remove ultralytics dependency

requirements.txt

@@ -12,10 +12,9 @@ PyYAML>=5.3.1
 requests>=2.23.0
 scipy>=1.4.1
 thop>=0.1.1  # FLOPs computation
-torch>=1.7.0  # see https://pytorch.org/get-started/locally (recommended)
-torchvision>=0.8.1
+torch>=2.0.0  # see https://pytorch.org/get-started/locally (recommended)
+torchvision>=0.15.0
 tqdm>=4.64.0
-ultralytics>=8.0.100
 # protobuf<=3.20.1  # https://github.com/ultralytics/yolov5/issues/8012
 
 # Logging ---------------------------------------------------------------------
@@ -50,7 +49,7 @@ setuptools>=65.5.1 # Snyk vulnerability fix
 
 
 # CLI
-fire
+fire==0.6.0
 # AWS
 boto3>=1.19.1
 # coco to yolov5 conversion

yolov5/hubconf.py

@@ -62,7 +62,7 @@ def _create(name, pretrained=True, channels=3, classes=80, autoshape=True, verbo
             cfg = list((Path(__file__).parent / 'models').rglob(f'{path.stem}.yaml'))[0]  # model.yaml path
             model = DetectionModel(cfg, channels, classes)  # create model
             if pretrained:
-                ckpt = torch.load(attempt_download(path), map_location=device)  # load
+                ckpt = torch.load(attempt_download(path), weights_only=False, map_location=device)  # load
                 csd = ckpt['model'].float().state_dict()  # checkpoint state_dict as FP32
                 csd = intersect_dicts(csd, model.state_dict(), exclude=['anchors'])  # intersect
                 model.load_state_dict(csd, strict=False)  # load

yolov5/models/experimental.py

@@ -76,7 +76,7 @@ def attempt_load(weights, device=None, inplace=True, fuse=True):
 
     model = Ensemble()
     for w in weights if isinstance(weights, list) else [weights]:
-        ckpt = torch.load(attempt_download(w), map_location='cpu')  # load
+        ckpt = torch.load(attempt_download(w), weights_only=False, map_location='cpu')  # load
         ckpt = (ckpt.get('ema') or ckpt['model']).to(device).float()  # FP32 model
 
         # Model compatibility updates

yolov5/segment/train.py

@@ -118,7 +118,7 @@ def train(hyp, opt, device, callbacks):  # hyp is path/to/hyp.yaml or hyp dictio
     if pretrained:
         with torch_distributed_zero_first(LOCAL_RANK):
             weights = attempt_download(weights)  # download if not found locally
-        ckpt = torch.load(weights, map_location='cpu')  # load checkpoint to CPU to avoid CUDA memory leak
+        ckpt = torch.load(weights, weights_only=False, map_location='cpu')  # load checkpoint to CPU to avoid CUDA memory leak
         model = SegmentationModel(cfg or ckpt['model'].yaml, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device)
         exclude = ['anchor'] if (cfg or hyp.get('anchors')) and not resume else []  # exclude keys
         csd = ckpt['model'].float().state_dict()  # checkpoint state_dict as FP32
@@ -544,7 +544,7 @@ def main(opt, callbacks=Callbacks()):
             with open(opt_yaml, errors='ignore') as f:
                 d = yaml.safe_load(f)
         else:
-            d = torch.load(last, map_location='cpu')['opt']
+            d = torch.load(last, weights_only=False, map_location='cpu')['opt']
         opt = argparse.Namespace(**d)  # replace
         opt.cfg, opt.weights, opt.resume = '', str(last), True  # reinstate
         if is_url(opt_data):

yolov5/train.py

@@ -137,7 +137,7 @@ def train(hyp, opt, device, callbacks):  # hyp is path/to/hyp.yaml or hyp dictio
     if pretrained:
         with torch_distributed_zero_first(LOCAL_RANK):
             weights = attempt_download(weights)  # download if not found locally
-        ckpt = torch.load(weights, map_location='cpu')  # load checkpoint to CPU to avoid CUDA memory leak
+        ckpt = torch.load(weights, weights_only=False, map_location='cpu')  # load checkpoint to CPU to avoid CUDA memory leak
         model = Model(cfg or ckpt['model'].yaml, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device)  # create
         exclude = ['anchor'] if (cfg or hyp.get('anchors')) and not resume else []  # exclude keys
         csd = ckpt['model'].float().state_dict()  # checkpoint state_dict as FP32
@@ -578,7 +578,7 @@ def main(opt, callbacks=Callbacks()):
             with open(opt_yaml, errors='ignore') as f:
                 d = yaml.safe_load(f)
         else:
-            d = torch.load(last, map_location='cpu')['opt']
+            d = torch.load(last, weights_only=False, map_location='cpu')['opt']
         if opt.neptune_resume_id is not None:
             d["neptune_resume_id"] = opt.neptune_resume_id
         opt = argparse.Namespace(**d)  # replace