support gsam2 image predictor model

grounding_dino/test.ipynb

@@ -0,0 +1,114 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "final text_encoder_type: bert-base-uncased\n"
+     ]
+    },
+    {
+     "data": {
+      "application/json": {
+       "ascii": false,
+       "bar_format": null,
+       "colour": null,
+       "elapsed": 0.014210224151611328,
+       "initial": 0,
+       "n": 0,
+       "ncols": null,
+       "nrows": null,
+       "postfix": null,
+       "prefix": "Downloading model.safetensors",
+       "rate": null,
+       "total": 440449768,
+       "unit": "B",
+       "unit_divisor": 1000,
+       "unit_scale": true
+      },
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "5922f34578364d36afa13de9f01254bd",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading model.safetensors:   0%|          | 0.00/440M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/root/miniconda3/lib/python3.8/site-packages/transformers/modeling_utils.py:881: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers.\n",
+      "  warnings.warn(\n",
+      "/root/miniconda3/lib/python3.8/site-packages/torch/utils/checkpoint.py:31: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\n",
+      "  warnings.warn(\"None of the inputs have requires_grad=True. Gradients will be None\")\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from groundingdino.util.inference import load_model, load_image, predict, annotate\n",
+    "import cv2\n",
+    "\n",
+    "model = load_model(\"groundingdino/config/GroundingDINO_SwinT_OGC.py\", \"../04-06-segment-anything/weights/groundingdino_swint_ogc.pth\")\n",
+    "IMAGE_PATH = \".asset/cat_dog.jpeg\"\n",
+    "TEXT_PROMPT = \"chair . person . dog .\"\n",
+    "BOX_TRESHOLD = 0.35\n",
+    "TEXT_TRESHOLD = 0.25\n",
+    "\n",
+    "image_source, image = load_image(IMAGE_PATH)\n",
+    "\n",
+    "boxes, logits, phrases = predict(\n",
+    "    model=model,\n",
+    "    image=image,\n",
+    "    caption=TEXT_PROMPT,\n",
+    "    box_threshold=BOX_TRESHOLD,\n",
+    "    text_threshold=TEXT_TRESHOLD\n",
+    ")\n",
+    "\n",
+    "annotated_frame = annotate(image_source=image_source, boxes=boxes, logits=logits, phrases=phrases)\n",
+    "cv2.imwrite(\"annotated_image.jpg\", annotated_frame)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "base",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.10"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}