update dds-cloudapi-sdk to 0.3.3

README.md

@@ -21,7 +21,7 @@ Grounded SAM 2 does not introduce significant methodological changes compared to
 
 ## Latest updates
 
-- `2024/12/02`: Support **DINO-X SAM 2 Demos** (including object segmentation and tracking), please install the latest version of `dds-cloudapi-sdk` and refer to [Grounded SAM 2 (with DINO-X)](#grounded-sam-2-image-demo-with-dino-x) and [Grounded SAM 2 Video (with DINO-X)](#grounded-sam-2-video-object-tracking-demo-with-custom-video-input-with-dino-x) for more details.
+- `2024/12/02`: Support **DINO-X with SAM 2** demos (including object segmentation and tracking), please install the latest version of `dds-cloudapi-sdk==0.3.3` and refer to [Grounded SAM 2 (with DINO-X)](#grounded-sam-2-image-demo-with-dino-x) and [Grounded SAM 2 Video (with DINO-X)](#grounded-sam-2-video-object-tracking-demo-with-custom-video-input-with-dino-x) for more details.
 - `2024/10/24`: Support [SAHI (Slicing Aided Hyper Inference)](https://docs.ultralytics.com/guides/sahi-tiled-inference/) on Grounded SAM 2 (with Grounding DINO 1.5) which may be helpful for inferencing high resolution image with dense small objects (e.g. **4K** images).
 - `2024/10/10`: Support `SAM-2.1` models, if you want to use `SAM 2.1` model, you need to update to the latest code and reinstall SAM 2 follow [SAM 2.1 Installation](https://github.com/facebookresearch/sam2?tab=readme-ov-file#latest-updates).
 - `2024/08/31`: Support `dump json results` in Grounded SAM 2 Image Demos (with Grounding DINO).

grounded_sam2_dinox_demo.py

@@ -2,6 +2,7 @@
 from dds_cloudapi_sdk import Config
 from dds_cloudapi_sdk import Client
 from dds_cloudapi_sdk.tasks.dinox import DinoxTask
+from dds_cloudapi_sdk.tasks.types import DetectionTarget
 from dds_cloudapi_sdk import TextPrompt
 
 import os
@@ -64,7 +65,9 @@ if WITH_SLICE_INFERENCE:
         image_url = client.upload_file(temp_filename)
         task = DinoxTask(
             image_url=image_url,
-            prompts=[TextPrompt(text=TEXT_PROMPT)]
+            prompts=[TextPrompt(text=TEXT_PROMPT)],
+            bbox_threshold=0.25,
+            targets=[DetectionTarget.BBox],
         )
         client.run_task(task)
         result = task.result
@@ -103,7 +106,9 @@ else:
 
     task = DinoxTask(
         image_url=image_url,
-        prompts=[TextPrompt(text=TEXT_PROMPT)]
+        prompts=[TextPrompt(text=TEXT_PROMPT)],
+        bbox_threshold=0.25,
+        targets=[DetectionTarget.BBox],
     )
 
     client.run_task(task)

grounded_sam2_tracking_demo_custom_video_input_dinox.py

@@ -2,6 +2,7 @@
 from dds_cloudapi_sdk import Config
 from dds_cloudapi_sdk import Client
 from dds_cloudapi_sdk.tasks.dinox import DinoxTask
+from dds_cloudapi_sdk.tasks.types import DetectionTarget
 from dds_cloudapi_sdk import TextPrompt
 
 import os
@@ -26,7 +27,7 @@ TEXT_PROMPT = "hippopotamus."
 OUTPUT_VIDEO_PATH = "./hippopotamus_tracking_demo.mp4"
 SOURCE_VIDEO_FRAME_DIR = "./custom_video_frames"
 SAVE_TRACKING_RESULTS_DIR = "./tracking_results"
-API_TOKEN_FOR_GD1_5 = "Your API token"
+API_TOKEN_FOR_DINOX = "Your API token"
 PROMPT_TYPE_FOR_VIDEO = "box" # choose from ["point", "box", "mask"]
 BOX_THRESHOLD = 0.2
 
@@ -92,7 +93,7 @@ img_path = os.path.join(SOURCE_VIDEO_FRAME_DIR, frame_names[ann_frame_idx])
 image = Image.open(img_path)
 
 # Step 1: initialize the config
-config = Config(API_TOKEN_FOR_GD1_5)
+config = Config(API_TOKEN_FOR_DINOX)
 
 # Step 2: initialize the client
 client = Client(config)
@@ -104,7 +105,9 @@ image_url = client.upload_file(img_path)
 
 task = DinoxTask(
     image_url=image_url,
-    prompts=[TextPrompt(text=TEXT_PROMPT)]
+    prompts=[TextPrompt(text=TEXT_PROMPT)],
+    bbox_threshold=0.25,
+    targets=[DetectionTarget.BBox],
 )
 
 client.run_task(task)