Merge pull request #85 from boostcampaitech3/lyh/feat

[refactoring] Add Violence filtering #80

streamlit-fastapi-serving/fastapi/data/alter_images/pngegg.png:Zone.Identifier

@@ -0,0 +1,3 @@
+[ZoneTransfer]
+ZoneId=3
+HostUrl=https://www.pngegg.com/

streamlit-fastapi-serving/fastapi/data/blood.yaml

@@ -0,0 +1,19 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Example usage: python train.py --data trash.yaml
+# parent
+# ├── yolov5_custom
+# └── custom_dataset
+#     └── images
+#          └── train
+#     └── labels  
+
+# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
+path: ../movie_dataset # dataset root dir
+train: images/train  # train images (relative to 'path') 
+val: images/val  # val images (relative to 'path') 
+# test:
+
+# Classes
+nc: 5 # number of classes
+names: ['blood', 'splink_blood', 'scar_blood', 'puddle_blood', 'background_blood']  # class names

streamlit-fastapi-serving/fastapi/inference/blood_detection.py

@@ -0,0 +1,327 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+Run inference on images, videos, directories, streams, etc.
+
+Usage - sources:
+    $ python path/to/detect.py --weights yolov5s.pt --source 0              # webcam
+                                                             img.jpg        # image
+                                                             vid.mp4        # video
+                                                             path/          # directory
+                                                             path/*.jpg     # glob
+                                                             'https://youtu.be/Zgi9g1ksQHc'  # YouTube
+                                                             'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream
+
+Usage - formats:
+    $ python path/to/detect.py --weights yolov5s.pt                 # PyTorch
+                                         yolov5s.torchscript        # TorchScript
+                                         yolov5s.onnx               # ONNX Runtime or OpenCV DNN with --dnn
+                                         yolov5s.xml                # OpenVINO
+                                         yolov5s.engine             # TensorRT
+                                         yolov5s.mlmodel            # CoreML (macOS-only)
+                                         yolov5s_saved_model        # TensorFlow SavedModel
+                                         yolov5s.pb                 # TensorFlow GraphDef
+                                         yolov5s.tflite             # TensorFlow Lite
+                                         yolov5s_edgetpu.tflite     # TensorFlow Edge TPU
+"""
+
+# import argparse
+import easydict
+import os
+import sys
+from pathlib import Path
+
+import torch
+import torch.backends.cudnn as cudnn
+
+FILE = Path(__file__).resolve()
+# ROOT = FILE.parents[0]  # YOLOv5 root directory
+# print("blood_detection ")
+# for i, path in enumerate(FILE.parents):
+#     print(i, path)
+# 0 /home/user/linux/hipipe/streamlit-fastapi-model-serving-master/fastapi/inference
+# 1 /home/user/linux/hipipe/streamlit-fastapi-model-serving-master/fastapi
+# 2 /home/user/linux/hipipe/streamlit-fastapi-model-serving-master
+# 3 /home/user/linux/hipipe
+# 4 /home/user/linux
+# 5 /home/user
+# 6 /home
+# 7 /
+# 1
+ROOT = FILE.parents[1]
+print(ROOT)
+if str(ROOT) not in sys.path:
+    # sys.path.append(str(ROOT))  # add ROOT to PATH
+    sys.path.insert(0, str(ROOT))  # add ROOT to PATH
+ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative
+
+print("ROOT ", ROOT)
+print(sys.path)
+print(os.getcwd())
+from models.common import DetectMultiBackend
+from yolo_utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadStreams
+from yolo_utils.general import (LOGGER, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2,
+                              increment_path, non_max_suppression, print_args, scale_coords, strip_optimizer, xyxy2xywh)
+from yolo_utils.plots import Annotator, colors, save_one_box
+from yolo_utils.torch_utils import select_device, time_sync
+
+
+@torch.no_grad()
+def run(
+        # weights=ROOT / 'yolov5s.pt',  # model.pt path(s)
+        weights='',  # model.pt path(s)
+        # source=ROOT / 'data/images',  # file/dir/URL/glob, 0 for webcam
+        source='',  # file/dir/URL/glob, 0 for webcam
+        data=ROOT / 'data/blood.yaml',  # dataset.yaml path
+        imgsz=(640, 640),  # inference size (height, width)
+        conf_thres=0.25,  # confidence threshold
+        iou_thres=0.45,  # NMS IOU threshold
+        max_det=1000,  # maximum detections per image
+        device='',  # cuda device, i.e. 0 or 0,1,2,3 or cpu
+        view_img=False,  # show results
+        save_txt=False,  # save results to *.txt
+        save_conf=False,  # save confidences in --save-txt labels
+        save_crop=False,  # save cropped prediction boxes
+        nosave=False,  # do not save images/videos
+        classes=None,  # filter by class: --class 0, or --class 0 2 3
+        agnostic_nms=False,  # class-agnostic NMS
+        augment=False,  # augmented inference
+        visualize=False,  # visualize features
+        update=False,  # update all models
+        project=ROOT / 'runs/detect',  # save results to project/name
+        name='exp',  # save results to project/name
