Duplicate from frapochetti/blurry-faces

Co-authored-by: Francesco Pochetti <frapochetti@users.noreply.huggingface.co>

.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
+*.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
+*.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

README.md

@@ -0,0 +1,47 @@
+---
+title: Blurry Faces
+emoji: 🙈
+colorFrom: pink
+colorTo: blue
+sdk: gradio
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: frapochetti/blurry-faces
+---
+
+# Configuration
+
+`title`: _string_
+Display title for the Space
+
+`emoji`: _string_
+Space emoji (emoji-only character allowed)
+
+`colorFrom`: _string_
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`colorTo`: _string_
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`sdk`: _string_
+Can be either `gradio`, `streamlit`, or `static`
+
+`sdk_version` : _string_
+Only applicable for `streamlit` SDK.  
+See [doc](https://hf.co/docs/hub/spaces) for more info on supported versions.
+
+`app_file`: _string_
+Path to your main application file (which contains either `gradio` or `streamlit` Python code, or `static` html code).
+Path is relative to the root of the repository.
+
+`models`: _List[string]_
+HF model IDs (like "gpt2" or "deepset/roberta-base-squad2") used in the Space.
+Will be parsed automatically from your code if not specified here.
+
+`datasets`: _List[string]_
+HF dataset IDs (like "common_voice" or "oscar-corpus/OSCAR-2109") used in the Space.
+Will be parsed automatically from your code if not specified here.
+
+`pinned`: _boolean_
+Whether the Space stays on top of your list.

app.py

@@ -0,0 +1,70 @@
+import cv2
+import gradio as gr
+from typing import Union, Tuple
+from PIL import Image, ImageOps
+import numpy as np
+import torch
+
+model = torch.jit.load('./model/model.pt').eval()
+
+def resize_with_padding(img: Image.Image, expected_size: Tuple[int, int]) -> Image.Image:
+    img.thumbnail((expected_size[0], expected_size[1]))
+    delta_width = expected_size[0] - img.size[0]
+    delta_height = expected_size[1] - img.size[1]
+    pad_width = delta_width // 2
+    pad_height = delta_height // 2
+    padding = (pad_width, pad_height, delta_width - pad_width, delta_height - pad_height)
+    return ImageOps.expand(img, padding), padding
+
+def preprocess_image(img: Image.Image, size: int = 512) -> Tuple[Image.Image, torch.tensor, Tuple[int]]:    
+    pil_img, padding = resize_with_padding(img, (size, size))
+    
+    img = (np.array(pil_img).astype(np.float32) / 255) - np.array([0.485, 0.456, 0.406], dtype=np.float32).reshape(1, 1, 3)
+    img = img / np.array([0.229, 0.224, 0.225], dtype=np.float32).reshape(1, 1, 3)
+    img = np.transpose(img, (2, 0, 1))
+    
+    return pil_img, torch.tensor(img[None]), padding
+
+def soft_blur_with_mask(image: Image.Image, mask: torch.tensor, padding: Tuple[int]) -> Image.Image:
+    image = np.array(image)
+    # Create a blurred copy of the original image.
+    blurred_image = cv2.GaussianBlur(image, (221, 221), sigmaX=20, sigmaY=20)
+    image_height, image_width = image.shape[:2]
+    mask = cv2.resize(mask.astype(np.uint8), (image_width, image_height), interpolation=cv2.INTER_NEAREST)
+    # Blurring the mask itself to get a softer mask with no firm edges
+    mask = cv2.GaussianBlur(mask.astype(np.float32), (11, 11), 10, 10)[:, :, None]
+
+    # Take the blurred image where the mask it positive, and the original image where the image is original
+    image = (mask * blurred_image + (1.0 - mask) * image)
+    pad_w, pad_h, _, _ = padding
+    img_w, img_h, _ = image.shape
+    image = image[(pad_h):(img_h-pad_h), (pad_w):(img_w-pad_w), :]
+    return Image.fromarray(image.astype(np.uint8))
+
+def run(image, size):
+    pil_image, torch_image, padding = preprocess_image(image, size=size)
+
+    with torch.inference_mode():
+        mask = model(torch_image)
+    mask = mask.argmax(dim=1).numpy().squeeze()
+
+    return soft_blur_with_mask(pil_image, mask, padding)
+
+content_image_input = gr.inputs.Image(label="Content Image", type="pil")
+model_image_size = gr.inputs.Radio([256, 384, 512, 1024], type="value", default=512, label="Inference size")
+
+description="Privacy first! Upload an image of a groupf of people and blur their faces automatically."
+article="""
+Demo built on top of a face segmentation model trained from scratch with IceVision on the 
+<a href='https://github.com/microsoft/FaceSynthetics' target='_blank'>FaceSynthetics</a> dataset.
+"""
+examples = [["./images/girls.jpeg", 384], ["./images/kid.jpeg", 256], ["./images/family.jpeg", 512], ["./images/crowd1.jpeg", 1024], ["./images/crowd2.jpeg", 1024]]
+
+app_interface = gr.Interface(fn=run,
+                             inputs=[content_image_input, model_image_size],
+                             outputs="image",
+                             title="Blurry Faces",
+                             description=description,
+                             examples=examples,
+                             article=article)
+app_interface.launch()

