Upload 7 files

config.json

@@ -0,0 +1,81 @@
+{
+  "_commit_hash": null,
+  "architectures": [
+    "DepthAnythingForDepthEstimation"
+  ],
+  "backbone": null,
+  "backbone_config": {
+    "architectures": [
+      "Dinov2Model"
+    ],
+    "hidden_size": 1024,
+    "image_size": 518,
+    "model_type": "dinov2",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "out_features": [
+      "stage5",
+      "stage12",
+      "stage18",
+      "stage24"
+    ],
+    "out_indices": [
+      5,
+      12,
+      18,
+      24
+    ],
+    "patch_size": 14,
+    "reshape_hidden_states": false,
+    "stage_names": [
+      "stem",
+      "stage1",
+      "stage2",
+      "stage3",
+      "stage4",
+      "stage5",
+      "stage6",
+      "stage7",
+      "stage8",
+      "stage9",
+      "stage10",
+      "stage11",
+      "stage12",
+      "stage13",
+      "stage14",
+      "stage15",
+      "stage16",
+      "stage17",
+      "stage18",
+      "stage19",
+      "stage20",
+      "stage21",
+      "stage22",
+      "stage23",
+      "stage24"
+    ],
+    "torch_dtype": "float32"
+  },
+  "fusion_hidden_size": 256,
+  "head_hidden_size": 32,
+  "head_in_index": -1,
+  "initializer_range": 0.02,
+  "model_type": "depth_anything",
+  "neck_hidden_sizes": [
+    256,
+    512,
+    1024,
+    1024
+  ],
+  "patch_size": 14,
+  "reassemble_factors": [
+    4,
+    2,
+    1,
+    0.5
+  ],
+  "reassemble_hidden_size": 1024,
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "use_pretrained_backbone": false
+}

depth_anything_v2_vits.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:715fade13be8f229f8a70cc02066f656f2423a59effd0579197bbf57860e1378
+size 99218434

iclight_sd15_fbc.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb8ccedaa4944b16cfa8356afcbc2c2174cc4c4af57de19124ae0cddd0d96947
+size 1719171352

iclight_sd15_fc.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a033fbaaa2f3f7859fa6a4477ee63ebbf9c116bf3569d5811856d2807f3468cd
+size 1719148312

preprocessor_config.json

@@ -0,0 +1,44 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "keep_aspect_ratio",
+    "ensure_multiple_of",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_pad",
+    "size_divisor",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "do_normalize": true,
+  "do_pad": false,
+  "do_rescale": true,
+  "do_resize": true,
+  "ensure_multiple_of": 14,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "DPTImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "keep_aspect_ratio": true,
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 518,
+    "width": 518
+  },
+  "size_divisor": null
+}

prompt_free_demo.py

@@ -0,0 +1,104 @@
+# dds cloudapi for DINO-X
+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.detection import DetectionTask
+from dds_cloudapi_sdk.tasks.types import DetectionTarget
+from dds_cloudapi_sdk import TextPrompt
+
+# using supervision for visualization
+import os
+import cv2
+import numpy as np
+import supervision as sv
+from pathlib import Path
+
+import gradio as gr
+
+
+"""
+Hyper Parameters
+"""
+API_TOKEN = "Your API Token"
+IMG_PATH = "demo2.jpg"
+TEXT_PROMPT = "<prompt_free>"
+OUTPUT_DIR = Path("./outputs/prompt_free_detection_segmentation")
+
+OUTPUT_DIR.mkdir(parents=True, exist_ok=True)
+
+"""
+Prompting DINO-X with Text for Box and Mask Generation with Cloud API
+"""
+
+# Step 1: initialize the config
+token = API_TOKEN
+config = Config(token)
+
+# Step 2: initialize the client
+client = Client(config)
+
+# Step 3: Run DINO-X task
+# 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, DetectionTarget.Mask]
+)
+client.run_task(task)
+predictions = task.result.objects
+
+"""
+Visualization
+"""
+# decode the prediction results
+classes = [pred.category for pred in predictions]
+classes = list(set(classes))
+class_name_to_id = {name: id for id, name in enumerate(classes)}
+class_id_to_name = {id: name for name, id in class_name_to_id.items()}
+
+boxes = []
+masks = []
+confidences = []
+class_names = []
+class_ids = []
+
+for idx, obj in enumerate(predictions):
+    boxes.append(obj.bbox)
+    masks.append(DetectionTask.rle2mask(DetectionTask.string2rle(obj.mask.counts), obj.mask.size))  # convert mask to np.array using DDS API
+    confidences.append(obj.score)
+    cls_name = obj.category.lower().strip()
+    class_names.append(cls_name)
+    class_ids.append(class_name_to_id[cls_name])
+
+boxes = np.array(boxes)
+masks = np.array(masks)
+class_ids = np.array(class_ids)
+labels = [
+    f"{class_name} {confidence:.2f}"
+    for class_name, confidence
+    in zip(class_names, confidences)
+]
+
+img = cv2.imread(IMG_PATH)
+detections = sv.Detections(
+    xyxy = boxes,
+    mask = masks.astype(bool),
+    class_id = class_ids,
+)
+
+box_annotator = sv.BoxAnnotator()
+annotated_frame = box_annotator.annotate(scene=img.copy(), detections=detections)
+
+label_annotator = sv.LabelAnnotator()
+annotated_frame = label_annotator.annotate(scene=annotated_frame, detections=detections, labels=labels)
+cv2.imwrite(os.path.join(OUTPUT_DIR, "annotated_demo_image.jpg"), annotated_frame)
+
+
+mask_annotator = sv.MaskAnnotator()
+annotated_frame = mask_annotator.annotate(scene=annotated_frame, detections=detections)
+cv2.imwrite(os.path.join(OUTPUT_DIR, "annotated_demo_image_with_mask.jpg"), annotated_frame)
+
+print(f"Annotated image has already been saved to {OUTPUT_DIR}")

sam2_hiera_large.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7442e4e9b732a508f80e141e7c2913437a3610ee0c77381a66658c3a445df87b
+size 897952466