Format code

Author: vectornguyen76

.flake8

@@ -0,0 +1,5 @@
+[flake8]
+    ignore = F401
+    max-line-length = 100
+    max-complexity = 18
+    select = B,C,E,F,W,T4,B9

.pre-commit-config.yaml

@@ -0,0 +1,38 @@
+exclude: "^\
+  (third-party/.*)\
+  "
+
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.1.0
+    hooks:
+      - id: check-merge-conflict # checks for some markers such as "<<<<<<<", "=======", and ">>>>>>>".
+      - id: detect-private-key # detects the presence of private keys.
+      - id: end-of-file-fixer # ensures that a file is either empty, or ends with one newline.
+      - id: requirements-txt-fixer # sorts entries in requirements.txt.
+      - id: trailing-whitespace # trims trailing whitespace at the end of lines.
+
+  # Format YAML and other files
+  - repo: https://github.com/pre-commit/mirrors-prettier
+    rev: v2.5.1
+    hooks:
+      - id: prettier
+        files: \.(js|ts|jsx|tsx|css|less|html|json|markdown|md|yaml|yml)$
+
+  # Sort the order of importing libs
+  - repo: https://github.com/PyCQA/isort
+    rev: 5.12.0
+    hooks:
+      - id: isort
+        args: [--profile=black]
+
+  # Format Python files
+  - repo: https://github.com/psf/black
+    rev: 23.7.0
+    hooks:
+      - id: black
+
+  # - repo: https://github.com/PyCQA/flake8
+  #   rev: 6.1.0
+  #   hooks:
+  #     - id: flake8

README.md

@@ -1,12 +1,17 @@
 # Real-Time Face Recognition
+
 <p align="center">
   <img src="./static/results/face-recognition.gif" alt="animated" />
 </p>
 
 # How to add 1 peason to recognize
+
 ### Step 1: Create a folder with the folder name being the name of the person
+
 ### Step 2: Add the person's photo in the folder
+
 ### Step 3: Move folder to additional-training-datasets folder
+
 #### Example:
 
 - |database
@@ -17,43 +22,58 @@
 - ----|full-training-datasets
 
 ### Step 4: Set up with Python >= 3.7
-````
+
+```
 pip install -r requirements.txt
-````
+```
+
 ### Step 5: Run to add person
-````
+
+```
 python train.py --is-add-user=True
-````
+```
+
 ### Step 6: Run recognize
-````
+
+```
 python recognize.py
-````
-# Face Recognition use Yolov5-face, Insightface, Similarity Measure 
+```
+
+# Face Recognition use Yolov5-face, Insightface, Similarity Measure
+
 <p align="center">
   <img src="./static/results/workflow.png" alt="animated" />
 </p>
 
 # Yolov5-face to dectect face
+
 <p align="center">
   <img src="./static/results/face-detection.gif" alt="animated" />
 </p>
 
 # Insight Face to recognition face
+
 ![image](https://user-images.githubusercontent.com/80930272/160270088-a3760d88-ebc8-4535-907e-6b684276755a.png)
 
 # Multi thread
+
 <p align="center">
   <img src="https://user-images.githubusercontent.com/80930272/165548024-6d25fbe4-057f-4123-a3f9-3912cce2b73b.png" alt="animated" />
 </p>
 
 # Cosine Similarity Algorithm
+
 ![image](https://user-images.githubusercontent.com/80930272/160270156-37fe3269-ca65-4692-a3b2-e9568b3876f8.png)
 
 # Reference
+
 - https://github.com/deepcam-cn/yolov5-face
 - https://github.com/deepinsight/insightface/tree/master/recognition/arcface_torch
 - https://github.com/SthPhoenix/InsightFace-REST
 
 pip install torch==1.9.1+cpu torchvision==0.10.1+cpu torchaudio==0.9.1 -f https://download.pytorch.org/whl/torch_stable.html
 