face_rec_benchmark.py

@@ -0,0 +1,27 @@
+import face_recognition
+import cv2
+import gradio as gr
+from PIL import Image
+import numpy as np
+import time
+
+def run(image):
+    image.thumbnail((1280, 1280))
+    image = np.array(image)
+    face_locations = face_recognition.face_locations(image, model="cnn")
+
+    for top, right, bottom, left in face_locations:
+        face_image = image[top:bottom, left:right]
+        face_image = cv2.GaussianBlur(face_image, (99, 99), 30)
+        image[top:bottom, left:right] = face_image
+    
+    return Image.fromarray(image)
+
+if __name__ == "__main__":
+
+    start = time.time()
+    for _ in range(100):
+        image = Image.open("./images/crowd.jpeg")
+        _ = run(image)
+
+    print('It took', (time.time()-start)/100, 'seconds.')

kornia_benchmark.py

@@ -0,0 +1,63 @@
+import cv2
+import gradio as gr
+from PIL import Image
+import numpy as np
+import torch
+import kornia as K
+from kornia.contrib import FaceDetector, FaceDetectorResult
+import time
+
+device = torch.device('cpu')
+face_detection = FaceDetector().to(device)
+
+def scale_image(img: np.ndarray, size: int) -> np.ndarray:
+    h, w = img.shape[:2]
+    scale = 1. * size / w
+    return cv2.resize(img, (int(w * scale), int(h * scale)))
+
+
+def apply_blur_face(img: torch.Tensor, img_vis: np.ndarray, det: FaceDetectorResult):
+    # crop the face
+    x1, y1 = det.xmin.int(), det.ymin.int()
+    x2, y2 = det.xmax.int(), det.ymax.int()
+    roi = img[..., y1:y2, x1:x2]
+    #print(roi.shape)
+    if roi.shape[-1]==0 or roi.shape[-2]==0:
+        return
+
+    # apply blurring and put back to the visualisation image
+    roi = K.filters.gaussian_blur2d(roi, (21, 21), (100., 100.))
+    roi = K.color.rgb_to_bgr(roi)
+    img_vis[y1:y2, x1:x2] = K.tensor_to_image(roi)
+
+
+def run(image):
+    image.thumbnail((1280, 1280))
+    img_raw = np.array(image)
+
+    # preprocess
+    img = K.image_to_tensor(img_raw, keepdim=False).to(device)
+    img = K.color.bgr_to_rgb(img.float())
+
+    with torch.no_grad():
+        dets = face_detection(img)
+    dets = [FaceDetectorResult(o) for o in dets]
+
+    img_vis = img_raw.copy()
+
+    for b in dets:
+        if b.score < 0.5:
+            continue
+
+        apply_blur_face(img, img_vis, b)
+
+    return Image.fromarray(img_vis)
+
+if __name__ == "__main__":
+
+    start = time.time()
+    for _ in range(100):
+        image = Image.open("./images/crowd.jpeg")
+        _ = run(image)
+
+    print('It took', (time.time()-start)/100, 'seconds.')

model/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e310f25944aaf0a35a334798e72aca4494dd19f3785225042017743ecd37757
+size 165321408

packages.txt

@@ -0,0 +1,4 @@
+cmake
+ffmpeg
+libsm6
+libxext6

requirements.txt

@@ -0,0 +1,2 @@
+opencv-python==4.5.5.62
+kornia==0.6.3