update DINO-X api usage to dds v2

README.md

@@ -20,6 +20,7 @@ In this repo, we've supported the following demo with **simple implementations**
 Grounded SAM 2 does not introduce significant methodological changes compared to [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://arxiv.org/abs/2401.14159). Both approaches leverage the capabilities of open-world models to address complex visual tasks. Consequently, we try to **simplify the code implementation** in this repository, aiming to enhance user convenience.
 
 ## Latest updates
+- **2025.04.20**: Update to `dds-cloudapi-sdk` API V2 version. The V1 version in the original API for `Grounding DINO 1.5` and `DINO-X` has been deprecated, please update to the latest `dds-cloudapi-sdk` by `pip install dds-cloudapi-sdk -U` to use `Grounding DINO 1.5 / 1.6` and `DINO-X` models. Please refer to [dds-cloudapi-sdk](https://github.com/deepdataspace/dds-cloudapi-sdk) and our [API docs](https://cloud.deepdataspace.com/docs) to view more details about the update.
 
 - **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.
 

grounded_sam2_tracking_demo_custom_video_input_dinox.py

@@ -1,9 +1,7 @@
-# dds cloudapi for Grounding DINO 1.5
+# dds cloudapi for DINO-X - update to V2Task API
 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
+from dds_cloudapi_sdk.tasks.v2_task import V2Task
 
 import os
 import cv2
@@ -30,6 +28,7 @@ SAVE_TRACKING_RESULTS_DIR = "./tracking_results"
 API_TOKEN_FOR_DINOX = "Your API token"
 PROMPT_TYPE_FOR_VIDEO = "box" # choose from ["point", "box", "mask"]
 BOX_THRESHOLD = 0.2
+IOU_THRESHOLD = 0.8  # 添加IOU阈值参数
 
 """
 Step 1: Environment settings and model initialization for SAM 2
@@ -98,22 +97,29 @@ config = Config(API_TOKEN_FOR_DINOX)
 # Step 2: initialize the client
 client = Client(config)
 
-# Step 3: run the task by DetectionTask class
-# image_url = "https://algosplt.oss-cn-shenzhen.aliyuncs.com/test_files/tasks/detection/iron_man.jpg"
+# Step 3: run the task using V2Task class
 # if you are processing local image file, upload them to DDS server to get the image url
 image_url = client.upload_file(img_path)
 
-task = DinoxTask(
-    image_url=image_url,
-    prompts=[TextPrompt(text=TEXT_PROMPT)],
-    bbox_threshold=0.25,
-    targets=[DetectionTarget.BBox],
+task = V2Task(
+    api_path="/v2/task/dinox/detection",
+    api_body={
+        "model": "DINO-X-1.0",
+        "image": image_url,
+        "prompt": {
+            "type": "text",
+            "text": TEXT_PROMPT
+        },
+        "targets": ["bbox"],
+        "bbox_threshold": BOX_THRESHOLD,
+        "iou_threshold": IOU_THRESHOLD,
+    }
 )
 
 client.run_task(task)
 result = task.result
 
-objects = result.objects  # the list of detected objects
+objects = result["objects"]  # the list of detected objects
 
 
 input_boxes = []
@@ -121,9 +127,9 @@ confidences = []
 class_names = []
 
 for idx, obj in enumerate(objects):
-    input_boxes.append(obj.bbox)
-    confidences.append(obj.score)
-    class_names.append(obj.category)
+    input_boxes.append(obj["bbox"])
+    confidences.append(obj["score"])
+    class_names.append(obj["category"])
 
 input_boxes = np.array(input_boxes)
 

grounded_sam2_tracking_demo_custom_video_input_gd1.5.py

@@ -1,10 +1,7 @@
-# dds cloudapi for Grounding DINO 1.5
+# dds cloudapi for Grounding DINO 1.5 - 更新至V2Task API
 from dds_cloudapi_sdk import Config
 from dds_cloudapi_sdk import Client
-from dds_cloudapi_sdk import DetectionTask
-from dds_cloudapi_sdk import TextPrompt
-from dds_cloudapi_sdk import DetectionModel
-from dds_cloudapi_sdk import DetectionTarget
+from dds_cloudapi_sdk.tasks.v2_task import V2Task
 
 import os
 import cv2
@@ -31,6 +28,7 @@ SAVE_TRACKING_RESULTS_DIR = "./tracking_results"
 API_TOKEN_FOR_GD1_5 = "Your API token"
 PROMPT_TYPE_FOR_VIDEO = "box" # choose from ["point", "box", "mask"]
 BOX_THRESHOLD = 0.2
+IOU_THRESHOLD = 0.8  # 添加IOU阈值参数
 
 """
 Step 1: Environment settings and model initialization for SAM 2
@@ -99,33 +97,38 @@ config = Config(API_TOKEN_FOR_GD1_5)
 # Step 2: initialize the client
 client = Client(config)
 
-# Step 3: run the task by DetectionTask class
-# image_url = "https://algosplt.oss-cn-shenzhen.aliyuncs.com/test_files/tasks/detection/iron_man.jpg"
+# Step 3: run the task using V2Task class
 # if you are processing local image file, upload them to DDS server to get the image url
 image_url = client.upload_file(img_path)
 
-task = DetectionTask(
-    image_url=image_url,
-    prompts=[TextPrompt(text=TEXT_PROMPT)],
-    targets=[DetectionTarget.BBox],  # detect bbox
-    model=DetectionModel.GDino1_6_Pro,  # detect with GroundingDino-1.5-Pro model
-    bbox_threshold=BOX_THRESHOLD,
+task = V2Task(
+    api_path="/v2/task/grounding_dino/detection",
+    api_body={
+        "model": "GroundingDino-1.5-Pro",
+        "image": image_url,
+        "prompt": {
+            "type": "text",
+            "text": TEXT_PROMPT
+        },
+        "targets": ["bbox"],
+        "bbox_threshold": BOX_THRESHOLD,
+        "iou_threshold": IOU_THRESHOLD,
+    }
 )
 
 client.run_task(task)
 result = task.result
 
-objects = result.objects  # the list of detected objects
-
+objects = result["objects"]  # the list of detected objects
 
 input_boxes = []
 confidences = []
 class_names = []
 
 for idx, obj in enumerate(objects):
-    input_boxes.append(obj.bbox)
-    confidences.append(obj.score)
-    class_names.append(obj.category)
+    input_boxes.append(obj["bbox"])
+    confidences.append(obj["score"])
+    class_names.append(obj["category"])
 
 input_boxes = np.array(input_boxes)