Update app.py

app.py

@@ -17,7 +17,7 @@ def parse_roboflow_url(url: str):
     parsed = urlparse(url)
     parts = parsed.path.strip('/').split('/')
     workspace = parts[0]
-    project   = parts[1]
+    project = parts[1]
     try:
         version = int(parts[-1])
     except ValueError:
@@ -71,8 +71,7 @@ def convert_seg_to_bbox(api_key: str, dataset_url: str, split_ratios=(0.8, 0.1,
         )
         annos.setdefault(img_id, []).append(line)
 
-    # prepare temporary split folder
-    out_root = tempfile.mkdtemp(prefix="yolov8_")
+    # gather all filenames and paths
     name_to_id = {img['file_name']: img['id'] for img in coco['images']}
     file_paths = {
         f: os.path.join(dp, f)
@@ -81,7 +80,7 @@ def convert_seg_to_bbox(api_key: str, dataset_url: str, split_ratios=(0.8, 0.1,
         if f in name_to_id
     }
 
-    # determine splits
+    # split filenames
     all_files = list(name_to_id.keys())
     random.shuffle(all_files)
     n = len(all_files)
@@ -94,7 +93,12 @@ def convert_seg_to_bbox(api_key: str, dataset_url: str, split_ratios=(0.8, 0.1,
         "test":  all_files[n_train+n_valid:]
     }
 
-    # create Roboflow‐style folders
+    # create Roboflow‐style dataset folder:
+    # out_root/
+    #   train/images, train/labels,
+    #   valid/images, valid/labels,
+    #   test/images, test/labels
+    out_root = tempfile.mkdtemp(prefix="yolov8_")
     for split, files in splits.items():
         img_dir = os.path.join(out_root, split, "images")
         lbl_dir = os.path.join(out_root, split, "labels")
@@ -108,19 +112,17 @@ def convert_seg_to_bbox(api_key: str, dataset_url: str, split_ratios=(0.8, 0.1,
             with open(os.path.join(lbl_dir, fname.rsplit('.',1)[0] + ".txt"), 'w') as f:
                 f.write(txt)
 
-    # prepare display examples
+    # prepare a few before/after examples
     before, after = [], []
     sample = random.sample(all_files, min(5, len(all_files)))
     for fname in sample:
         img = cv2.cvtColor(cv2.imread(file_paths[fname]), cv2.COLOR_BGR2RGB)
-
         seg_vis = img.copy()
         for anno in coco['annotations']:
             if anno['image_id'] != name_to_id[fname]:
                 continue
             pts = np.array(anno['segmentation'][0], np.int32).reshape(-1,2)
             cv2.polylines(seg_vis, [pts], True, (255,0,0), 2)
-
         box_vis = img.copy()
         for line in annos.get(name_to_id[fname], []):
             _, cxn, cyn, wnorm, hnorm = map(float, line.split())
@@ -129,7 +131,6 @@ def convert_seg_to_bbox(api_key: str, dataset_url: str, split_ratios=(0.8, 0.1,
             x0 = int(cxn*iw - w0/2)
             y0 = int(cyn*ih - h0/2)
             cv2.rectangle(box_vis, (x0,y0), (x0+w0,y0+h0), (0,255,0), 2)
-
         before.append(Image.fromarray(seg_vis))
         after.append(Image.fromarray(box_vis))
 
@@ -145,14 +146,14 @@ def upload_and_train_detection(
     project_type: str = "object-detection"
 ):
     """
-    Uploads your converted dataset into *your* active Roboflow workspace,
-    creates (or finds) a project named `detection_slug`, and kicks off training.
-    Returns the hosted endpoint URL.
+    Uploads the converted dataset (with train/valid/test splits) to Roboflow,
+    creates or fetches a detection project, and kicks off training.
+    Returns the hosted model URL.
     """
     rf = Roboflow(api_key=api_key)
     ws = rf.workspace()
 
-    # get-or-create project
+    # get or create project
     try:
         proj = ws.project(detection_slug)
     except Exception as e:
@@ -175,7 +176,7 @@ def upload_and_train_detection(
         project_type=project_type
     )
 
-    # generate new version (with fallback)
+    # generate new version (with fallback slug bump)
     try:
         version_num = proj.generate_version(settings={"augmentation": {}, "preprocessing": {}})
     except RuntimeError as e:
@@ -195,7 +196,7 @@ def upload_and_train_detection(
         else:
             raise
 
-    # wait until ready, then train
+    # wait for generation, then train
     for _ in range(20):
         try:
             model = proj.version(str(version_num)).train()