manual merge

Author: htuann2712

.gitignore

@@ -0,0 +1 @@
+*/__pycache__

LICENSE

@@ -1 +1,4 @@
+Run facedet
 
+
+ python .\yolo2deepsort.py --weights ./weights/yolov5n-face.pt --source 0 --view-img

README.md

@@ -0,0 +1,21 @@
+# Argoverse-HD dataset (ring-front-center camera) http://www.cs.cmu.edu/~mengtial/proj/streaming/
+# Train command: python train.py --data argoverse_hd.yaml
+# Default dataset location is next to /yolov5:
+#   /parent_folder
+#     /argoverse
+#     /yolov5
+
+
+# download command/URL (optional)
+download: bash data/scripts/get_argoverse_hd.sh
+
+# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
+train: ../argoverse/Argoverse-1.1/images/train/  # 39384 images
+val: ../argoverse/Argoverse-1.1/images/val/  # 15062 iamges
+test: ../argoverse/Argoverse-1.1/images/test/  # Submit to: https://eval.ai/web/challenges/challenge-page/800/overview
+
+# number of classes
+nc: 8
+
+# class names
+names: [ 'person',  'bicycle',  'car',  'motorcycle',  'bus',  'truck',  'traffic_light',  'stop_sign' ]

data/argoverse_hd.yaml

@@ -0,0 +1,35 @@
+# COCO 2017 dataset http://cocodataset.org
+# Train command: python train.py --data coco.yaml
+# Default dataset location is next to /yolov5:
+#   /parent_folder
+#     /coco
+#     /yolov5
+
+
+# download command/URL (optional)
+download: bash data/scripts/get_coco.sh
+
+# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
+train: ../coco/train2017.txt  # 118287 images
+val: ../coco/val2017.txt  # 5000 images
+test: ../coco/test-dev2017.txt  # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794
+
+# number of classes
+nc: 80
+
+# class names
+names: [ 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light',
+         'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
+         'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee',
+         'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard',
+         'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple',
+         'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch',
+         'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone',
+         'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear',
+         'hair drier', 'toothbrush' ]
+
+# Print classes
+# with open('data/coco.yaml') as f:
+#   d = yaml.load(f, Loader=yaml.FullLoader)  # dict
+#   for i, x in enumerate(d['names']):
+#     print(i, x)

data/coco.yaml

@@ -0,0 +1,28 @@
+# COCO 2017 dataset http://cocodataset.org - first 128 training images
+# Train command: python train.py --data coco128.yaml
+# Default dataset location is next to /yolov5:
+#   /parent_folder
+#     /coco128
+#     /yolov5
+
+
+# download command/URL (optional)
+download: https://github.com/ultralytics/yolov5/releases/download/v1.0/coco128.zip
+
+# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
+train: ../coco128/images/train2017/  # 128 images
+val: ../coco128/images/train2017/  # 128 images
+
+# number of classes
+nc: 80
+
+# class names
+names: [ 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light',
+         'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
+         'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee',
+         'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard',
+         'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple',
+         'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch',
+         'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone',
+         'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear',
+         'hair drier', 'toothbrush' ]

data/coco128.yaml

@@ -0,0 +1,38 @@
+# Hyperparameters for VOC finetuning
+# python train.py --batch 64 --weights yolov5m.pt --data voc.yaml --img 512 --epochs 50
+# See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials
+
+
+# Hyperparameter Evolution Results
+# Generations: 306
+#                   P         R     mAP.5 mAP.5:.95       box       obj       cls
+# Metrics:        0.6     0.936     0.896     0.684    0.0115   0.00805   0.00146
+
+lr0: 0.0032
+lrf: 0.12
+momentum: 0.843
+weight_decay: 0.00036
+warmup_epochs: 2.0
+warmup_momentum: 0.5
+warmup_bias_lr: 0.05
+box: 0.0296
+cls: 0.243
+cls_pw: 0.631
+obj: 0.301
+obj_pw: 0.911
+iou_t: 0.2
+anchor_t: 2.91
+# anchors: 3.63
+fl_gamma: 0.0
+hsv_h: 0.0138
+hsv_s: 0.664
+hsv_v: 0.464
+degrees: 0.373
+translate: 0.245
+scale: 0.898
+shear: 0.602
+perspective: 0.0
+flipud: 0.00856
+fliplr: 0.5
+mosaic: 1.0
+mixup: 0.243

