udpate

classify/predict.py

@@ -36,7 +36,7 @@
 
 import torch
 import torch.nn.functional as F
-from ultralytics.yolo.utils.checks import check_requirements, print_args, check_img_size, check_imshow
+from ultralytics.yolo.utils.checks import check_requirements, print_args, check_imgsz, check_imshow
 from ultralytics.yolo.utils.torch_utils import select_device, smart_inference_mode, strip_optimizer
 
 FILE = Path(__file__).resolve()
@@ -89,7 +89,7 @@ def run(
     device = select_device(device)
     model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
     stride, names, pt = model.stride, model.names, model.pt
-    imgsz = check_img_size(imgsz, s=stride)  # check image size
+    imgsz = check_imgsz(imgsz, s=stride)  # check image size
 
     # Dataloader
     bs = 1  # batch_size

classify/val.py

@@ -28,7 +28,7 @@
 import torch
 from tqdm import tqdm
 from ultralytics.yolo.utils.torch_utils import select_device, smart_inference_mode
-from ultralytics.yolo.utils.checks import check_img_size, check_requirements, print_args
+from ultralytics.yolo.utils.checks import check_imgsz, check_requirements, print_args
 from ultralytics.yolo.utils import colorstr
 
 FILE = Path(__file__).resolve()
@@ -77,7 +77,7 @@ def run(
         # Load model
         model = DetectMultiBackend(weights, device=device, dnn=dnn, fp16=half)
         stride, pt, jit, engine = model.stride, model.pt, model.jit, model.engine
-        imgsz = check_img_size(imgsz, s=stride)  # check image size
+        imgsz = check_imgsz(imgsz, s=stride)  # check image size
         half = model.fp16  # FP16 supported on limited backends with CUDA
         if engine:
             batch_size = model.batch_size

detect.py

@@ -36,7 +36,7 @@
 
 import torch
 from ultralyitcs.yolo.utils import colorstr
-from ultralytics.yolo.utils.checks import print_args, check_img_size, check_imshow, check_requirements
+from ultralytics.yolo.utils.checks import print_args, check_imgsz, check_imshow, check_requirements
 from ultralytics.yolo.utils.torch_utils import select_device, smart_inference_mode
 
 FILE = Path(__file__).resolve()
@@ -98,7 +98,7 @@ def run(
     device = select_device(device)
     model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
     stride, names, pt = model.stride, model.names, model.pt
-    imgsz = check_img_size(imgsz, s=stride)  # check image size
+    imgsz = check_imgsz(imgsz, s=stride)  # check image size
 
     # Dataloader
     bs = 1  # batch_size

export.py

@@ -62,7 +62,7 @@
 from ultralytics.nn.tasks import attempt_load_weights
 from ultralytics.yolo.utils.torch_utils import select_device, smart_inference_mode
 from ultraltics.yolo.utils import file_size, check_requirements, colorstr
-from ultralytics.yolo.utils.checks import print_args, check_img_size, check_version
+from ultralytics.yolo.utils.checks import print_args, check_imgsz, check_version
 
 FILE = Path(__file__).resolve()
 ROOT = FILE.parents[0]  # YOLOv5 root directory
@@ -698,7 +698,7 @@ def run(
 
     # Input
     gs = int(max(model.stride))  # grid size (max stride)
-    imgsz = [check_img_size(x, gs) for x in imgsz]  # verify img_size are gs-multiples
+    imgsz = [check_imgsz(x, gs) for x in imgsz]  # verify img_size are gs-multiples
     im = torch.zeros(batch_size, 3, *imgsz).to(device)  # image size(1,3,320,192) BCHW iDetection
 
     # Update model

models/common.py

@@ -24,10 +24,12 @@
 from PIL import Image
 from torch.cuda import amp
 from ultralytics.nn.tasks import attempt_load_weights
+from ultralytics.yolo.utils.checks import check_requirements, check_suffix, check_version
+from ultralytics.yolo.utils import colorstr
 
 from utils import TryExcept
 from utils.dataloaders import exif_transpose, letterbox
-from utils.general import (LOGGER, ROOT, Profile, check_requirements, check_suffix, check_version, colorstr,
+from utils.general import (LOGGER, ROOT, Profile,
                            increment_path, is_jupyter, make_divisible, non_max_suppression, scale_boxes, xywh2xyxy,
                            xyxy2xywh, yaml_load)
 from utils.plots import Annotator, colors, save_one_box

models/yolo.py

@@ -16,6 +16,7 @@
 
 from ultralytics.yolo.utils.checks import print_args
 from ultralytics.yolo.utils.torch_utils import select_device
+from ultralytics.yolo.utils.checks import check_version
 
 FILE = Path(__file__).resolve()
 ROOT = FILE.parents[1]  # YOLOv5 root directory
@@ -27,7 +28,7 @@
 from models.common import *
 from models.experimental import *
 from utils.autoanchor import check_anchor_order
-from utils.general import LOGGER, check_version, check_yaml, make_divisible
+from utils.general import LOGGER, check_yaml, make_divisible
 from utils.plots import feature_visualization
 from utils.torch_utils import fuse_conv_and_bn, initialize_weights, model_info, profile, scale_img, time_sync
 

segment/predict.py

@@ -36,7 +36,7 @@
 
 import torch
 from ultralytics.yolo.utils.torch_utils import select_device, smart_inference_mode, strip_optimizer
-from ultrlalytics.yolo.utils.checks import print_args,  check_img_size, check_imshow
+from ultrlalytics.yolo.utils.checks import print_args,  check_imgsz, check_imshow
 
