dgenerate-ultralytics-headless 8.3.181__py3-none-any.whl → 8.3.182__py3-none-any.whl

{dgenerate_ultralytics_headless-8.3.181.dist-info → dgenerate_ultralytics_headless-8.3.182.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dgenerate-ultralytics-headless
-Version: 8.3.181
+Version: 8.3.182
 Summary: Automatically built Ultralytics package with python-opencv-headless dependency instead of python-opencv
 Author-email: Glenn Jocher <glenn.jocher@ultralytics.com>, Jing Qiu <jing.qiu@ultralytics.com>
 Maintainer-email: Ultralytics <hello@ultralytics.com>

{dgenerate_ultralytics_headless-8.3.181.dist-info → dgenerate_ultralytics_headless-8.3.182.dist-info}/RECORD

@@ -1,4 +1,4 @@
-dgenerate_ultralytics_headless-8.3.181.dist-info/licenses/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
+dgenerate_ultralytics_headless-8.3.182.dist-info/licenses/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
 tests/__init__.py,sha256=b4KP5_q-2IO8Br8YHOSLYnn7IwZS81l_vfEF2YPa2lM,894
 tests/conftest.py,sha256=LXtQJcFNWPGuzauTGkiXgsvVC3llJKfg22WcmhRzuQc,2593
 tests/test_cli.py,sha256=EMf5gTAopOnIz8VvzaM-Qb044o7D0flnUHYQ-2ffOM4,5670
@@ -8,7 +8,8 @@ tests/test_exports.py,sha256=CY-4xVZlVM16vdyIC0mSR3Ix59aiZm1qjFGIhSNmB20,11007
 tests/test_integrations.py,sha256=kl_AKmE_Qs1GB0_91iVwbzNxofm_hFTt0zzU6JF-pg4,6323
 tests/test_python.py,sha256=-qvdeg-hEcKU5mWSDEU24iFZ-i8FAwQRznSXpkp6WQ4,27928
 tests/test_solutions.py,sha256=tuf6n_fsI8KvSdJrnc-cqP2qYdiYqCWuVrx0z9dOz3Q,13213
-ultralytics/__init__.py,sha256=OqBNN1EOKn4_vq1OWj-ax36skQmjTn4HuE7IOLGpaI0,730
+ultralytics/__init__.py,sha256=NmFp8Z3Rk0s1QZu4IuBv2wLLf-Pc5DLFdycD5Y49Keg,730
+ultralytics/py.typed,sha256=la67KBlbjXN-_-DfGNcdOcjYumVpKG_Tkw-8n5dnGB4,8
 ultralytics/assets/bus.jpg,sha256=wCAZxJecGR63Od3ZRERe9Aja1Weayrb9Ug751DS_vGM,137419
 ultralytics/assets/zidane.jpg,sha256=Ftc4aeMmen1O0A3o6GCDO9FlfBslLpTAw0gnetx7bts,50427
 ultralytics/cfg/__init__.py,sha256=Uj1br3-NVFvP6VY5CL4PK63mAQAom93XFC5cqSbM6t4,39887
@@ -151,13 +152,13 @@ ultralytics/models/sam/__init__.py,sha256=iR7B06rAEni21eptg8n4rLOP0Z_qV9y9PL-L93
 ultralytics/models/sam/amg.py,sha256=IpcuIfC5KBRiF4sdrsPl1ecWEJy75axo1yG23r5BFsw,11783
 ultralytics/models/sam/build.py,sha256=J6n-_QOYLa63jldEZmhRe9D3Is_AJE8xyZLUjzfRyTY,12629
 ultralytics/models/sam/model.py,sha256=j1TwsLmtxhiXyceU31VPzGVkjRXGylphKrdPSzUJRJc,7231
-ultralytics/models/sam/predict.py,sha256=awE_46I-GmYRIeDDLmGIdaYwJvPeSbw316DyanrA1Ys,86453
+ultralytics/models/sam/predict.py,sha256=R32JjExRBL5c2zBcDdauhX4UM8E8kMrBLoa0sZ9vk6I,86494
 ultralytics/models/sam/modules/__init__.py,sha256=lm6MckFYCPTbqIoX7w0s_daxdjNeBeKW6DXppv1-QUM,70
 ultralytics/models/sam/modules/blocks.py,sha256=lnMhnexvXejzhixWRQQyqjrpALoIhuOSwnSGW-c9kZk,46089
 ultralytics/models/sam/modules/decoders.py,sha256=U9jqFRkD0JmO3eugSmwLD0sQkiGqJJLympWNO83osGM,25638
 ultralytics/models/sam/modules/encoders.py,sha256=srtxrfy3SfUarkC41L1S8tY4GdFueUuR2qQDFZ6ZPl4,37362
 ultralytics/models/sam/modules/memory_attention.py,sha256=F1XJAxSwho2-LMlrao_ij0MoALTvhkK-OVghi0D4cU0,13651
-ultralytics/models/sam/modules/sam.py,sha256=ACI2wA-FiWwj5ctHMHJIi_ZMw4ujrBkHEaZ77X1De_Y,55649
+ultralytics/models/sam/modules/sam.py,sha256=CjM4M2PfRltQFnHFOp2G6QAdYk9BxWlurx82FSX_TYo,55760
 ultralytics/models/sam/modules/tiny_encoder.py,sha256=lmUIeZ9-3M-C3YmJBs13W6t__dzeJloOl0qFR9Ll8ew,42241
 ultralytics/models/sam/modules/transformer.py,sha256=xc2g6gb0jvr7cJkHkzIbZOGcTrmsOn2ojvuH-MVIMVs,14953
