxiliary_head": true,
|
| 90 |
+
"use_mask_token": false,
|
| 91 |
+
"use_mean_pooling": true,
|
| 92 |
+
"use_relative_position_bias": true,
|
| 93 |
+
"use_shared_relative_position_bias": false,
|
| 94 |
+
"vocab_size": 8192
|
| 95 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65d26a809de91813e11d88381aca3cf24be6c704bf605f827e7301a927aa98e5
|
| 3 |
+
size 1213707856
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": {
|
| 3 |
+
"height": 224,
|
| 4 |
+
"width": 224
|
| 5 |
+
},
|
| 6 |
+
"do_center_crop": false,
|
| 7 |
+
"do_normalize": true,
|
| 8 |
+
"do_reduce_labels": false,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"image_mean": [
|
| 12 |
+
0.5,
|
| 13 |
+
0.5,
|
| 14 |
+
0.5
|
| 15 |
+
],
|
| 16 |
+
"image_processor_type": "BeitImageProcessor",
|
| 17 |
+
"image_std": [
|
| 18 |
+
0.5,
|
| 19 |
+
0.5,
|
| 20 |
+
0.5
|
| 21 |
+
],
|
| 22 |
+
"resample": 2,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"height": 224,
|
| 26 |
+
"width": 224
|
| 27 |
+
}
|
| 28 |
+
}
|
source_meta.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"source_names": [
|
| 3 |
+
"COCO",
|
| 4 |
+
"DALLE3",
|
| 5 |
+
"FLUX",
|
| 6 |
+
"Midjourney",
|
| 7 |
+
"Real",
|
| 8 |
+
"SD21",
|
| 9 |
+
"SD3",
|
| 10 |
+
"SDXL"
|
| 11 |
+
],
|
| 12 |
+
"source_is_real": {
|
| 13 |
+
"SDXL": false,
|
| 14 |
+
"Midjourney": false,
|
| 15 |
+
"FLUX": false,
|
| 16 |
+
"SD3": false,
|
| 17 |
+
"COCO": true,
|
| 18 |
+
"DALLE3": false,
|
| 19 |
+
"Real": false,
|
| 20 |
+
"SD21": false
|
| 21 |
+
},
|
| 22 |
+
"num_labels": 8,
|
| 23 |
+
"multiclass": true,
|
| 24 |
+
"dual_head": true,
|
| 25 |
+
"hidden_size": 1024
|
| 26 |
+
}
|