 FILE = Path(__file__).resolve()
 ROOT = FILE.parents[1]  # YOLOv5 root directory
@@ -100,7 +100,7 @@ def run(
     device = select_device(device)
     model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
     stride, names, pt = model.stride, model.names, model.pt
-    imgsz = check_img_size(imgsz, s=stride)  # check image size
+    imgsz = check_imgsz(imgsz, s=stride)  # check image size
 
     # Dataloader
     bs = 1  # batch_size

segment/train.py

@@ -34,7 +34,7 @@
 from torch.optim import lr_scheduler
 from tqdm import tqdm
 from ultralytics.nn.tasks import attempt_load_weights
-from ultralytics.yolo.utils.checks import check_requirements, check_img_size
+from ultralytics.yolo.utils.checks import check_requirements, check_imgsz
 from ultralytics.yolo.utils.autobatch import check_train_batch_size
 from ultralytics.yolo.utils import  colorstr, increment_path
 from ultralytics.yolo.utils.torch_utils import strip_optimizer, de_parallel, torch_distributed_zero_first
@@ -133,7 +133,7 @@ def train(hyp, opt, device, callbacks):  # hyp is path/to/hyp.yaml or hyp dictio
 
     # Image size
     gs = max(int(model.stride.max()), 32)  # grid size (max stride)
-    imgsz = check_img_size(opt.imgsz, gs, floor=gs * 2)  # verify imgsz is gs-multiple
+    imgsz = check_imgsz(opt.imgsz, gs, floor=gs * 2)  # verify imgsz is gs-multiple
 
     # Batch size
     if RANK == -1 and batch_size == -1:  # single-GPU only, estimate best batch size

segment/val.py

@@ -39,7 +39,7 @@
 ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative
 
 import torch.nn.functional as F
-from ultralytis.yolo.utils.checks import check_requirements, print_args, check_img_size
+from ultralytis.yolo.utils.checks import check_requirements, print_args, check_imgsz
 from ultralytics.yolo.utils.torch_utils import de_parallel, select_device, smart_inference_mode
 
 from models.common import DetectMultiBackend
@@ -183,7 +183,7 @@ def run(
         # Load model
         model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
         stride, pt, jit, engine = model.stride, model.pt, model.jit, model.engine
-        imgsz = check_img_size(imgsz, s=stride)  # check image size
+        imgsz = check_imgsz(imgsz, s=stride)  # check image size
         half = model.fp16  # FP16 supported on limited backends with CUDA
         nm = de_parallel(model).model.model[-1].nm if isinstance(model, SegmentationModel) else 32  # number of masks
         if engine:

train.py

@@ -34,10 +34,11 @@
 from torch.optim import lr_scheduler
 from tqdm import tqdm
 from ultralytics.nn.tasks import attempt_load_weights
-from ultralytics.yolo.utils.checks import check_requirements, check_suffix, print_args, check_img_size
+from ultralytics.yolo.utils.checks import check_requirements, check_suffix, print_args, check_imgsz
 from ultralytics.yolo.utils.torch_utils import (EarlyStopping, ModelEMA, de_parallel, select_device, strip_optimizer,
                                                 torch_distributed_zero_first)
 from ultralytics.yolo.utils.autobatch import check_train_batch_size
+from ultralytics.yolo.utils import colorstr
 
 FILE = Path(__file__).resolve()
 ROOT = FILE.parents[0]  # YOLOv5 root directory
@@ -144,7 +145,7 @@ def train(hyp, opt, device, callbacks):  # hyp is path/to/hyp.yaml or hyp dictio
 
     # Image size
     gs = max(int(model.stride.max()), 32)  # grid size (max stride)
-    imgsz = check_img_size(opt.imgsz, gs, floor=gs * 2)  # verify imgsz is gs-multiple
+    imgsz = check_imgsz(opt.imgsz, gs, floor=gs * 2)  # verify imgsz is gs-multiple
 
     # Batch size
     if RANK == -1 and batch_size == -1:  # single-GPU only, estimate best batch size

utils/augmentations.py

@@ -11,8 +11,10 @@
 import torch
 import torchvision.transforms as T
 import torchvision.transforms.functional as TF
+from ultralytics.yolo.utils import colorstr
+from ultralytics.yolo.utils.checks import check_version 
 
-from utils.general import LOGGER, check_version, colorstr, resample_segments, segment2box, xywhn2xyxy
+from utils.general import LOGGER, resample_segments, segment2box, xywhn2xyxy
 from utils.metrics import bbox_ioa
 
 IMAGENET_MEAN = 0.485, 0.456, 0.406  # RGB mean

utils/general.py

@@ -35,7 +35,8 @@
 import torch
 import torchvision
 import yaml
-from ultralytics.yolo.utils.checks import check_requirements
+from ultralytics.yolo.utils.checks import check_requirements, check_version
+from ultralytics.yolo.utils import colorstr
 
 from utils import TryExcept, emojis
 from utils.downloads import curl_download, gsutil_getsize

val.py

@@ -29,7 +29,7 @@
 import numpy as np
 import torch
 from tqdm import tqdm
-from ultralytics.yolo.utils.checks import check_requirements, print_args, check_img_size
+from ultralytics.yolo.utils.checks import check_requirements, print_args, check_imgsz
 from ultralytics.yolo.utils.torch_utils import select_device, smart_inference_mode
 
 FILE = Path(__file__).resolve()
@@ -143,7 +143,7 @@ def run(
         # Load model
         model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
         stride, pt, jit, engine = model.stride, model.pt, model.jit, model.engine
-        imgsz = check_img_size(imgsz, s=stride)  # check image size
+        imgsz = check_imgsz(imgsz, s=stride)  # check image size
         half = model.fp16  # FP16 supported on limited backends with CUDA
         if engine:
             batch_size = model.batch_size