 ultralytics/models/sam/modules/utils.py,sha256=-PYSLExtBajbotBdLan9J07aFaeXJ03WzopAv4JcYd4,16022
@@ -250,7 +251,7 @@ ultralytics/utils/loss.py,sha256=fbOWc3Iu0QOJiWbi-mXWA9-1otTYlehtmUsI7os7ydM,397
 ultralytics/utils/metrics.py,sha256=tQjYxPd0dSzjucVyI1evIISunyYRkABXMXVQo64mAUE,68756
 ultralytics/utils/ops.py,sha256=8d60fbpntrexK3gPoLUS6mWAYGrtrQaQCOYyRJsCjuI,34521
 ultralytics/utils/patches.py,sha256=PPWiKzwGbCvuawLzDKVR8tWOQAlZbJBi8g_-A6eTCYA,6536
-ultralytics/utils/plotting.py,sha256=IEugKlTITLxArZjbSr7i_cTaHHAqNwVVk08Ak7I_ZdM,47169
+ultralytics/utils/plotting.py,sha256=4TG_J8rz9VVPrOXbdjRHPJZVgJrFYVmEYE0BcVDdolc,47745
 ultralytics/utils/tal.py,sha256=aXawOnhn8ni65tJWIW-PYqWr_TRvltbHBjrTo7o6lDQ,20924
 ultralytics/utils/torch_utils.py,sha256=D76Pvmw5OKh-vd4aJkOMO0dSLbM5WzGr7Hmds54hPEk,39233
 ultralytics/utils/triton.py,sha256=M7qe4RztiADBJQEWQKaIQsp94ERFJ_8_DUHDR6TXEOM,5410
@@ -266,8 +267,8 @@ ultralytics/utils/callbacks/neptune.py,sha256=j8pecmlcsM8FGzLKWoBw5xUsi5t8E5HuxY
 ultralytics/utils/callbacks/raytune.py,sha256=S6Bq16oQDQ8BQgnZzA0zJHGN_BBr8iAM_WtGoLiEcwg,1283
 ultralytics/utils/callbacks/tensorboard.py,sha256=MDPBW7aDes-66OE6YqKXXvqA_EocjzEMHWGM-8z9vUQ,5281
 ultralytics/utils/callbacks/wb.py,sha256=Tm_-aRr2CN32MJkY9tylpMBJkb007-MSRNSQ7rDJ5QU,7521
-dgenerate_ultralytics_headless-8.3.181.dist-info/METADATA,sha256=6a7UOAonIPqJS7OoY1QQ6pBR1hIhPk4Tu5Rb-RSlINU,38727
-dgenerate_ultralytics_headless-8.3.181.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dgenerate_ultralytics_headless-8.3.181.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
-dgenerate_ultralytics_headless-8.3.181.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
-dgenerate_ultralytics_headless-8.3.181.dist-info/RECORD,,
+dgenerate_ultralytics_headless-8.3.182.dist-info/METADATA,sha256=9mclDbKNmjy6iHAfrNiWQ6ub-pJajkvFPmjeHl25Ios,38727
+dgenerate_ultralytics_headless-8.3.182.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dgenerate_ultralytics_headless-8.3.182.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
+dgenerate_ultralytics_headless-8.3.182.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
+dgenerate_ultralytics_headless-8.3.182.dist-info/RECORD,,

ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "8.3.181"
+__version__ = "8.3.182"
 
 import os
 

ultralytics/models/sam/modules/sam.py

@@ -1032,3 +1032,4 @@ class SAM2Model(torch.nn.Module):
         self.image_size = imgsz[0]
         self.sam_prompt_encoder.input_image_size = imgsz
         self.sam_prompt_encoder.image_embedding_size = [x // 16 for x in imgsz]  # fixed ViT patch size of 16
+        self.sam_image_embedding_size = self.image_size // self.backbone_stride  # update image embedding size

ultralytics/models/sam/predict.py

@@ -1283,6 +1283,7 @@ class SAM2VideoPredictor(SAM2Predictor):
             - If `batch` is greater than 1, the features are expanded to fit the batch size.
             - The method leverages the model's `_prepare_backbone_features` method to prepare the backbone features.
         """
+        self.model.set_imgsz(self.imgsz)
         backbone_out = self.model.forward_image(im)
         if batch > 1:  # expand features if there's more than one prompt
             for i, feat in enumerate(backbone_out["backbone_fpn"]):

ultralytics/py.typed

@@ -0,0 +1 @@
+partial

ultralytics/utils/plotting.py

@@ -361,38 +361,46 @@ class Annotator:
                     lineType=cv2.LINE_AA,
                 )
 
