Update app.py

remove - DINO sources

app.py

@@ -1,5 +1,6 @@
 import spaces
-from transformers import Owlv2Processor, Owlv2ForObjectDetection, AutoProcessor, AutoModelForZeroShotObjectDetection
+# from transformers import Owlv2Processor, Owlv2ForObjectDetection, AutoProcessor, AutoModelForZeroShotObjectDetection
+from transformers import Owlv2Processor, Owlv2ForObjectDetection
 import torch
 import gradio as gr
 
@@ -8,8 +9,8 @@ device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
 owl_model = Owlv2ForObjectDetection.from_pretrained("google/owlv2-base-patch16-ensemble").to("cuda")
 owl_processor = Owlv2Processor.from_pretrained("google/owlv2-base-patch16-ensemble")
 
-dino_processor = AutoProcessor.from_pretrained("IDEA-Research/grounding-dino-base")
-dino_model = AutoModelForZeroShotObjectDetection.from_pretrained("IDEA-Research/grounding-dino-base").to("cuda")
+# dino_processor = AutoProcessor.from_pretrained("IDEA-Research/grounding-dino-base")
+# dino_model = AutoModelForZeroShotObjectDetection.from_pretrained("IDEA-Research/grounding-dino-base").to("cuda")
 
 @spaces.GPU
 def infer(img, text_queries, score_threshold, model):
@@ -57,26 +58,30 @@ def infer(img, text_queries, score_threshold, model):
             result_labels.append((box, label))
   return result_labels
 
-def query_image(img, text_queries, owl_threshold, dino_threshold):
+# def query_image(img, text_queries, owl_threshold, dino_threshold):
+def query_image(img, text_queries, owl_threshold):
     text_queries = text_queries
     text_queries = text_queries.split(",")
     owl_output = infer(img, text_queries, owl_threshold, "owl")
-    dino_output = infer(img, text_queries, dino_threshold, "dino")
+    # dino_output = infer(img, text_queries, dino_threshold, "dino")
 
 
-    return (img, owl_output), (img, dino_output)
+    # return (img, owl_output), (img, dino_output)
+    return (img, owl_output)
 
 
 owl_threshold = gr.Slider(0, 1, value=0.16, label="OWL Threshold")
-dino_threshold = gr.Slider(0, 1, value=0.12, label="Grounding DINO Threshold")
+# dino_threshold = gr.Slider(0, 1, value=0.12, label="Grounding DINO Threshold")
 owl_output = gr.AnnotatedImage(label="OWL Output")
-dino_output = gr.AnnotatedImage(label="Grounding DINO Output")
+# dino_output = gr.AnnotatedImage(label="Grounding DINO Output")
 demo = gr.Interface(
     query_image,
-    inputs=[gr.Image(label="Input Image"), gr.Textbox(label="Candidate Labels"), owl_threshold, dino_threshold],
-    outputs=[owl_output, dino_output],
-    title="OWLv2 ⚔ Grounding DINO",
-    description="Compare two state-of-the-art zero-shot object detection models [OWLv2](https://huggingface.co/google/owlv2-base-patch16) and [Grounding DINO](https://huggingface.co/IDEA-Research/grounding-dino-base) in this Space. Simply enter an image and the objects you want to find with comma, or try one of the examples. Play with the threshold to filter out low confidence predictions in each model.",
+    # inputs=[gr.Image(label="Input Image"), gr.Textbox(label="Candidate Labels"), owl_threshold, dino_threshold],
+    inputs=[gr.Image(label="Input Image"), gr.Textbox(label="Candidate Labels"), owl_threshold],
+    # outputs=[owl_output, dino_output],
+    outputs=[owl_output],
+    title="OWLv2 Demo",
+    description="Compare two state-of-the-art zero-shot object detection models [OWLv2](https://huggingface.co/google/owlv2-base-patch16) . Simply enter an image and the objects you want to find with comma, or try one of the examples. Play with the threshold to filter out low confidence predictions in each model.",
     examples=[["./bee.jpg", "bee, flower", 0.16, 0.12], ["./cats.png", "cat, fishnet", 0.16, 0.12]]
 )
 demo.launch(debug=True)