-python tracking3.py video -f face_tracking/exps/example/mot/yolox_s_mix_det.py -c face_tracking/pretrained/bytetrack_s_mot17.pth.tar --fuse --save_result &> log.txt
+python tracking3.py video -f face_tracking/exps/example/mot/yolox_s_mix_det.py -c face_tracking/pretrained/bytetrack_s_mot17.pth.tar --fuse --save_result &> log.txt
+
+vector database
+kapka redis

detect.py

@@ -1,138 +1,55 @@
-#pytorch
-import torch
-from torchvision import transforms
+import time
 
-#other lib
-import sys
-import numpy as np
 import cv2
-import time
 
-sys.path.insert(0, "face_detection/yolov5_face")
-
-from face_detection.yolov5_face.models.experimental import attempt_load
-from face_detection.yolov5_face.utils.datasets import letterbox
-from face_detection.yolov5_face.utils.general import check_img_size, non_max_suppression_face, scale_coords
-
-# Check device
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-
-# Get model detect
-## Case 1:
-# model = attempt_load("face_detection/yolov5_face/yolov5s-face.pt", map_location=device)
-
-## Case 2:
-model = attempt_load("face_detection/yolov5_face/yolov5n-0.5.pt", map_location=device)
-
-# Resize image
-def resize_image(img0, img_size):
-    h0, w0 = img0.shape[:2]  # orig hw
-    r = img_size / max(h0, w0)  # resize image to img_size
-
-    if r != 1:  # always resize down, only resize up if training with augmentation
-        interp = cv2.INTER_AREA if r < 1  else cv2.INTER_LINEAR
-        img0 = cv2.resize(img0, (int(w0 * r), int(h0 * r)), interpolation=interp)
-
-    imgsz = check_img_size(img_size, s=model.stride.max())  # check img_size
-    img = letterbox(img0, new_shape=imgsz)[0]
-
-    # Convert
-    img = img[:, :, ::-1].transpose(2, 0, 1).copy()  # BGR to RGB, to 3x416x416
-
-    img = torch.from_numpy(img).to(device)
-    img = img.float()  # uint8 to fp16/32
-    img /= 255.0  # 0 - 255 to 0.0 - 1.0
-    
-    return img
-
-def scale_coords_landmarks(img1_shape, coords, img0_shape, ratio_pad=None):
-    # Rescale coords (xyxy) from img1_shape to img0_shape
-    if ratio_pad is None:  # calculate from img0_shape
-        gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1])  # gain  = old / new
-        pad = (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2  # wh padding
-    else:
-        gain = ratio_pad[0][0]
-        pad = ratio_pad[1]
-
-    coords[:, [0, 2, 4, 6, 8]] -= pad[0]  # x padding
-    coords[:, [1, 3, 5, 7, 9]] -= pad[1]  # y padding
-    coords[:, :10] /= gain
-    #clip_coords(coords, img0_shape)
-    coords[:, 0].clamp_(0, img0_shape[1])  # x1
-    coords[:, 1].clamp_(0, img0_shape[0])  # y1
-    coords[:, 2].clamp_(0, img0_shape[1])  # x2
-    coords[:, 3].clamp_(0, img0_shape[0])  # y2
-    coords[:, 4].clamp_(0, img0_shape[1])  # x3
-    coords[:, 5].clamp_(0, img0_shape[0])  # y3
-    coords[:, 6].clamp_(0, img0_shape[1])  # x4
-    coords[:, 7].clamp_(0, img0_shape[0])  # y4
-    coords[:, 8].clamp_(0, img0_shape[1])  # x5
-    coords[:, 9].clamp_(0, img0_shape[0])  # y5
-    return coords
-
-def get_face(input_image):
-    # Parameters
-    size_convert = 128
-    conf_thres = 0.4
-    iou_thres = 0.5
-    
-    # Resize image
-    img = resize_image(input_image.copy(), size_convert)
-
-    # Via yolov5-face
-    with torch.no_grad():
-        pred = model(img[None, :])[0]
-
-    # Apply NMS
-    det = non_max_suppression_face(pred, conf_thres, iou_thres)[0]
-    bboxs = np.int32(scale_coords(img.shape[1:], det[:, :4], input_image.shape).round().cpu().numpy())
-    
-    landmarks = np.int32(scale_coords_landmarks(img.shape[1:], det[:, 5:15], input_image.shape).round().cpu().numpy())    
-    
-    return bboxs, landmarks
+from face_detection.yolov5_face.detect import Detector
+
 
