Use pathlib in DOTA ops (#7552)

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>

docker/Dockerfile-cpu

@@ -32,7 +32,7 @@ RUN pip install --no-cache -e ".[export]" lancedb --extra-index-url https://down
 RUN yolo export model=tmp/yolov8n.pt format=edgetpu imgsz=32
 RUN yolo export model=tmp/yolov8n.pt format=ncnn imgsz=32
 # Requires <= Python 3.10, bug with paddlepaddle==2.5.0 https://github.com/PaddlePaddle/X2Paddle/issues/991
-# RUN pip install --no-cache paddlepaddle==2.4.2 x2paddle
+# RUN pip install --no-cache paddlepaddle>=2.6.0 x2paddle
 # Remove exported models
 RUN rm -rf tmp
 

ultralytics/data/split_dota.py

@@ -1,7 +1,6 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
 import itertools
-import os
 from glob import glob
 from math import ceil
 from pathlib import Path
@@ -73,9 +72,9 @@ def load_yolo_dota(data_root, split="train"):
                     - val
     """
     assert split in ["train", "val"]
-    im_dir = os.path.join(data_root, f"images/{split}")
+    im_dir = Path(data_root) / "images" / split
-    assert Path(im_dir).exists(), f"Can't find {im_dir}, please check your data root."
+    assert im_dir.exists(), f"Can't find {im_dir}, please check your data root."
-    im_files = glob(os.path.join(data_root, f"images/{split}/*"))
+    im_files = glob(str(Path(data_root) / "images" / split / "*"))
     lb_files = img2label_paths(im_files)
     annos = []
     for im_file, lb_file in zip(im_files, lb_files):
@@ -94,7 +93,7 @@ def get_windows(im_size, crop_sizes=[1024], gaps=[200], im_rate_thr=0.6, eps=0.0
     Args:
         im_size (tuple): Original image size, (h, w).
         crop_sizes (List(int)): Crop size of windows.
-        gaps (List(int)): Gap between each crops.
+        gaps (List(int)): Gap between crops.
         im_rate_thr (float): Threshold of windows areas divided by image ares.
     """
     h, w = im_size
@@ -173,7 +172,7 @@ def crop_and_save(anno, windows, window_objs, im_dir, lb_dir):
         patch_im = im[y_start:y_stop, x_start:x_stop]
         ph, pw = patch_im.shape[:2]
 
-        cv2.imwrite(os.path.join(im_dir, f"{new_name}.jpg"), patch_im)
+        cv2.imwrite(str(Path(im_dir) / f"{new_name}.jpg"), patch_im)
         label = window_objs[i]
         if len(label) == 0:
             continue
@@ -182,7 +181,7 @@ def crop_and_save(anno, windows, window_objs, im_dir, lb_dir):
         label[:, 1::2] /= pw
         label[:, 2::2] /= ph
 
-        with open(os.path.join(lb_dir, f"{new_name}.txt"), "w") as f:
+        with open(Path(lb_dir) / f"{new_name}.txt", "w") as f:
             for lb in label:
                 formatted_coords = ["{:.6g}".format(coord) for coord in lb[1:]]
                 f.write(f"{int(lb[0])} {' '.join(formatted_coords)}\n")
@@ -269,7 +268,7 @@ def split_test(data_root, save_dir, crop_size=1024, gap=200, rates=[1.0]):
     save_dir = Path(save_dir) / "images" / "test"
     save_dir.mkdir(parents=True, exist_ok=True)
 
-    im_dir = Path(os.path.join(data_root, "images/test"))
+    im_dir = Path(data_root) / "images" / "test"
     assert im_dir.exists(), f"Can't find {im_dir}, please check your data root."
     im_files = glob(str(im_dir / "*"))
     for im_file in tqdm(im_files, total=len(im_files), desc="test"):
@@ -281,15 +280,9 @@ def split_test(data_root, save_dir, crop_size=1024, gap=200, rates=[1.0]):
             x_start, y_start, x_stop, y_stop = window.tolist()
             new_name = f"{name}__{x_stop - x_start}__{x_start}___{y_start}"
             patch_im = im[y_start:y_stop, x_start:x_stop]
-            cv2.imwrite(os.path.join(str(save_dir), f"{new_name}.jpg"), patch_im)
+            cv2.imwrite(str(save_dir / f"{new_name}.jpg"), patch_im)
 
 
 if __name__ == "__main__":
-    split_trainval(
+    split_trainval(data_root="DOTAv2", save_dir="DOTAv2-split")
-        data_root="DOTAv2",
+    split_test(data_root="DOTAv2", save_dir="DOTAv2-split")
-        save_dir="DOTAv2-split",
-    )
-    split_test(
-        data_root="DOTAv2",
-        save_dir="DOTAv2-split",
-    )

ultralytics/models/sam/modules/encoders.py

@@ -198,12 +198,7 @@ class PromptEncoder(nn.Module):
         """
         return self.pe_layer(self.image_embedding_size).unsqueeze(0)
 
