Upload 6 files

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "real",
+    "1": "fake"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "fake": 1,
+    "real": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "pooler_act": "tanh",
+  "pooler_output_size": 768,
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.3"
+}

main.py

@@ -0,0 +1,39 @@
+from pathlib import Path
+from PIL import Image
+import torch
+from transformers import AutoImageProcessor, ViTForImageClassification
+from fastapi import FastAPI, File, UploadFile
+from io import BytesIO
+import shutil
+
+model_path = "./best_model"
+
+app = FastAPI()
+
+processor = AutoImageProcessor.from_pretrained(
+    model_path,
+    local_files_only=True,
+    use_fast=True
+)
+
+model = ViTForImageClassification.from_pretrained(
+    model_path,
+    local_files_only=True,
+    id2label={"0": "real", "1": "fake"},
+    label2id={"real": 0, "fake": 1}
+)
+
+def predict_image(image: Image.Image):
+    inputs = processor(image, return_tensors="pt")
+    with torch.no_grad():
+        outputs = model(**inputs)
+        pred_id = torch.argmax(outputs.logits, dim=1).item()
+        pred_label = model.config.id2label[str(pred_id)]
+    return pred_label
+
+@app.post("/predict/")
+async def upload_file(file: UploadFile = File(...)):
+    image_data = await file.read()
+    image = Image.open(BytesIO(image_data)).convert("RGB")
+    prediction = predict_image(image)
+    return {"filename": file.filename, "prediction": prediction}

makefile

@@ -0,0 +1,27 @@
+VENV_NAME = venv
+PYTHON = $(VENV_NAME)/bin/python
+
+.PHONY: all setup install train infer clean
+
+build: setup install
+
+setup:
+	python3 -m venv $(VENV_NAME)
+
+install:
+	$(PYTHON) -m pip install --upgrade pip
+	$(PYTHON) -m pip install -r requirements.txt
+
+train:
+	$(PYTHON) train.py
+
+test:
+	$(PYTHON) test.py
+
+infer:
+	uvicorn main:app --reload
+
+
+clean:
+	rm -rf $(VENV_NAME)
+	rm -rf __pycache__

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11dc93bbdaa2b9c05e3566d57cfe9d3821fdf01743c4212636b8fa2a90c723d9
+size 343223968

preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

requirements.txt

@@ -0,0 +1,9 @@
+torch
+torchvision
+transformers
+uvicorn
+fastapi
+pillow
+numpy
+scikit-learn
+scipy