Instructions to use dima806/deepfake_vs_real_image_detection with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dima806/deepfake_vs_real_image_detection with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="dima806/deepfake_vs_real_image_detection") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("dima806/deepfake_vs_real_image_detection") model = AutoModelForImageClassification.from_pretrained("dima806/deepfake_vs_real_image_detection") - Inference
- Notebooks
- Google Colab
- Kaggle
Upload folder using huggingface_hub
Browse files- checkpoint-5653/config.json +32 -0
- checkpoint-5653/model.safetensors +3 -0
- checkpoint-5653/optimizer.pt +3 -0
- checkpoint-5653/preprocessor_config.json +22 -0
- checkpoint-5653/rng_state.pth +3 -0
- checkpoint-5653/scheduler.pt +3 -0
- checkpoint-5653/trainer_state.json +107 -0
- checkpoint-5653/training_args.bin +3 -0
- config.json +2 -2
- model.safetensors +3 -0
- training_args.bin +2 -2
checkpoint-5653/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "dima806/deepfake_vs_real_image_detection",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ViTForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"encoder_stride": 16,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "Real",
|
| 13 |
+
"1": "Fake"
|
| 14 |
+
},
|
| 15 |
+
"image_size": 224,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"Fake": 1,
|
| 20 |
+
"Real": 0
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-12,
|
| 23 |
+
"model_type": "vit",
|
| 24 |
+
"num_attention_heads": 12,
|
| 25 |
+
"num_channels": 3,
|
| 26 |
+
"num_hidden_layers": 12,
|
| 27 |
+
"patch_size": 16,
|
| 28 |
+
"problem_type": "single_label_classification",
|
| 29 |
+
"qkv_bias": true,
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.38.1"
|
| 32 |
+
}
|
checkpoint-5653/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19dab90100d6296f7611e7c9e615a32b91940b6f0662af638e5847a6bc836cb6
|
| 3 |
+
size 343223968
|
checkpoint-5653/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51a461ee7ae77dc6763efb4f4cac2053adb1968ff1b8b4f2f9f7ea7bd723da93
|
| 3 |
+
size 686568453
|
checkpoint-5653/preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_rescale": true,
|
| 4 |
+
"do_resize": true,
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.5,
|
| 7 |
+
0.5,
|
| 8 |
+
0.5
|
| 9 |
+
],
|
| 10 |
+
"image_processor_type": "ViTImageProcessor",
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.5,
|
| 13 |
+
0.5,
|
| 14 |
+
0.5
|
| 15 |
+
],
|
| 16 |
+
"resample": 2,
|
| 17 |
+
"rescale_factor": 0.00392156862745098,
|
| 18 |
+
"size": {
|
| 19 |
+
"height": 224,
|
| 20 |
+
"width": 224
|
| 21 |
+
}
|
| 22 |
+
}
|
checkpoint-5653/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec43cba9ba03b1cd6cdbb5f5c4c8accb557d7a2b67311a80f3f79d6649db19fb
|
| 3 |
+
size 14575
|
checkpoint-5653/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7573586c1c38ac054ac6ef7b5c823ce7f341bee010c52f0c07586fc6faf79f64
|
| 3 |
+
size 627
|
checkpoint-5653/trainer_state.json
ADDED
|
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.021508002653717995,
|
| 3 |
+
"best_model_checkpoint": "deepfake_vs_real_image_detection/checkpoint-5653",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 5653,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.09,
|
| 13 |
+
"grad_norm": 1.0086122751235962,
|
| 14 |
+
"learning_rate": 4.598429412814564e-06,
|
| 15 |
+
"loss": 0.0287,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.18,
