ultralytics 8.0.30 Docker, rect, data=*.zip updates (#832)

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: Laughing <61612323+Laughing-q@users.noreply.github.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

ultralytics/yolo/data/build.py

@@ -61,7 +61,7 @@ def seed_worker(worker_id):
     random.seed(worker_seed)
 
 
-def build_dataloader(cfg, batch_size, img_path, stride=32, label_path=None, rank=-1, mode="train"):
+def build_dataloader(cfg, batch_size, img_path, stride=32, rect=False, label_path=None, rank=-1, mode="train"):
     assert mode in ["train", "val"]
     shuffle = mode == "train"
     if cfg.rect and shuffle:
@@ -75,7 +75,7 @@ def build_dataloader(cfg, batch_size, img_path, stride=32, label_path=None, rank
             batch_size=batch_size,
             augment=mode == "train",  # augmentation
             hyp=cfg,  # TODO: probably add a get_hyps_from_cfg function
-            rect=cfg.rect if mode == "train" else True,  # rectangular batches
+            rect=cfg.rect or rect,  # rectangular batches
             cache=cfg.cache or None,
             single_cls=cfg.single_cls or False,
             stride=int(stride),

ultralytics/yolo/data/dataset.py

@@ -113,13 +113,15 @@ class YOLODataset(BaseDataset):
             tqdm(None, desc=self.prefix + d, total=n, initial=n, bar_format=TQDM_BAR_FORMAT)  # display cache results
             if cache["msgs"]:
                 LOGGER.info("\n".join(cache["msgs"]))  # display warnings
-        assert nf > 0, f"{self.prefix}No labels found in {cache_path}, can not start training. {HELP_URL}"
+        if nf == 0:  # number of labels found
+            raise FileNotFoundError(f"{self.prefix}No labels found in {cache_path}, can not start training. {HELP_URL}")
 
         # Read cache
         [cache.pop(k) for k in ("hash", "version", "msgs")]  # remove items
         labels = cache["labels"]
 
         # Check if the dataset is all boxes or all segments
+        len_cls = sum(len(lb["cls"]) for lb in labels)
         len_boxes = sum(len(lb["bboxes"]) for lb in labels)
         len_segments = sum(len(lb["segments"]) for lb in labels)
         if len_segments and len_boxes != len_segments:
@@ -129,8 +131,8 @@ class YOLODataset(BaseDataset):
                 "To avoid this please supply either a detect or segment dataset, not a detect-segment mixed dataset.")
             for lb in labels:
                 lb["segments"] = []
-        nl = len(np.concatenate([label["cls"] for label in labels], 0))  # number of labels
-        assert nl > 0, f"{self.prefix}All labels empty in {cache_path}, can not start training. {HELP_URL}"
+        if len_cls == 0:
+            raise ValueError(f"{self.prefix}All labels empty in {cache_path}, can not start training. {HELP_URL}")
         return labels
 
     # TODO: use hyp config to set all these augmentations

ultralytics/yolo/data/utils.py

@@ -192,7 +192,7 @@ def check_det_dataset(dataset, autodownload=True):
     # Download (optional)
     extract_dir = ''
     if isinstance(data, (str, Path)) and (is_zipfile(data) or is_tarfile(data)):
-        download(data, dir=f'{DATASETS_DIR}/{Path(data).stem}', unzip=True, delete=False, curl=False, threads=1)
+        download(data, dir=DATASETS_DIR, unzip=True, delete=False, curl=False, threads=1)
         data = next((DATASETS_DIR / Path(data).stem).rglob('*.yaml'))
         extract_dir, autodownload = data.parent, False
 
@@ -211,7 +211,8 @@ def check_det_dataset(dataset, autodownload=True):
     data['nc'] = len(data['names'])
 
     # Resolve paths
-    path = Path(extract_dir or data.get('path') or '')  # optional 'path' default to '.'
+    path = Path(extract_dir or data.get('path') or Path(data.get('yaml_file', '')).parent)  # dataset root
+
     if not path.is_absolute():
         path = (DATASETS_DIR / path).resolve()
         data['path'] = path  # download scripts