Duplicate from aaronespasa/deepfake-detection

Co-authored-by: Aarón Espasandín <[email protected]>

.gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+examples/

README.md

@@ -0,0 +1,14 @@
+---
+title: Deepfake Detection
+emoji: 📚
+colorFrom: red
+colorTo: indigo
+sdk: gradio
+sdk_version: 3.0.14
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: aaronespasa/deepfake-detection
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,102 @@
+import gradio as gr
+import torch
+import torch.nn.functional as F
+from facenet_pytorch import MTCNN, InceptionResnetV1
+import os
+import numpy as np
+from PIL import Image
+import zipfile
+import cv2
+from pytorch_grad_cam import GradCAM
+from pytorch_grad_cam.utils.model_targets import ClassifierOutputTarget
+from pytorch_grad_cam.utils.image import show_cam_on_image
+
+with zipfile.ZipFile("examples.zip","r") as zip_ref:
+    zip_ref.extractall(".")
+
+DEVICE = 'cuda:0' if torch.cuda.is_available() else 'cpu'
+
+mtcnn = MTCNN(
+    select_largest=False,
+    post_process=False,
+    device=DEVICE
+).to(DEVICE).eval()
+
+model = InceptionResnetV1(
+    pretrained="vggface2",
+    classify=True,
+    num_classes=1,
+    device=DEVICE
+)
+
+checkpoint = torch.load("resnetinceptionv1_epoch_32.pth", map_location=torch.device('cpu'))
+model.load_state_dict(checkpoint['model_state_dict'])
+model.to(DEVICE)
+model.eval()
+
+EXAMPLES_FOLDER = 'examples'
+examples_names = os.listdir(EXAMPLES_FOLDER)
+examples = []
+for example_name in examples_names:
+    example_path = os.path.join(EXAMPLES_FOLDER, example_name)
+    label = example_name.split('_')[0]
+    example = {
+        'path': example_path,
+        'label': label
+    }
+    examples.append(example)
+np.random.shuffle(examples) # shuffle
+
+def predict(input_image:Image.Image, true_label:str):
+    """Predict the label of the input_image"""
+    face = mtcnn(input_image)
+    if face is None:
+        raise Exception('No face detected')
+    face = face.unsqueeze(0) # add the batch dimension
+    face = F.interpolate(face, size=(256, 256), mode='bilinear', align_corners=False)
+    
+    # convert the face into a numpy array to be able to plot it
+    prev_face = face.squeeze(0).permute(1, 2, 0).cpu().detach().int().numpy()
+    prev_face = prev_face.astype('uint8')
+
+    face = face.to(DEVICE)
+    face = face.to(torch.float32)
+    face = face / 255.0
+    face_image_to_plot = face.squeeze(0).permute(1, 2, 0).cpu().detach().int().numpy()
+
+    target_layers=[model.block8.branch1[-1]]
+    use_cuda = True if torch.cuda.is_available() else False
+    cam = GradCAM(model=model, target_layers=target_layers, use_cuda=use_cuda)
+    targets = [ClassifierOutputTarget(0)]
+
+    grayscale_cam = cam(input_tensor=face, targets=targets, eigen_smooth=True)
+    grayscale_cam = grayscale_cam[0, :]
+    visualization = show_cam_on_image(face_image_to_plot, grayscale_cam, use_rgb=True)
+    face_with_mask = cv2.addWeighted(prev_face, 1, visualization, 0.5, 0)
+
+    with torch.no_grad():
+        output = torch.sigmoid(model(face).squeeze(0))
+        prediction = "real" if output.item() < 0.5 else "fake"
+        
+        real_prediction = 1 - output.item()
+        fake_prediction = output.item()
+        
+        confidences = {
+            'real': real_prediction,
+            'fake': fake_prediction
+        }
+    return confidences, true_label, face_with_mask
+
+interface = gr.Interface(
+    fn=predict,
+    inputs=[
+        gr.inputs.Image(label="Input Image", type="pil"),
+        "text"
+    ],
+    outputs=[
+        gr.outputs.Label(label="Class"),
+        "text",
+        gr.outputs.Image(label="Face with Explainability")
+    ],
+    examples=[[examples[i]["path"], examples[i]["label"]] for i in range(10)]
+).launch()

examples.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c719c2f16bad2e71d0d33d6ae59fa646dac82a812e1a90578c4b97ef6e8f36c
+size 28750945

requirements.txt

@@ -0,0 +1,6 @@
+gradio==3.0.9
+Pillow
+facenet-pytorch==2.5.2
+torch==1.11.0
+opencv-python
+grad-cam

resnetinceptionv1_epoch_32.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:794ebe83c6a7d7959c30c175030b4885e2b9fa175f1cc3e582236595d119f52b
+size 282395989