|
| 20 |
+
"grad_norm": 0.11366910487413406,
|
| 21 |
+
"learning_rate": 4.152239871497413e-06,
|
| 22 |
+
"loss": 0.0292,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.27,
|
| 27 |
+
"grad_norm": 0.04216881841421127,
|
| 28 |
+
"learning_rate": 3.706050330180261e-06,
|
| 29 |
+
"loss": 0.0273,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.35,
|
| 34 |
+
"grad_norm": 0.0077363960444927216,
|
| 35 |
+
"learning_rate": 3.2598607888631096e-06,
|
| 36 |
+
"loss": 0.0288,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.44,
|
| 41 |
+
"grad_norm": 0.012885607779026031,
|
| 42 |
+
"learning_rate": 2.8136712475459575e-06,
|
| 43 |
+
"loss": 0.0285,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.53,
|
| 48 |
+
"grad_norm": 0.006761148571968079,
|
| 49 |
+
"learning_rate": 2.367481706228806e-06,
|
| 50 |
+
"loss": 0.0246,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.62,
|
| 55 |
+
"grad_norm": 0.020215608179569244,
|
| 56 |
+
"learning_rate": 1.9212921649116544e-06,
|
| 57 |
+
"loss": 0.026,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.71,
|
| 62 |
+
"grad_norm": 0.03672046586871147,
|
| 63 |
+
"learning_rate": 1.4751026235945032e-06,
|
| 64 |
+
"loss": 0.0254,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.8,
|
| 69 |
+
"grad_norm": 1.4788285493850708,
|
| 70 |
+
"learning_rate": 1.0289130822773514e-06,
|
| 71 |
+
"loss": 0.0262,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.88,
|
| 76 |
+
"grad_norm": 0.04541263356804848,
|
| 77 |
+
"learning_rate": 5.827235409601999e-07,
|
| 78 |
+
"loss": 0.028,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.97,
|
| 83 |
+
"grad_norm": 0.007974252104759216,
|
| 84 |
+
"learning_rate": 1.3653399964304838e-07,
|
| 85 |
+
"loss": 0.0253,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.0,
|
| 90 |
+
"eval_accuracy": 0.9934880789833,
|
| 91 |
+
"eval_loss": 0.021508002653717995,
|
| 92 |
+
"eval_runtime": 96.1411,
|
| 93 |
+
"eval_samples_per_second": 99.031,
|
| 94 |
+
"eval_steps_per_second": 12.388,
|
| 95 |
+
"step": 5653
|
| 96 |
+
}
|
| 97 |
+
],
|
| 98 |
+
"logging_steps": 500,
|
| 99 |
+
"max_steps": 5653,
|
| 100 |
+
"num_input_tokens_seen": 0,
|
| 101 |
+
"num_train_epochs": 1,
|
| 102 |
+
"save_steps": 500,
|
| 103 |
+
"total_flos": 1.4016828573477016e+19,
|
| 104 |
+
"train_batch_size": 32,
|
| 105 |
+
"trial_name": null,
|
| 106 |
+
"trial_params": null
|
| 107 |
+
}
|
checkpoint-5653/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7061d4c8be847b0ffff735139df55c183bccfd202b6a97c2dcdf43e93dfa2c3
|
| 3 |
+
size 4411
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"ViTForImageClassification"
|
| 5 |
],
|
|
@@ -28,5 +28,5 @@
|
|
| 28 |
"problem_type": "single_label_classification",
|
| 29 |
"qkv_bias": true,
|
| 30 |
"torch_dtype": "float32",
|
| 31 |
-
"transformers_version": "4.
|
| 32 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "dima806/deepfake_vs_real_image_detection",
|
| 3 |
"architectures": [
|
| 4 |
"ViTForImageClassification"
|
| 5 |
],
|
|
|
|
| 28 |
"problem_type": "single_label_classification",
|
| 29 |
"qkv_bias": true,
|
| 30 |
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.38.1"
|
| 32 |
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19dab90100d6296f7611e7c9e615a32b91940b6f0662af638e5847a6bc836cb6
|
| 3 |
+
size 343223968
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7061d4c8be847b0ffff735139df55c183bccfd202b6a97c2dcdf43e93dfa2c3
|
| 3 |
+
size 4411
|