Override fixes and general updates (#129)

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Kalen Michael <kalenmike@gmail.com>

ultralytics/yolo/configs/default.yaml

@@ -1,11 +1,11 @@
 # YOLO 🚀 by Ultralytics, GPL-3.0 license
 # Default training settings and hyperparameters for medium-augmentation COCO training
 
-task: "classify" # choices=['detect', 'segment', 'classify', 'init'] # init is a special case. Specify task to run.
+task: "detect" # choices=['detect', 'segment', 'classify', 'init'] # init is a special case. Specify task to run.
 mode: "train" # choices=['train', 'val', 'predict'] # mode to run task in.
 
 # Train settings -------------------------------------------------------------------------------------------------------
-model: null # i.e. yolov5s.pt, yolo.yaml. Path to model file
+model: null # i.e. yolov8n.pt, yolov8n.yaml. Path to model file
 data: null # i.e. coco128.yaml. Path to data file
 epochs: 100 # number of epochs to train for
 patience: 50  # TODO: epochs to wait for no observable improvement for early stopping of training

ultralytics/yolo/engine/exporter.py

@@ -137,8 +137,6 @@ class Exporter:
         """
         if overrides is None:
             overrides = {}
-        if 'batch_size' not in overrides:
-            overrides['batch_size'] = 1  # set default export batch size
         self.args = get_config(config, overrides)
         project = self.args.project or f"runs/{self.args.task}"
         name = self.args.name or "exp"  # hardcode mode as export doesn't require it
@@ -166,6 +164,8 @@ class Exporter:
             assert not self.args.dynamic, '--half not compatible with --dynamic, i.e. use either --half or --dynamic'
 
         # Checks
+        if self.args.batch_size == 16:
+            self.args.batch_size = 1  # TODO: resolve batch_size 16 default in config.yaml
         self.imgsz = check_imgsz(self.args.imgsz, stride=model.stride, min_dim=2)  # check image size
         if self.args.optimize:
             assert self.device.type == 'cpu', '--optimize not compatible with cuda devices, i.e. use --device cpu'

ultralytics/yolo/engine/model.py

@@ -1,6 +1,7 @@
-import torch
 from pathlib import Path
 
+import torch
+
 from ultralytics import yolo  # noqa
 from ultralytics.nn.tasks import ClassificationModel, DetectionModel, SegmentationModel, attempt_load_weights
 from ultralytics.yolo.configs import get_config

ultralytics/yolo/engine/trainer.py

@@ -107,6 +107,8 @@ class BaseTrainer:
         self.device = utils.torch_utils.select_device(self.args.device, self.batch_size)
         self.amp = self.device.type != 'cpu'
         self.scaler = amp.GradScaler(enabled=self.amp)
+        if self.device.type == 'cpu':
+            self.args.workers = 0  # faster CPU training as time dominated by inference, not dataloading
 
         # Model and Dataloaders.
         self.model = self.args.model

ultralytics/yolo/utils/__init__.py

@@ -6,6 +6,7 @@ import platform
 import sys
 import tempfile
 import threading
+import uuid
 from pathlib import Path
 
 import cv2
@@ -160,7 +161,7 @@ def get_user_config_dir(sub_dir='Ultralytics'):
         raise ValueError(f'Unsupported operating system: {os_name}')
 
     # GCP and AWS lambda fix, only /tmp is writeable
-    if not is_dir_writeable(path.parent):
+    if not is_dir_writeable(str(path.parent)):
         path = Path('/tmp') / sub_dir
 
     # Create the subdirectory if it does not exist
@@ -172,9 +173,9 @@ def get_user_config_dir(sub_dir='Ultralytics'):
 USER_CONFIG_DIR = get_user_config_dir()  # Ultralytics settings dir
 
 
-def emojis(str=''):
+def emojis(string=''):
     # Return platform-dependent emoji-safe version of string
-    return str.encode().decode('ascii', 'ignore') if platform.system() == 'Windows' else str
+    return string.encode().decode('ascii', 'ignore') if platform.system() == 'Windows' else string
 
 
 def colorstr(*input):
@@ -282,27 +283,39 @@ def yaml_load(file='data.yaml'):
     """
     with open(file, errors='ignore') as f:
         # Add YAML filename to dict and return
-        return {**yaml.safe_load(f), 'yaml_file': file}
+        return {**yaml.safe_load(f), 'yaml_file': str(file)}
 
 
 def get_settings(file=USER_CONFIG_DIR / 'settings.yaml'):
     """
-    Function that loads a global settings YAML, or creates it and populates it with default values if it does not exist.
+    Loads a global settings YAML file or creates one with default values if it does not exist.
 
-    If the datasets or weights directories are set to None, the current working directory will be used.
-    The 'sync' setting determines whether analytics will be synced to help with YOLO development.
+    Args:
+        file (Path): Path to the settings YAML file. Defaults to 'settings.yaml' in the USER_CONFIG_DIR.
+
+    Returns:
+        dict: Dictionary of settings key-value pairs.
     """
     from ultralytics.yolo.utils.torch_utils import torch_distributed_zero_first
 
+    defaults = {
+        'datasets_dir': None,  # default datasets directory. If None, current working directory is used.
+        'weights_dir': None,  # default weights directory. If None, current working directory is used.
+        'runs_dir': None,  # default runs directory. If None, current working directory is used.
+        'sync': True,  # sync analytics to help with YOLO development
+        'uuid': uuid.getnode(),  # device UUID to align analytics
+        'yaml_file': str(file)}  # setting YAML file path
+
     with torch_distributed_zero_first(RANK):
         if not file.exists():
-            settings = {
-                'datasets_dir': None,  # default datasets directory. If None, current working directory is used.
-                'weights_dir': None,  # default weights directory. If None, current working directory is used.
-                'sync': True}  # sync analytics to help with YOLO development
-            yaml_save(file, settings)
+            yaml_save(file, defaults)
 
-    return yaml_load(file)
+        settings = yaml_load(file)
+        if settings.keys() != defaults.keys():
+            settings = {**defaults, **settings}  # merge **defaults with **settings (prefer **settings)
+            yaml_save(file, settings)  # save updated defaults
+
+        return settings
 
 
 # Run below code on utils init -----------------------------------------------------------------------------------------

ultralytics/yolo/utils/callbacks/hub.py

@@ -48,7 +48,7 @@ def on_train_end(trainer):
         # Upload final model and metrics with exponential standoff
         LOGGER.info(f"{PREFIX}Training completed successfully ✅\n"
                     f"{PREFIX}Uploading final {session.model_id}")
-        session.upload_model(trainer.epoch, trainer.best, map=trainer.metrics['metrics/mAP50(B)'], final=True)
+        session.upload_model(trainer.epoch, trainer.best, map=trainer.metrics['metrics/mAP50-95(B)'], final=True)
         session.alive = False  # stop heartbeats
         LOGGER.info(f"{PREFIX}View model at https://hub.ultralytics.com/models/{session.model_id} 🚀")
 

ultralytics/yolo/utils/torch_utils.py

@@ -201,7 +201,7 @@ def copy_attr(a, b, include=(), exclude=()):
             setattr(a, k, v)
 
 
-def intersect_state_dicts(da, db, exclude=()):
+def intersect_dicts(da, db, exclude=()):
     # Dictionary intersection of matching keys and shapes, omitting 'exclude' keys, using da values
     return {k: v for k, v in da.items() if k in db and all(x not in k for x in exclude) and v.shape == db[k].shape}