add config

README.md

@@ -0,0 +1,50 @@
+---
+tags:
+- autotrain
+- vision
+- image-classification
+widget:
+- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
+  example_title: Tiger
+- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg
+  example_title: Teapot
+- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
+  example_title: Palace
+co2_eq_emissions:
+  emissions: 7.940487247386902
+license: cc-by-4.0
+---
+
+*__NOTE__: Unless you are trying to detect imagery generated using older models such as VQGAN+CLIP, please use the [updated version](https://huggingface.co/Organika/sdxl-detector) of this detector instead.*
+
+This model is a proof-of-concept demonstration of using a ViT model to predict whether an artistic image was generated using AI.
+
+It was created in October 2022, and as such, the training data did not include any samples generated by Midjourney 5, SDXL, or DALLE-3. It still may be able to correctly identify samples from these more recent models due to being trained on outputs of their predecessors.
+
+Furthermore the intended scope of this tool is artistic images; that is to say, it is not a deepfake photo detector, and general computer imagery (webcams, screenshots, etc.) may throw it off.
+
+In general, this tool can only serve as one of many potential indicators that an image was AI-generated. Images scoring as very probably artificial (e.g. 90% or higher) could be referred to a human expert for further investigation, if needed.
+
+For more information please see the blog post describing this project at:
+https://medium.com/@matthewmaybe/can-an-ai-learn-to-identify-ai-art-545d9d6af226
+
+# Model Trained Using AutoTrain
+
+- Problem type: Binary Classification
+- Model ID: 1519658722
+- CO2 Emissions (in grams): 7.9405
+
+## Validation Metrics
+
+- Loss: 0.163
+- Accuracy: 0.942
+- Precision: 0.938
+- Recall: 0.978
+- AUC: 0.980
+- F1: 0.958
+
+# License Notice
+
+This work is licensed under a [Creative Commons Attribution-NoDerivatives 4.0 International License](https://creativecommons.org/licenses/by-nd/4.0/).
+
+You may distribute and make this model available to others as part of your own web page, app, or service so long as you provide attribution. However, use of this model within text-to-image systems to evade AI image detection would be considered a "derivative work" and as such prohibited by the license terms.

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "AutoTrain",
+  "architectures": [
+    "SwinForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "depths": [
+    2,
+    2,
+    18,
+    2
+  ],
+  "drop_path_rate": 0.1,
+  "embed_dim": 128,
+  "encoder_stride": 32,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "artificial",
+    "1": "human"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "artificial": "0",
+    "human": "1"
+  },
+  "layer_norm_eps": 1e-05,
+  "max_length": 128,
+  "mlp_ratio": 4.0,
+  "model_type": "swin",
+  "num_channels": 3,
+  "num_heads": [
+    4,
+    8,
+    16,
+    32
+  ],
+  "num_layers": 4,
+  "padding": "max_length",
+  "patch_size": 4,
+  "path_norm": true,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.22.1",
+  "use_absolute_embeddings": false,
+  "window_size": 7
+}

preprocessor_config.json

@@ -0,0 +1,17 @@
+{
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "ViTFeatureExtractor",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "size": 224
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c14ed23eb1d65b1c6ca7b163f8f91bebcf3a4d8c275296c850c9f1bbd01daf
+size 347596479