+        exist_ok=False,  # existing project/name ok, do not increment
+        line_thickness=3,  # bounding box thickness (pixels)
+        hide_labels=False,  # hide labels
+        hide_conf=False,  # hide confidences
+        half=False,  # use FP16 half-precision inference
+        dnn=False,  # use OpenCV DNN for ONNX inference
+):
+    source = str(source)
+    save_img = not nosave and not source.endswith('.txt')  # save inference images
+    is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
+    is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
+    webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file)
+    if is_url and is_file:
+        source = check_file(source)  # download
+
+    # Directories
+    # save_dir = increment_path(Path(project) / name, exist_ok=exist_ok)  # increment run
+    save_dir = Path(project) / name  # overwrite
+    (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir
+
+    # Load model
+    device = select_device(device)
+    model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
+    stride, names, pt = model.stride, model.names, model.pt
+    imgsz = check_img_size(imgsz, s=stride)  # check image size
+
+    # Dataloader
+    if webcam:
+        view_img = check_imshow()
+        cudnn.benchmark = True  # set True to speed up constant image size inference
+        dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt)
+        bs = len(dataset)  # batch_size
+    else:
+        dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt)
+        bs = 1  # batch_size
+    vid_path, vid_writer = [None] * bs, [None] * bs
+
+    # Run inference
+    model.warmup(imgsz=(1 if pt else bs, 3, *imgsz))  # warmup
+    dt, seen = [0.0, 0.0, 0.0], 0
+    for path, im, im0s, vid_cap, s in dataset:
+        t1 = time_sync()
+        im = torch.from_numpy(im).to(device)
+        im = im.half() if model.fp16 else im.float()  # uint8 to fp16/32
+        im /= 255  # 0 - 255 to 0.0 - 1.0
+        if len(im.shape) == 3:
+            im = im[None]  # expand for batch dim
+        t2 = time_sync()
+        dt[0] += t2 - t1
+
+        # Inference
+        visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
+        pred = model(im, augment=augment, visualize=visualize)
+        t3 = time_sync()
+        dt[1] += t3 - t2
+
+        # NMS
+        pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
+        dt[2] += time_sync() - t3
+
+        # Second-stage classifier (optional)
+        # pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)
+
+        # Process predictions
+        for i, det in enumerate(pred):  # per image
+            seen += 1
+            if webcam:  # batch_size >= 1
+                p, im0, frame = path[i], im0s[i].copy(), dataset.count
+                s += f'{i}: '
+            else:
+                p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0)
+
+            p = Path(p)  # to Path
+            save_path = str(save_dir / p.name)  # im.jpg
+            txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}')  # im.txt
+            s += '%gx%g ' % im.shape[2:]  # print string
+            gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]  # normalization gain whwh
+            imc = im0.copy() if save_crop else im0  # for save_crop
+            annotator = Annotator(im0, line_width=line_thickness, example=str(names))
+            if len(det):
+                # Rescale boxes from img_size to im0 size
+                det[:, :4] = scale_coords(im.shape[2:], det[:, :4], im0.shape).round()
+
+                # Print results
+                for c in det[:, -1].unique():
+                    n = (det[:, -1] == c).sum()  # detections per class
+                    s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string
+
+                # Write results
+                for *xyxy, conf, cls in reversed(det):
+                    if save_txt:  # Write to file
+                        xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
+                        line = (cls, *xywh, conf) if save_conf else (cls, *xywh)  # label format
+                        with open(f'{txt_path}.txt', 'a') as f:
+                            f.write(('%g ' * len(line)).rstrip() % line + '\n')
+
+                    if save_img or save_crop or view_img:  # Add bbox to image
+                        c = int(cls)  # integer class
+                        label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')
+                        # annotator.box_label(xyxy, label, color=colors(c, True))
+                        # annotator.mosaic_label(xyxy)
+                        # annotator.blur(xyxy)
+                        annotator.bubble(xyxy)
+                    if save_crop:
+                        save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)
+
+            # Stream results
+            im0 = annotator.result()
+            if view_img:
+                cv2.imshow(str(p), im0)
+                cv2.waitKey(1)  # 1 millisecond
+
+            # Save results (image with detections)
+            if save_img:
+                if dataset.mode == 'image':
+                    cv2.imwrite(save_path, im0)
+                else:  # 'video' or 'stream'
+                    if vid_path[i] != save_path:  # new video