data/hyp.finetune.yaml

@@ -0,0 +1,34 @@
+# Hyperparameters for COCO training from scratch
+# python train.py --batch 40 --cfg yolov5m.yaml --weights '' --data coco.yaml --img 640 --epochs 300
+# See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials
+
+
+lr0: 0.01  # initial learning rate (SGD=1E-2, Adam=1E-3)
+lrf: 0.2  # final OneCycleLR learning rate (lr0 * lrf)
+momentum: 0.937  # SGD momentum/Adam beta1
+weight_decay: 0.0005  # optimizer weight decay 5e-4
+warmup_epochs: 3.0  # warmup epochs (fractions ok)
+warmup_momentum: 0.8  # warmup initial momentum
+warmup_bias_lr: 0.1  # warmup initial bias lr
+box: 0.05  # box loss gain
+cls: 0.5  # cls loss gain
+landmark: 0.005 # landmark loss gain
+cls_pw: 1.0  # cls BCELoss positive_weight
+obj: 1.0  # obj loss gain (scale with pixels)
+obj_pw: 1.0  # obj BCELoss positive_weight
+iou_t: 0.20  # IoU training threshold
+anchor_t: 4.0  # anchor-multiple threshold
+# anchors: 3  # anchors per output layer (0 to ignore)
+fl_gamma: 0.0  # focal loss gamma (efficientDet default gamma=1.5)
+hsv_h: 0.015  # image HSV-Hue augmentation (fraction)
+hsv_s: 0.7  # image HSV-Saturation augmentation (fraction)
+hsv_v: 0.4  # image HSV-Value augmentation (fraction)
+degrees: 0.0  # image rotation (+/- deg)
+translate: 0.1  # image translation (+/- fraction)
+scale: 0.5  # image scale (+/- gain)
+shear: 0.5  # image shear (+/- deg)
+perspective: 0.0  # image perspective (+/- fraction), range 0-0.001
+flipud: 0.0  # image flip up-down (probability)
+fliplr: 0.5  # image flip left-right (probability)
+mosaic: 0.5  # image mosaic (probability)
+mixup: 0.0  # image mixup (probability)

data/hyp.scratch.yaml

@@ -0,0 +1,150 @@
+import os
+import os.path
+import sys
+import torch
+import torch.utils.data as data
+import cv2
+import numpy as np
+
+class WiderFaceDetection(data.Dataset):
+    def __init__(self, txt_path, preproc=None):
+        self.preproc = preproc
+        self.imgs_path = []
+        self.words = []
+        f = open(txt_path,'r')
+        lines = f.readlines()
+        isFirst = True
+        labels = []
+        for line in lines:
+            line = line.rstrip()
+            if line.startswith('#'):
+                if isFirst is True:
+                    isFirst = False
+                else:
+                    labels_copy = labels.copy()
+                    self.words.append(labels_copy)
+                    labels.clear()
+                path = line[2:]
+                path = txt_path.replace('label.txt','images/') + path
+                self.imgs_path.append(path)
+            else:
+                line = line.split(' ')
+                label = [float(x) for x in line]
+                labels.append(label)
+
+        self.words.append(labels)
+
+    def __len__(self):
+        return len(self.imgs_path)
+
+    def __getitem__(self, index):
+        img = cv2.imread(self.imgs_path[index])
+        height, width, _ = img.shape
+
+        labels = self.words[index]
+        annotations = np.zeros((0, 15))
+        if len(labels) == 0:
+            return annotations
+        for idx, label in enumerate(labels):
+            annotation = np.zeros((1, 15))
+            # bbox
+            annotation[0, 0] = label[0]  # x1
+            annotation[0, 1] = label[1]  # y1
+            annotation[0, 2] = label[0] + label[2]  # x2
+            annotation[0, 3] = label[1] + label[3]  # y2
+
+            # landmarks
+            annotation[0, 4] = label[4]    # l0_x
+            annotation[0, 5] = label[5]    # l0_y
+            annotation[0, 6] = label[7]    # l1_x
+            annotation[0, 7] = label[8]    # l1_y
+            annotation[0, 8] = label[10]   # l2_x
+            annotation[0, 9] = label[11]   # l2_y
+            annotation[0, 10] = label[13]  # l3_x
+            annotation[0, 11] = label[14]  # l3_y
+            annotation[0, 12] = label[16]  # l4_x
+            annotation[0, 13] = label[17]  # l4_y
+            if (annotation[0, 4]<0):
+                annotation[0, 14] = -1
+            else:
+                annotation[0, 14] = 1
+
+            annotations = np.append(annotations, annotation, axis=0)
+        target = np.array(annotations)
+        if self.preproc is not None:
+            img, target = self.preproc(img, target)
+
+        return torch.from_numpy(img), target
+
+def detection_collate(batch):
+    """Custom collate fn for dealing with batches of images that have a different
+    number of associated object annotations (bounding boxes).
+
+    Arguments:
+        batch: (tuple) A tuple of tensor images and lists of annotations
+
+    Return:
+        A tuple containing:
+            1) (tensor) batch of images stacked on their 0 dim
+            2) (list of tensors) annotations for a given image are stacked on 0 dim
+    """
+    targets = []
+    imgs = []
+    for _, sample in enumerate(batch):
+        for _, tup in enumerate(sample):
+            if torch.is_tensor(tup):
+                imgs.append(tup)
+            elif isinstance(tup, type(np.empty(0))):
+                annos = torch.from_numpy(tup).float()
+                targets.append(annos)
+
+    return (torch.stack(imgs, 0), targets)
+
+save_path = '/ssd_1t/derron/yolov5-face/data/widerface/train'
+aa=WiderFaceDetection("/ssd_1t/derron/yolov5-face/data/widerface/widerface/train/label.txt")
+for i in range(len(aa.imgs_path)):
+    print(i, aa.imgs_path[i])
+    img = cv2.imread(aa.imgs_path[i])
+    base_img = os.path.basename(aa.imgs_path[i])
+    base_txt = os.path.basename(aa.imgs_path[i])[:-4] +".txt"
+    save_img_path = os.path.join(save_path, base_img)
+    save_txt_path = os.path.join(save_path, base_txt)
+    with open(save_txt_path, "w") as f:
+        height, width, _ = img.shape
+        labels = aa.words[i]
+        annotations = np.zeros((0, 14))
+        if len(labels) == 0:
+            continue
+        for idx, label in enumerate(labels):
+            annotation = np.zeros((1, 14))
+            # bbox
+            label[0] = max(0, label[0])
+            label[1] = max(0, label[1])
+            label[2] = min(width -  1, label[2])
+            label[3] = min(height - 1, label[3])
+            annotation[0, 0] = (label[0] + label[2] / 2) / width  # cx
+            annotation[0, 1] = (label[1] + label[3] / 2) / height  # cy
+            annotation[0, 2] = label[2] / width  # w
+            annotation[0, 3] = label[3] / height  # h
+            #if (label[2] -label[0]) < 8 or (label[3] - label[1]) < 8:
+            #    img[int(label[1]):int(label[3]), int(label[0]):int(label[2])] = 127
+            #    continue
+            # landmarks
+            annotation[0, 4] = label[4] / width  # l0_x
+            annotation[0, 5] = label[5] / height  # l0_y
+            annotation[0, 6] = label[7] / width  # l1_x
+            annotation[0, 7] = label[8]  / height # l1_y
+            annotation[0, 8] = label[10] / width  # l2_x
+            annotation[0, 9] = label[11] / height  # l2_y
+            annotation[0, 10] = label[13] / width  # l3_x
+            annotation[0, 11] = label[14] / height  # l3_y
+            annotation[0, 12] = label[16] / width  # l4_x
+            annotation[0, 13] = label[17] / height  # l4_y
+            str_label="0 "
+            for i in range(len(annotation[0])):
+                str_label =str_label+" "+str(annotation[0][i])
+            str_label = str_label.replace('[', '').replace(']', '')
+            str_label = str_label.replace(',', '') + '\n'
+            f.write(str_label)
+    cv2.imwrite(save_img_path, img)
+