-    def masks(self, masks, colors, im_gpu, alpha: float = 0.5, retina_masks: bool = False):
+    def masks(self, masks, colors, im_gpu: torch.Tensor = None, alpha: float = 0.5, retina_masks: bool = False):
         """
         Plot masks on image.
 
         Args:
-            masks (torch.Tensor): Predicted masks on cuda, shape: [n, h, w]
+            masks (torch.Tensor | np.ndarray): Predicted masks with shape: [n, h, w]
             colors (List[List[int]]): Colors for predicted masks, [[r, g, b] * n]
-            im_gpu (torch.Tensor): Image is in cuda, shape: [3, h, w], range: [0, 1]
+            im_gpu (torch.Tensor | None): Image is in cuda, shape: [3, h, w], range: [0, 1]
             alpha (float, optional): Mask transparency: 0.0 fully transparent, 1.0 opaque.
             retina_masks (bool, optional): Whether to use high resolution masks or not.
         """
         if self.pil:
             # Convert to numpy first
             self.im = np.asarray(self.im).copy()
-        if len(masks) == 0:
-            self.im[:] = im_gpu.permute(1, 2, 0).contiguous().cpu().numpy() * 255
-        if im_gpu.device != masks.device:
-            im_gpu = im_gpu.to(masks.device)
-        colors = torch.tensor(colors, device=masks.device, dtype=torch.float32) / 255.0  # shape(n,3)
-        colors = colors[:, None, None]  # shape(n,1,1,3)
-        masks = masks.unsqueeze(3)  # shape(n,h,w,1)
-        masks_color = masks * (colors * alpha)  # shape(n,h,w,3)
-
-        inv_alpha_masks = (1 - masks * alpha).cumprod(0)  # shape(n,h,w,1)
-        mcs = masks_color.max(dim=0).values  # shape(n,h,w,3)
-
-        im_gpu = im_gpu.flip(dims=[0])  # flip channel
-        im_gpu = im_gpu.permute(1, 2, 0).contiguous()  # shape(h,w,3)
-        im_gpu = im_gpu * inv_alpha_masks[-1] + mcs
-        im_mask = im_gpu * 255
-        im_mask_np = im_mask.byte().cpu().numpy()
-        self.im[:] = im_mask_np if retina_masks else ops.scale_image(im_mask_np, self.im.shape)
+        if im_gpu is None:
+            assert isinstance(masks, np.ndarray), "`masks` must be a np.ndarray if `im_gpu` is not provided."
+            overlay = self.im.copy()
+            for i, mask in enumerate(masks):
+                overlay[mask.astype(bool)] = colors[i]
+            self.im = cv2.addWeighted(self.im, 1 - alpha, overlay, alpha, 0)
+        else:
+            assert isinstance(masks, torch.Tensor), "`masks` must be a torch.Tensor if `im_gpu` is provided."
+            if len(masks) == 0:
+                self.im[:] = im_gpu.permute(1, 2, 0).contiguous().cpu().numpy() * 255
+            if im_gpu.device != masks.device:
+                im_gpu = im_gpu.to(masks.device)
+            colors = torch.tensor(colors, device=masks.device, dtype=torch.float32) / 255.0  # shape(n,3)
+            colors = colors[:, None, None]  # shape(n,1,1,3)
+            masks = masks.unsqueeze(3)  # shape(n,h,w,1)
+            masks_color = masks * (colors * alpha)  # shape(n,h,w,3)
+
+            inv_alpha_masks = (1 - masks * alpha).cumprod(0)  # shape(n,h,w,1)
+            mcs = masks_color.max(dim=0).values  # shape(n,h,w,3)
+
+            im_gpu = im_gpu.flip(dims=[0])  # flip channel
+            im_gpu = im_gpu.permute(1, 2, 0).contiguous()  # shape(h,w,3)
+            im_gpu = im_gpu * inv_alpha_masks[-1] + mcs
+            im_mask = im_gpu * 255
+            im_mask_np = im_mask.byte().cpu().numpy()
+            self.im[:] = im_mask_np if retina_masks else ops.scale_image(im_mask_np, self.im.shape)
         if self.pil:
             # Convert im back to PIL and update draw
             self.fromarray(self.im)