Fix device variable which was shadowed (#8)

- Remove device variable from gradio state for now (9f022b04640263be67b10e2bc5d1bc092eae547e)

.dockerignore

@@ -5,6 +5,8 @@ env
 .github/
 .gitignore
 
+models/GroundingDINO/ops/build/
+
 *.zip
 *.whl
 !gradio_image_prompter-0.1.0-py3-none-any.whl

.gitignore

@@ -4,5 +4,8 @@ __pycache__
 .python-version
 *.py[od]
 
+# GroundingDINO build folder
+models/GroundingDINO/ops/build/
+
 # vim
 *.sw[op]

app.py

@@ -285,15 +285,17 @@ if __name__ == '__main__':
     model, transform = build_model_and_transforms(args)
     model = model.to(device)
 
-    _predict = lambda image, text, prompts: predict(model, transform, image, text, prompts, device)
+    def _predict(image, text, prompts):
+        return predict(model, transform, image, text, prompts, device)
+
 
     @spaces.GPU(duration=120)
-    def count(image, text, prompts, state, device):
+    def count(image, text, prompts, state):
         if prompts is None:
             prompts = {"image": image, "points": []}
         
         boxes, _ = _predict(image, text, prompts)
-        count = len(boxes)
+        predicted_count = len(boxes)
         output_img = generate_heatmap(image, boxes)
 
         num_exemplars = len(get_box_inputs(prompts["points"]))
@@ -317,19 +319,19 @@ if __name__ == '__main__':
             main_instructions_comp = gr.Markdown(visible=True)
             step_3 = gr.Tab(visible=True)
 
-        return (gr.Image(output_img, visible=True, label=out_label, show_label=True), gr.Number(label="Predicted Count", visible=True, value=count), new_submit_btn, gr.Tab(visible=True), step_3, state)
+        return (gr.Image(output_img, visible=True, label=out_label, show_label=True), gr.Number(label="Predicted Count", visible=True, value=predicted_count), new_submit_btn, gr.Tab(visible=True), step_3, state)
 
     @spaces.GPU
-    def count_main(image, text, prompts, device):
+    def count_main(image, text, prompts):
         if prompts is None:
             prompts = {"image": image, "points": []}
         boxes, _ = _predict(image, text, prompts)
-        count = len(boxes)
+        predicted_count = len(boxes)
         output_img = generate_heatmap(image, boxes)
         num_exemplars = len(get_box_inputs(prompts["points"]))
         out_label = generate_output_label(text, num_exemplars)
 
-        return (gr.Image(output_img, visible=True, label=out_label, show_label=True), gr.Number(label="Predicted Count", visible=True, value=count))
+        return (gr.Image(output_img, visible=True, label=out_label, show_label=True), gr.Number(label="Predicted Count", visible=True, value=predicted_count))
 
     def remove_label(image):
         return gr.Image(show_label=False)
@@ -359,7 +361,6 @@ if __name__ == '__main__':
 
     with gr.Blocks(title="CountGD: Multi-Modal Open-World Counting", theme="soft", head="""<meta name="viewport" content="width=device-width, initial-scale=1, user-scalable=1">""") as demo:
         state = gr.State(value=[AppSteps.JUST_TEXT])
-        device = gr.State(device)
         with gr.Tab("Tutorial"):
             with gr.Row():
                 with gr.Column():
@@ -383,7 +384,7 @@ if __name__ == '__main__':
                 pred_count = gr.Number(label="Predicted Count", visible=False)
             submit_btn = gr.Button("Count", variant="primary", interactive=True)
 
-            submit_btn.click(fn=remove_label, inputs=[detected_instances], outputs=[detected_instances]).then(fn=count, inputs=[input_image, input_text, exemplar_image, state, device], outputs=[detected_instances, pred_count, submit_btn, step_2, step_3, state])
+            submit_btn.click(fn=remove_label, inputs=[detected_instances], outputs=[detected_instances]).then(fn=count, inputs=[input_image, input_text, exemplar_image, state], outputs=[detected_instances, pred_count, submit_btn, step_2, step_3, state])
             exemplar_image.change(check_submit_btn, inputs=[exemplar_image, state], outputs=[submit_btn])
         with gr.Tab("App", visible=True) as main_app:
 
@@ -409,7 +410,7 @@ if __name__ == '__main__':
                     submit_btn_main = gr.Button("Count", variant="primary")
                     clear_btn_main = gr.ClearButton(variant="secondary")
             gr.Examples(label="Examples: click on a row to load the example. Add visual exemplars by drawing boxes on the loaded \"Visual Exemplar Image.\"", examples=examples, inputs=[input_image_main, input_text_main, exemplar_image_main])
-            submit_btn_main.click(fn=remove_label, inputs=[detected_instances_main], outputs=[detected_instances_main]).then(fn=count_main, inputs=[input_image_main, input_text_main, exemplar_image_main, device], outputs=[detected_instances_main, pred_count_main])
+            submit_btn_main.click(fn=remove_label, inputs=[detected_instances_main], outputs=[detected_instances_main]).then(fn=count_main, inputs=[input_image_main, input_text_main, exemplar_image_main], outputs=[detected_instances_main, pred_count_main])
             clear_btn_main.add([input_image_main, input_text_main, exemplar_image_main, detected_instances_main, pred_count_main])