dgenerate-ultralytics-headless 8.3.181__tar.gz → 8.3.182__tar.gz

{dgenerate_ultralytics_headless-8.3.181 → dgenerate_ultralytics_headless-8.3.182}/PKG-INFO

@@ -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 → dgenerate_ultralytics_headless-8.3.182}/dgenerate_ultralytics_headless.egg-info/PKG-INFO

@@ -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 → dgenerate_ultralytics_headless-8.3.182}/dgenerate_ultralytics_headless.egg-info/SOURCES.txt

@@ -15,6 +15,7 @@ tests/test_integrations.py
 tests/test_python.py
 tests/test_solutions.py
 ultralytics/__init__.py
+ultralytics/py.typed
 ultralytics/../tests/__init__.py
 ultralytics/../tests/conftest.py
 ultralytics/../tests/test_cli.py

{dgenerate_ultralytics_headless-8.3.181 → dgenerate_ultralytics_headless-8.3.182}/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
 

{dgenerate_ultralytics_headless-8.3.181 → dgenerate_ultralytics_headless-8.3.182}/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

{dgenerate_ultralytics_headless-8.3.181 → dgenerate_ultralytics_headless-8.3.182}/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"]):

dgenerate_ultralytics_headless-8.3.182/ultralytics/py.typed

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

{dgenerate_ultralytics_headless-8.3.181 → dgenerate_ultralytics_headless-8.3.182}/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)