Add app.py - with only grounding dino bounding box function

app.py

@@ -0,0 +1,119 @@
+import argparse
+from functools import partial
+import cv2
+import os
+from io import BytesIO
+from PIL import Image
+import numpy as np
+from pathlib import Path
+import gradio as gr
+
+import warnings
+
+import torch
+warnings.filterwarnings("ignore")
+
+# grounding DINO
+from groundingdino.models import build_model
+from groundingdino.util.slconfig import SLConfig
+from groundingdino.util.utils import clean_state_dict
+from groundingdino.util.inference import annotate, load_image, predict
+import groundingdino.datasets.transforms as T
+
+from huggingface_hub import hf_hub_download
+
+os.environ["CUDA_VISIBLE_DEVICES"] = "0"
+
+
+# Use this command for evaluate the GLIP-T model
+config_file = "groundingdino/config/GroundingDINO_SwinT_OGC.py"
+ckpt_repo_id = "ShilongLiu/GroundingDINO"
+ckpt_filename = "groundingdino_swint_ogc.pth"
+groundingdino_device = 'cpu'
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
+
+
+def load_model_hf(model_config_path, repo_id, filename, device='cpu'):
+    args = SLConfig.fromfile(model_config_path) 
+    model = build_model(args)
+    args.device = device
+
+    cache_file = hf_hub_download(repo_id=repo_id, filename=filename)
+    checkpoint = torch.load(cache_file, map_location='cpu')
+    log = model.load_state_dict(clean_state_dict(checkpoint['model']), strict=False)
+    print("Model loaded from {} \n => {}".format(cache_file, log))
+    _ = model.eval()
+    return model    
+
+def image_transform_grounding(init_image):
+    transform = T.Compose([
+        T.RandomResize([800], max_size=1333),
+        T.ToTensor(),
+        T.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
+    ])
+    image, _ = transform(init_image, None) # 3, h, w
+    return init_image, image
+
+def image_transform_grounding_for_vis(init_image):
+    transform = T.Compose([
+        T.RandomResize([800], max_size=1333),
+    ])
+    image, _ = transform(init_image, None) # 3, h, w
+    return image
+
+model = load_model_hf(config_file, ckpt_repo_id, ckpt_filename, groundingdino_device)
+
+def get_grounding_box(input_image, grounding_caption, box_threshold, text_threshold):
+    init_image = input_image.convert("RGB")
+    original_size = init_image.size
+
+    _, image_tensor = image_transform_grounding(init_image)
+    image_pil: Image = image_transform_grounding_for_vis(init_image)
+
+    # run grounding
+    boxes, logits, phrases = predict(model, image_tensor, grounding_caption, box_threshold, text_threshold, device=groundingdino_device)
+    annotated_frame = annotate(image_source=np.asarray(image_pil), boxes=boxes, logits=logits, phrases=phrases)
+    image_with_box = Image.fromarray(cv2.cvtColor(annotated_frame, cv2.COLOR_BGR2RGB))
+
+
+    return image_with_box
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser("Grounding SAM demo", add_help=True)
+    parser.add_argument("--debug", action="store_true", help="using debug mode")
+    parser.add_argument("--share", action="store_true", help="share the app")
+    args = parser.parse_args()
+
+    print(f'args = {args}')
+
+    block = gr.Blocks().queue()
+    with block:
+        gr.Markdown("# [Grounding SAM Playground]")
+        with gr.Row():
+            with gr.Column():
+                input_image = gr.Image(source='upload', type="pil")
+                grounding_caption = gr.Textbox(label="Detection Prompt")
+                run_button = gr.Button(label="Run")
+                with gr.Accordion("Advanced options", open=False):
+                    box_threshold = gr.Slider(
+                        label="Box Threshold", minimum=0.0, maximum=1.0, value=0.25, step=0.001
+                    )
+                    text_threshold = gr.Slider(
+                        label="Text Threshold", minimum=0.0, maximum=1.0, value=0.25, step=0.001
+                    )
+
+            with gr.Column():
+                gallery = gr.outputs.Image(
+                    type="pil",
+                    # label="grounding results"
+                ).style(full_width=True, full_height=True)
+                # gallery = gr.Gallery(label="Generated images", show_label=False).style(
+                #         grid=[1], height="auto", container=True, full_width=True, full_height=True)
+        
+        DESCRIPTION = '### This demo from [Grounded-Segment-Anything](https://github.com/IDEA-Research/Grounded-Segment-Anything) and kudos to thier excellent works. Welcome everyone to try this out and learn together!'
+        gr.Markdown(DESCRIPTION)
+        run_button.click(fn=get_grounding_box, inputs=[
+                        input_image, grounding_caption, box_threshold, text_threshold], outputs=[gallery])
+
+    block.launch(share=False, show_api=False, show_error=True)