standalone val (#56)

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

ultralytics/yolo/utils/configs/default.yaml

@@ -28,17 +28,22 @@ single_cls: False  # train multi-class data as single-class
 image_weights: False  # use weighted image selection for training
 rect: False  # support rectangular training
 cos_lr: False # Use cosine LR scheduler
-overlap_mask: True  # Segmentation masks overlap
-mask_ratio: 4  # Segmentation mask downsample ratio
-noval: False
+# Segmentation
+overlap_mask: True  # masks overlap
+mask_ratio: 4  # mask downsample ratio
+# Classification
+dropout: False # use dropout
+
 
 # Val/Test settings ----------------------------------------------------------------------------------------------------
+noval: False
 save_json: False
 save_hybrid: False
 conf_thres: 0.001
 iou_thres: 0.6
 max_det: 300
 half: True
+dnn: False # use OpenCV DNN for ONNX inference
 plots: False
 save_txt: False
 

ultralytics/yolo/utils/modeling/__init__.py

@@ -113,8 +113,8 @@ def get_model(model='s.pt', pretrained=True):
         model = model.split(".")[0]
 
     if Path(f"{model}.pt").is_file():  # local file
-        return torch.load(f"{model}.pt", map_location='cpu')
+        return attempt_load_weights(f"{model}.pt", device='cpu')
     elif model in torchvision.models.__dict__:  # TorchVision models i.e. resnet50, efficientnet_b0
         return torchvision.models.__dict__[model](weights='IMAGENET1K_V1' if pretrained else None)
     else:  # Ultralytics assets
-        return torch.load(attempt_download(f"{model}.pt"), map_location='cpu')
+        return attempt_load_weights(f"{model}.pt", device='cpu')

ultralytics/yolo/utils/modeling/autobackend.py

@@ -304,7 +304,7 @@ class AutoBackend(nn.Module):
     def _model_type(p='path/to/model.pt'):
         # Return model type from model path, i.e. path='path/to/model.onnx' -> type=onnx
         # types = [pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, paddle]
-        from export import export_formats
+        from ultralytics.yolo.engine.exporter import export_formats
         sf = list(export_formats().Suffix)  # export suffixes
         if not is_url(p, check=False):
             check_suffix(p, sf)  # checks

ultralytics/yolo/utils/modeling/tasks.py

@@ -172,7 +172,7 @@ class DetectionModel(BaseModel):
         csd = weights['model'].float().state_dict()  # checkpoint state_dict as FP32
         csd = intersect_state_dicts(csd, self.state_dict())  # intersect
         self.load_state_dict(csd, strict=False)  # load
-        LOGGER.info(f'Transferred {len(csd)}/{len(self.model.state_dict())} items from {weights}')
+        LOGGER.info(f'Transferred {len(csd)}/{len(self.model.state_dict())} items from pretrained weights')
 
 
 class SegmentationModel(DetectionModel):

ultralytics/yolo/utils/torch_utils.py

@@ -164,6 +164,25 @@ def scale_img(img, ratio=1.0, same_shape=False, gs=32):  # img(16,3,256,416)
     return F.pad(img, [0, w - s[1], 0, h - s[0]], value=0.447)  # value = imagenet mean
 
 
+def check_img_size(imgsz, s=32, floor=0):
+    # Verify image size is a multiple of stride s in each dimension
+    if isinstance(imgsz, int):  # integer i.e. img_size=640
+        new_size = max(make_divisible(imgsz, int(s)), floor)
+    else:  # list i.e. img_size=[640, 480]
+        imgsz = list(imgsz)  # convert to list if tuple
+        new_size = [max(make_divisible(x, int(s)), floor) for x in imgsz]
+    if new_size != imgsz:
+        LOGGER.warning(f'WARNING ⚠️ --img-size {imgsz} must be multiple of max stride {s}, updating to {new_size}')
+    return new_size
+
+
+def make_divisible(x, divisor):
+    # Returns nearest x divisible by divisor
+    if isinstance(divisor, torch.Tensor):
+        divisor = int(divisor.max())  # to int
+    return math.ceil(x / divisor) * divisor
+
+
 def copy_attr(a, b, include=(), exclude=()):
     # Copy attributes from b to a, options to only include [...] and to exclude [...]
     for k, v in b.__dict__.items():