add new models

.gitignore

@@ -1 +1,3 @@
 virtualenv/
+dataset-obj365/
+dataset-rubick/

download.py

@@ -0,0 +1,58 @@
+from tqdm import tqdm
+
+from ultralytics.yolo.utils.checks import check_requirements
+from ultralytics.yolo.utils.downloads import download
+from ultralytics.yolo.utils.ops import xyxy2xywhn
+
+import numpy as np
+from pathlib import Path
+
+check_requirements(('pycocotools>=2.0',))
+from pycocotools.coco import COCO
+
+# Make Directories
+dir = Path(yaml['path'])  # dataset root dir
+for p in 'images', 'labels':
+    (dir / p).mkdir(parents=True, exist_ok=True)
+    for q in 'train', 'val':
+        (dir / p / q).mkdir(parents=True, exist_ok=True)
+
+# Train, Val Splits
+for split, patches in [('train', 50 + 1), ('val', 43 + 1)]:
+    print(f"Processing {split} in {patches} patches ...")
+    images, labels = dir / 'images' / split, dir / 'labels' / split
+
+    # Download
+    url = f"https://dorc.ks3-cn-beijing.ksyun.com/data-set/2020Objects365%E6%95%B0%E6%8D%AE%E9%9B%86/{split}/"
+    if split == 'train':
+        download([f'{url}zhiyuan_objv2_{split}.tar.gz'], dir=dir)  # annotations json
+        download([f'{url}patch{i}.tar.gz' for i in range(patches)], dir=images, curl=True, threads=8)
+    elif split == 'val':
+        download([f'{url}zhiyuan_objv2_{split}.json'], dir=dir)  # annotations json
+        download([f'{url}images/v1/patch{i}.tar.gz' for i in range(15 + 1)], dir=images, curl=True, threads=8)
+        download([f'{url}images/v2/patch{i}.tar.gz' for i in range(16, patches)], dir=images, curl=True, threads=8)
+
+    # Move
+    for f in tqdm(images.rglob('*.jpg'), desc=f'Moving {split} images'):
+        f.rename(images / f.name)  # move to /images/{split}
+
+    # Labels
+    coco = COCO(dir / f'zhiyuan_objv2_{split}.json')
+    names = [x["name"] for x in coco.loadCats(coco.getCatIds())]
+    for cid, cat in enumerate(names):
+        catIds = coco.getCatIds(catNms=[cat])
+        imgIds = coco.getImgIds(catIds=catIds)
+        for im in tqdm(coco.loadImgs(imgIds), desc=f'Class {cid + 1}/{len(names)} {cat}'):
+            width, height = im["width"], im["height"]
+            path = Path(im["file_name"])  # image filename
+            try:
+                with open(labels / path.with_suffix('.txt').name, 'a') as file:
+                    annIds = coco.getAnnIds(imgIds=im["id"], catIds=catIds, iscrowd=None)
+                    for a in coco.loadAnns(annIds):
+                        x, y, w, h = a['bbox']  # bounding box in xywh (xy top-left corner)
+                        xyxy = np.array([x, y, x + w, y + h])[None]  # pixels(1,4)
+                        x, y, w, h = xyxy2xywhn(xyxy, w=width, h=height, clip=True)[0]  # normalized and clipped
+                        file.write(f"{cid} {x:.5f} {y:.5f} {w:.5f} {h:.5f}\n")
+            except Exception as e:
+                print(e)
+

example/demo.py

@@ -1,53 +1,20 @@
 from ultralytics import YOLO
 # from ultralytics.yolo.utils.benchmarks import benchmark
-import cv2
 
 # Load a model
 # model = YOLO("yolov8n.yaml")  # build a new model from scratch
-model = YOLO("yolov8n.pt")  # load a pretrained model (recommended for training)
+# model = YOLO("../runs/detect/train3/weights/best.pt")  # zhou
+model = YOLO("../runs/detect/train4/weights/best.pt")  # 1000 img, mine
+model = YOLO("../runs/detect/train2/weights/best.pt")  # 1000 img, based on 3000 img
+# model = YOLO("../../../project/runs/detect/train3/weights/best.pt")  # 3000 img, mine
+
 
 # Use the model
 # model.train(data="coco128.yaml", epochs=3,workers=0)  # train the model,workers=0 if windows
 # metrics = model.val()  # evaluate model performance on the validation set
-'''
-results = model("bus.jpg")  # predict on an image
-print(results)
-# '''
-img_path = "./image/"
-# results = model.predict(img_path, save=True,conf=0.5) # device=0 by default, conf:置信度阈值
+img_path = "./image"
+results = model.predict(img_path, save = True) # device=0 by default, conf:置信度阈值
 # results = model.predict(img_path,save=True,classes=[0,2],conf=0.5) # i.e. classes=0,classes=[0,3,4]
 