 def main():
-    # Open camera 
+    detector = Detector()
+
+    # Open camera
     cap = cv2.VideoCapture(0)
     start = time.time_ns()
     frame_count = 0
     fps = -1
-    
+
     # Save video
     frame_width = int(cap.get(3))
     frame_height = int(cap.get(4))
-    
+
     size = (frame_width, frame_height)
-    video = cv2.VideoWriter('results/face-detection.mp4',cv2.VideoWriter_fourcc(*'mp4v'), 30, size)
-    
+    video = cv2.VideoWriter(
+        "results/face-detection.mp4", cv2.VideoWriter_fourcc(*"mp4v"), 30, size
+    )
+
     # Read until video is completed
-    while(True):
+    while True:
         # Capture frame-by-frame
         _, frame = cap.read()
-        
+
         # Get faces
-        bboxs, landmarks = get_face(frame)
-        h,w,c = frame.shape
-        
+        bboxs, landmarks = detector.inference_detect(input_image=frame)
+        h, w, c = frame.shape
+
         tl = 1 or round(0.002 * (h + w) / 2) + 1  # line/font thickness
-        clors = [(255,0,0),(0,255,0),(0,0,255),(255,255,0),(0,255,255)]
-        
+        clors = [(255, 0, 0), (0, 255, 0), (0, 0, 255), (255, 255, 0), (0, 255, 255)]
 
         # Get boxs
         for i in range(len(bboxs)):
             # Get location face
             x1, y1, x2, y2 = bboxs[i]
             cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 146, 230), 2)
-            
+
             # Landmarks
             for x in range(5):
                 point_x = int(landmarks[i][2 * x])
                 point_y = int(landmarks[i][2 * x + 1])
-                cv2.circle(frame, (point_x, point_y), tl+1, clors[x], -1)
-            
-        # Count fps 
+                cv2.circle(frame, (point_x, point_y), tl + 1, clors[x], -1)
+
+        # Count fps
         frame_count += 1
-        
+
         if frame_count >= 30:
             end = time.time_ns()
             fps = 1e9 * frame_count / (end - start)
@@ -141,22 +58,25 @@ def main():
 
         if fps > 0:
             fps_label = "FPS: %.2f" % fps
-            cv2.putText(frame, fps_label, (10, 25), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2)
-        
-        #Save video
+            cv2.putText(
+                frame, fps_label, (10, 25), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2
+            )
+
+        # Save video
         video.write(frame)
-        
-        #Show result
+
+        # Show result
         cv2.imshow("Face Detection", frame)
-        
+
         # Press Q on keyboard to  exit
-        if cv2.waitKey(25) & 0xFF == ord('q'):
-            break  
-    
+        if cv2.waitKey(25) & 0xFF == ord("q"):
+            break
+
     video.release()
     cap.release()
     cv2.destroyAllWindows()
     cv2.waitKey(0)
 
-if __name__=="__main__":
-    main()
+
+if __name__ == "__main__":
+    main()

face_detection/retinaface/LICENSE.MIT

@@ -1,4 +1,4 @@
-MIT License 
+MIT License
 
 Copyright (c) 2019
 

face_detection/retinaface/README.md

@@ -19,13 +19,14 @@ python camera_test.py --trained_model weights/mobilenet0.25_Final.pth --network
 <h3> Using Image </h3>
 change image in ./curve, change file path in detect.py (line 87)
 
-
 backbone: resnet50
+
 ```
 python detect.py --trained_model weights/Resnet50_Final.pth --network resnet50 --cpu
 ```
 
 backbone: mobilenet0.25
+
 ```
 python detect.py --trained_model weights/mobilenet0.25_Final.pth --network mobile0.25 --cpu
 ```