+                        vid_path[i] = save_path
+                        if isinstance(vid_writer[i], cv2.VideoWriter):
+                            vid_writer[i].release()  # release previous video writer
+                        if vid_cap:  # video
+                            fps = vid_cap.get(cv2.CAP_PROP_FPS)
+                            w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+                            h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+                        else:  # stream
+                            fps, w, h = 30, im0.shape[1], im0.shape[0]
+                        save_path = str(Path(save_path).with_suffix('.mp4'))  # force *.mp4 suffix on results videos
+                        vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
+                    vid_writer[i].write(im0)
+
+        # Print time (inference-only)
+        LOGGER.info(f'{s}Done. ({t3 - t2:.3f}s)')
+
+    # Print results
+    t = tuple(x / seen * 1E3 for x in dt)  # speeds per image
+    LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t)
+    if save_txt or save_img:
+        s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
+        LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
+    if update:
+        strip_optimizer(weights)  # update model (to fix SourceChangeWarning)
+
+
+'''
+import easydict
+
+opt = easydict.EasyDict({
+    'modality': 'MIX2',
+    'rgb_list': 'list/rgb.list',
+    'flow_list': 'list/flow.list',
+    'audio_list': 'list/audio.list',
+    'test_rgb_list': 'data/list/video.list',
+    'test_flow_list': 'list/xx_flow_test.list',
+    'test_audio_list': 'data/list/audio.list',
+    'gt': 'list/gt.npy',
+    'gpus': 0,
+    'lr': 0.0001,
+    'batch_size': 128,
+    'workers': 4,
+    'model_name': 'wsanodet',
+    'pretrained_ckpt': None,
+    'feature_size': 1024+128,
+    'num_classes': 1,
+    'dataset_name': 'XD-Violence',
+    'max_seqlen': 200,
+    'max_epoch': 50,
+})
+parser = argparse.ArgumentParser(description='WeaklySupAnoDet')
+# args = option.parser.parse_args()
+args = option.opt
+'''
+
+
+def parse_opt():
+    image_path = 'data/blurred_images'
+    video_name = os.listdir(image_path)[0]
+    # parser = argparse.ArgumentParser()
+    # parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'last.pt', help='model path(s)')
+    # parser.add_argument('--source', type=str, default=os.path.join(image_path, video_name), help='file/dir/URL/glob, 0 for webcam')
+    # parser.add_argument('--data', type=str, default=ROOT / 'data/blood.yaml', help='(optional) dataset.yaml path')
+    # parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')
+    # parser.add_argument('--conf-thres', type=float, default=0.25, help='confidence threshold')
+    # parser.add_argument('--iou-thres', type=float, default=0.45, help='NMS IoU threshold')
+    # parser.add_argument('--max-det', type=int, default=1000, help='maximum detections per image')
+    # parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    # parser.add_argument('--view-img', action='store_true', help='show results')
+    # parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
+    # parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
+    # parser.add_argument('--save-crop', action='store_true', help='save cropped prediction boxes')
+    # parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
+    # parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --classes 0, or --classes 0 2 3')
+    # parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
+    # parser.add_argument('--augment', action='store_true', help='augmented inference')
+    # parser.add_argument('--visualize', action='store_true', help='visualize features')
+    # parser.add_argument('--update', action='store_true', help='update all models')
+    # parser.add_argument('--project', default=image_path, help='save results to project/name')
+    # parser.add_argument('--name', default=video_name, help='save results to project/name')
+    # parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
+    # parser.add_argument('--line-thickness', default=3, type=int, help='bounding box thickness (pixels)')
+    # parser.add_argument('--hide-labels', default=False, action='store_true', help='hide labels')
+    # parser.add_argument('--hide-conf', default=False, action='store_true', help='hide confidences')
+    # parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')
+    # parser.add_argument('--dnn', action='store_true', help='use OpenCV DNN for ONNX inference')
+    # opt = parser.parse_args()
+
+    opt = easydict.EasyDict({
+        'weights': ROOT / 'last.pt',
+        'source': os.path.join(image_path, video_name),
+        'data': ROOT / 'data/blood.yaml',
+        'imgsz': [640],
+        'conf_thres': 0.25,
+        'iou_thres': 0.45,
+        'max_det': 1000,
+        'device': '',
+        'project': image_path,
+        'name': video_name,
+        'line_thickness': 3,
+        'hide_labels': False,
+        'hide_conf': False,
+    })
+
+    opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1  # expand
+    print_args(vars(opt))
+    return opt
+
+
+def main():
+    opt = parse_opt()
+    check_requirements(exclude=('tensorboard', 'thop'))
+    run(**vars(opt))
+
+
+if __name__ == "__main__":
+    opt = parse_opt()
+    main()

