Add AutoBatch from YOLOv5 (#145)

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

ultralytics/yolo/engine/trainer.py

@@ -27,6 +27,7 @@ from ultralytics.yolo.configs import get_config
 from ultralytics.yolo.data.utils import check_dataset, check_dataset_yaml
 from ultralytics.yolo.utils import (DEFAULT_CONFIG, LOGGER, RANK, SETTINGS, TQDM_BAR_FORMAT, callbacks, colorstr,
                                     yaml_save)
+from ultralytics.yolo.utils.autobatch import check_train_batch_size
 from ultralytics.yolo.utils.checks import check_file, print_args
 from ultralytics.yolo.utils.dist import ddp_cleanup, generate_ddp_command
 from ultralytics.yolo.utils.files import get_latest_run, increment_path
@@ -135,7 +136,7 @@ class BaseTrainer:
         self.fitness = None
         self.loss = None
         self.tloss = None
-        self.loss_names = None
+        self.loss_names = ['Loss']
         self.csv = self.save_dir / 'results.csv'
         self.plot_idx = [0, 1, 2]
 
@@ -192,6 +193,15 @@ class BaseTrainer:
         self.set_model_attributes()
         if world_size > 1:
             self.model = DDP(self.model, device_ids=[rank])
+
+        # Batch size
+        if self.batch_size == -1:
+            if RANK == -1:  # single-GPU only, estimate best batch size
+                self.batch_size = check_train_batch_size(self.model, self.args.imgsz, self.amp)
+            else:
+                SyntaxError('batch=-1 to use AutoBatch is only available in Single-GPU training. '
+                            'Please pass a valid batch size value for Multi-GPU DDP training, i.e. batch=16')
+
         # Optimizer
         self.accumulate = max(round(self.args.nbs / self.batch_size), 1)  # accumulate loss before optimizing
         self.args.weight_decay *= self.batch_size * self.accumulate / self.args.nbs  # scale weight_decay

ultralytics/yolo/engine/validator.py

@@ -78,7 +78,7 @@ class BaseValidator:
             self.device = trainer.device
             self.data = trainer.data
             model = trainer.ema.ema or trainer.model
-            self.args.half &= self.device.type != 'cpu'
+            self.args.half = self.device.type != 'cpu'  # force FP16 val during training
             model = model.half() if self.args.half else model.float()
             self.model = model
             self.loss = torch.zeros_like(trainer.loss_items, device=trainer.device)