Import YOLOv5 dataloader (#94)

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

ultralytics/yolo/v8/detect/train.py

@@ -4,7 +4,9 @@ import torch.nn as nn
 
 from ultralytics.yolo import v8
 from ultralytics.yolo.data import build_dataloader
+from ultralytics.yolo.data.dataloaders.v5loader import create_dataloader
 from ultralytics.yolo.engine.trainer import DEFAULT_CONFIG, BaseTrainer
+from ultralytics.yolo.utils import colorstr
 from ultralytics.yolo.utils.loss import BboxLoss
 from ultralytics.yolo.utils.metrics import smooth_BCE
 from ultralytics.yolo.utils.modeling.tasks import DetectionModel
@@ -21,7 +23,22 @@ class DetectionTrainer(BaseTrainer):
         # TODO: manage splits differently
         # calculate stride - check if model is initialized
         gs = max(int(de_parallel(self.model).stride.max() if self.model else 0), 32)
-        return build_dataloader(self.args, batch_size, img_path=dataset_path, stride=gs, rank=rank, mode=mode)[0]
+        return create_dataloader(path=dataset_path,
+                                 imgsz=self.args.imgsz,
+                                 batch_size=batch_size,
+                                 stride=gs,
+                                 hyp=dict(self.args),
+                                 augment=mode == "train",
+                                 cache=self.args.cache,
+                                 pad=0 if mode == "train" else 0.5,
+                                 rect=self.args.rect,
+                                 rank=rank,
+                                 workers=self.args.workers,
+                                 close_mosaic=self.args.close_mosaic != 0,
+                                 prefix=colorstr(f'{mode}: '),
+                                 shuffle=mode == "train",
+                                 seed=self.args.seed)[0] if self.args.v5loader else \
+            build_dataloader(self.args, batch_size, img_path=dataset_path, stride=gs, rank=rank, mode=mode)[0]
 
     def preprocess_batch(self, batch):
         batch["img"] = batch["img"].to(self.device, non_blocking=True).float() / 255

ultralytics/yolo/v8/models/yolov8m.yaml

@@ -0,0 +1,42 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.67  # model depth multiple
+width_multiple: 0.75  # layer channel multiple
+
+# YOLOv8.0m backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 3, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C2f, [128, True]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C2f, [256, True]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 6, C2f, [512, True]],
+   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
+   [-1, 3, C2f, [768, True]],
+   [-1, 1, SPPF, [768, 5]],  # 9
+  ]
+
+# YOLOv8.0m head
+head:
+  [[-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C2f, [512]],  # 13
+
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C2f, [256]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 12], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C2f, [512]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 9], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C2f, [768]],  # 23 (P5/32-large)
+
+   [[15, 18, 21], 1, Detect, [nc]],  # Detect(P3, P4, P5)
+  ]

ultralytics/yolo/v8/models/yolov8s.yaml

@@ -0,0 +1,42 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.50  # layer channel multiple
+
+# YOLOv8.0s backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 3, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C2f, [128, True]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C2f, [256, True]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 6, C2f, [512, True]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C2f, [1024, True]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv8.0s head
+head:
+  [[-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C2f, [512]],  # 13
+
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C2f, [256]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 12], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C2f, [512]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 9], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C2f, [1024]],  # 23 (P5/32-large)
+
+   [[15, 18, 21], 1, Detect, [nc]],  # Detect(P3, P4, P5)
+  ]