data/images/1.jpg

@@ -0,0 +1,62 @@
+#!/bin/bash
+# Argoverse-HD dataset (ring-front-center camera) http://www.cs.cmu.edu/~mengtial/proj/streaming/
+# Download command: bash data/scripts/get_argoverse_hd.sh
+# Train command: python train.py --data argoverse_hd.yaml
+# Default dataset location is next to /yolov5:
+#   /parent_folder
+#     /argoverse
+#     /yolov5
+
+# Download/unzip images
+d='../argoverse/' # unzip directory
+mkdir $d
+url=https://argoverse-hd.s3.us-east-2.amazonaws.com/
+f=Argoverse-HD-Full.zip
+curl -L $url$f -o $f && unzip -q $f -d $d && rm $f &# download, unzip, remove in background
+wait                                              # finish background tasks
+
+cd ../argoverse/Argoverse-1.1/
+ln -s tracking images
+
+cd ../Argoverse-HD/annotations/
+
+python3 - "$@" <<END
+import json
+from pathlib import Path
+
+annotation_files = ["train.json", "val.json"]
+print("Converting annotations to YOLOv5 format...")
+
+for val in annotation_files:
+    a = json.load(open(val, "rb"))
+
+    label_dict = {}
+    for annot in a['annotations']:
+        img_id = annot['image_id']
+        img_name = a['images'][img_id]['name']
+        img_label_name = img_name[:-3] + "txt"
+
+        obj_class = annot['category_id']
+        x_center, y_center, width, height = annot['bbox']
+        x_center = (x_center + width / 2) / 1920.  # offset and scale
+        y_center = (y_center + height / 2) / 1200.  # offset and scale
+        width /= 1920.  # scale
+        height /= 1200.  # scale
+
+        img_dir = "./labels/" + a['seq_dirs'][a['images'][annot['image_id']]['sid']]
+
+        Path(img_dir).mkdir(parents=True, exist_ok=True)
+
+        if img_dir + "/" + img_label_name not in label_dict:
+            label_dict[img_dir + "/" + img_label_name] = []
+
+        label_dict[img_dir + "/" + img_label_name].append(f"{obj_class} {x_center} {y_center} {width} {height}\n")
+
+    for filename in label_dict:
+        with open(filename, "w") as file:
+            for string in label_dict[filename]:
+                file.write(string)
+
+END
+
+mv ./labels ../../Argoverse-1.1/