 # save detection results *
 # results = model.predict(img_path,save=True,save_txt=True,classes=0,conf=0.4)
-
-
-
-# predict video
-video_path = "./video/1.mp4"
-cap = cv2.VideoCapture(0)
-
-# Loop through the video frames
-while cap.isOpened():
-    # Read a frame from the video
-    success, frame = cap.read()
-
-    if success:
-        # Run YOLOv8 inference on the frame
-        results = model(frame)
-
-        # Visualize the results on the frame
-        annotated_frame = results[0].plot()
-
-        # Display the annotated frame
-        cv2.imshow("YOLOv8 Inference", annotated_frame)
-
-        # Break the loop if 'q' is pressed
-        if cv2.waitKey(1) & 0xFF == ord("q"):
-            break
-    else:
-        # Break the loop if the end of the video is reached
-        break
-
-# Release the video capture object and close the display window
-cap.release()
-cv2.destroyAllWindows()

example/video.py

@@ -0,0 +1,39 @@
+import cv2
+from ultralytics import YOLO
+
+# Load the YOLOv8 model
+# model = YOLO("../runs/detect/train3/weights/best.pt")  # zhou
+# model = YOLO("../runs/detect/train4/weights/best.pt")  # 1000 img, mine
+# model = YOLO("../runs/detect/train2/weights/best.pt")  # 1000 img, based on 3000 img
+model = YOLO("../../../project/runs/detect/train3/weights/best.pt")  # 3000 img, mine
+
+
+# Open the video file
+video_path = "./video/demo_video_no_detection.mp4"
+cap = cv2.VideoCapture(video_path)
+
+# Loop through the video frames
+while cap.isOpened():
+    # Read a frame from the video
+    success, frame = cap.read()
+
+    if success:
+        # Run YOLOv8 inference on the frame
+        results = model(frame)
+
+        # Visualize the results on the frame
+        annotated_frame = results[0].plot()
+
+        # Display the annotated frame
+        cv2.imshow("YOLOv8 Inference", annotated_frame)
+
+        # Break the loop if 'q' is pressed
+        if cv2.waitKey(1) & 0xFF == ord("q"):
+            break
+    else:
+        # Break the loop if the end of the video is reached
+        break
+
+# Release the video capture object and close the display window
+cap.release()
+cv2.destroyAllWindows()

runs/detect/train2/args.yaml

@@ -0,0 +1,97 @@
+task: detect
+mode: train
+model: ../../project/runs/detect/train3/weights/best.pt
+data: ../datasets/zcxv.v2i.yolov8/data.yaml
+epochs: 100
+patience: 50
+batch: 16
+imgsz: 640
+save: true
+save_period: -1
+cache: false
+device: cuda
+workers: 8
+project: null
+name: null
+exist_ok: false
+pretrained: true
+optimizer: auto
+verbose: true
+seed: 0
+deterministic: true
+single_cls: false
+rect: false
+cos_lr: false
+close_mosaic: 0
+resume: false
+amp: true
+fraction: 1.0
+profile: false
+overlap_mask: true
+mask_ratio: 4
+dropout: 0.0
+val: true
+split: val
+save_json: false
+save_hybrid: false
+conf: null
+iou: 0.7
+max_det: 300
+half: false
+dnn: false
+plots: true
+source: null
+show: false
+save_txt: false
+save_conf: false
+save_crop: false
+show_labels: true
+show_conf: true
+vid_stride: 1
+line_width: null
+visualize: false
+augment: false
+agnostic_nms: false
+classes: null
+retina_masks: false
+boxes: true
+format: torchscript
+keras: false
+optimize: false
+int8: false
+dynamic: false
+simplify: false
+opset: null
+workspace: 4
+nms: false
+lr0: 0.01
+lrf: 0.01
+momentum: 0.937
+weight_decay: 0.0005
+warmup_epochs: 3.0
+warmup_momentum: 0.8
+warmup_bias_lr: 0.1
+box: 7.5
+cls: 0.5
+dfl: 1.5
+pose: 12.0
+kobj: 1.0
+label_smoothing: 0.0
+nbs: 64
+hsv_h: 0.015
+hsv_s: 0.7
+hsv_v: 0.4
+degrees: 0.0
+translate: 0.1
+scale: 0.5
+shear: 0.0
+perspective: 0.0
+flipud: 0.0
+fliplr: 0.5
+mosaic: 1.0
+mixup: 0.0
+copy_paste: 0.0
+cfg: null
+v5loader: false
+tracker: botsort.yaml
+save_dir: /home/ryan/Documents/School/2023t1/dnb/project/runs/detect/train2