streamlit-fastapi-serving/fastapi/inference/kinetics_violence_localization.py

@@ -31,16 +31,15 @@
 # sys.path.append("..")
 tf.compat.v1.disable_v2_behavior()
 # Import utilites
-from ..models.ViolenceDetectionAndLocalization.local_utils import label_map_util
+from models.ViolenceDetectionAndLocalization.local_utils import label_map_util
 # from local_utils import visualization_utils as vis_util
 
 # Name of the directory containing the object detection module we're using
 MODEL_NAME = 'inference_graph'
 
 # txtfile = open("hypotheses.txt", "w")
 # Grab path to current working directory
-# CWD_PATH = os.getcwd()
-CWD_PATH = "../models/ViolenceDetectionAndLocalization"
+CWD_PATH = "models/ViolenceDetectionAndLocalization"
 
 # Path to frozen detection graph .pb file, which contains the model that is used
 # for object detection.
@@ -117,14 +116,11 @@ def cleanfilesandfolders(boxfolderspattern,videofilespattern):
 num_detections = detection_graph.get_tensor_by_name('num_detections:0')
 
 def kinetics_violence_localization(threshold):
-
-    off_path = '../data/npys/off.npy'
-    original_image_path = '../data/images'
-    image_path = '../data/blurred_images'
+    off_path = 'data/npys/off.npy'
+    original_image_path = 'data/images'
+    image_path = 'data/blurred_images'
     video_name = os.listdir(image_path)[0]
-
     off_score = np.load(off_path)
-
     violent_scene = []
 
     for i in range(len(off_score)):