-    def _embed_points(
+    def _embed_points(self, points: torch.Tensor, labels: torch.Tensor, pad: bool) -> torch.Tensor:
-        self,
-        points: torch.Tensor,
-        labels: torch.Tensor,
-        pad: bool,
-    ) -> torch.Tensor:
         """Embeds point prompts."""
         points = points + 0.5  # Shift to center of pixel
         if pad:

ultralytics/utils/benchmarks.py

@@ -84,12 +84,8 @@ def benchmark(
         emoji, filename = "❌", None  # export defaults
         try:
             assert i != 9 or LINUX, "Edge TPU export only supported on Linux"
-            if i == 5:
+            if i in {5, 10}:  # CoreML and TF.js
-                assert MACOS or LINUX, "CoreML export only supported on macOS and Linux"
+                assert MACOS or LINUX, "export only supported on macOS and Linux"
-            elif i == 10:
-                assert MACOS or LINUX, "TF.js export only supported on macOS and Linux"
-            # elif i == 11:
-            #     assert sys.version_info < (3, 11), "PaddlePaddle export only supported on Python<=3.10"
             if "cpu" in device.type:
                 assert cpu, "inference not supported on CPU"
             if "cuda" in device.type:

ultralytics/utils/callbacks/comet.py

@@ -105,12 +105,7 @@ def _fetch_trainer_metadata(trainer):
     save_interval = curr_epoch % save_period == 0
     save_assets = save and save_period > 0 and save_interval and not final_epoch
 
-    return dict(
+    return dict(curr_epoch=curr_epoch, curr_step=curr_step, save_assets=save_assets, final_epoch=final_epoch)
-        curr_epoch=curr_epoch,
-        curr_step=curr_step,
-        save_assets=save_assets,
-        final_epoch=final_epoch,
-    )
 
 
 def _scale_bounding_box_to_original_image_shape(box, resized_image_shape, original_image_shape, ratio_pad):
@@ -218,11 +213,7 @@ def _log_confusion_matrix(experiment, trainer, curr_step, curr_epoch):
     conf_mat = trainer.validator.confusion_matrix.matrix
     names = list(trainer.data["names"].values()) + ["background"]
     experiment.log_confusion_matrix(
-        matrix=conf_mat,
+        matrix=conf_mat, labels=names, max_categories=len(names), epoch=curr_epoch, step=curr_step
-        labels=names,
-        max_categories=len(names),
-        epoch=curr_epoch,
-        step=curr_step,
     )
 
 
@@ -294,12 +285,7 @@ def _log_plots(experiment, trainer):
 def _log_model(experiment, trainer):
     """Log the best-trained model to Comet.ml."""
     model_name = _get_comet_model_name()
-    experiment.log_model(
+    experiment.log_model(model_name, file_or_folder=str(trainer.best), file_name="best.pt", overwrite=True)
-        model_name,
-        file_or_folder=str(trainer.best),
-        file_name="best.pt",
-        overwrite=True,
-    )
 
 
 def on_pretrain_routine_start(trainer):
@@ -320,11 +306,7 @@ def on_train_epoch_end(trainer):
     curr_epoch = metadata["curr_epoch"]
     curr_step = metadata["curr_step"]
 
-    experiment.log_metrics(
+    experiment.log_metrics(trainer.label_loss_items(trainer.tloss, prefix="train"), step=curr_step, epoch=curr_epoch)
-        trainer.label_loss_items(trainer.tloss, prefix="train"),
-        step=curr_step,
-        epoch=curr_epoch,
-    )
 
     if curr_epoch == 1:
         _log_images(experiment, trainer.save_dir.glob("train_batch*.jpg"), curr_step)

ultralytics/utils/loss.py

@@ -38,9 +38,7 @@ class VarifocalLoss(nn.Module):
 class FocalLoss(nn.Module):
     """Wraps focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5)."""
 
-    def __init__(
+    def __init__(self):
-        self,
-    ):
         """Initializer for FocalLoss class with no parameters."""
         super().__init__()