new OV-API

app.py

@@ -11,8 +11,9 @@ core = Core()
 
 # Get the available devices
 devices = core.available_devices
-
 inferencer = None
+prev_category_selection = None
+prev_device_selection = None
 
 example_list = [["bottle/examples/000.png", "anomaly_map", "bottle", "CPU"],
                ["pill/examples/014.png", "heat_map", "pill", "CPU"],
@@ -57,27 +58,49 @@ def OV_inference(input_img, operation, category_choice, device):
         output_img1 = predictions.image
     return output_img1, round(inference_time*1000), round(confidence*100,2)
 
+#Run + Compile the model
+def OV_compile_run_model(category_choice, device_choice, image, output_choice):
+    #If a different category or device are selected, compile/re-compile the model
+    global prev_category_selection
+    global prev_device_selection
+    if device_choice != prev_device_selection or category_choice != prev_category_selection:
+        OV_compilemodel(category_choice, device_choice)
+        prev_category_selection = category_choice
+        prev_device_selection = device_choice
+    #Run model
+    print("Running model")
+    output_img, output_time, output_confidence = OV_inference(image, output_choice, category_choice, device_choice)
+    return output_img, output_time, output_confidence
+
 with gr.Blocks() as demo:
+
     gr.Markdown(
     """
     <img align="left" width="150" src= "https://github.com/openvinotoolkit/anomalib/assets/10940214/7e61a627-d1b0-4ad4-b602-da9b348c0cbe">   
     <img align="right" width="150" src= "https://github.com/openvinotoolkit/anomalib/assets/10940214/5d6dd038-b40c-441f-ad38-1cf526137de2">   
     
     <h1 align="center"> 🚀 Anomaly detection 🚀 </h1>  
-    
-    Experience the power of the state-of-the-art anomaly detection with Anomalib-OpenVINO Anomaly detection toolbox. This interactive APP leverages the robust capabilities of Anomalib and OpenVINO.
-    
-    All model are FP32 precision, if you select GPU it will automatically change precision to FP16. Using Anomalib you can also quantize your model in INT8 using NNCF.
-    
-    
-     
-    ![](https://github.com/openvinotoolkit/anomalib/assets/10940214/ce78346f-4d27-4f99-bea7-75b87e2ac02a)
-    
-    
-    
+
     """
     )
     
+    with gr.Row():
+        with gr.Column():
+            gr.Markdown(
+                """
+                Experience the power of the state-of-the-art anomaly detection with Anomalib-OpenVINO Anomaly detection toolbox. This interactive APP leverages the robust capabilities of Anomalib and OpenVINO.
+                
+                All model are FP32 precision, if you select GPU it will automatically change precision to FP16. Using Anomalib you can also quantize your model in INT8 using NNCF.
+                """
+            ) 
+            
+        with gr.Column():
+            gr.Markdown(
+                """
+                ![image](https://github.com/openvinotoolkit/openvino_notebooks/assets/10940214/017d494b-1c37-45f8-bd6e-cad0d64ef652)
+                """
+            ) 
+    
     gr.Markdown("## 1. Select the category over you want to detect anormalities.")
     category_choice = gr.Radio(["bottle", "grid", "pill", "zipper", "cubes"], label="Choose the category")
     
@@ -92,23 +115,19 @@ with gr.Blocks() as demo:
         """
     )
     device_choice = gr.Dropdown(devices, label="Choose the device")
-    
-    gr.Markdown("## 3. Compile the model")
-    compile_btn = gr.Button("Compile Model")
 
-    gr.Markdown("## 4. Choose the output you want to visualize.")
+    gr.Markdown("## 3. Choose the output you want to visualize.")
     output_choice = gr.Radio(["original", "anomaly_map", "heat_map", "pred_mask", "segmentations"], label="Choose the output")
     
-    gr.Markdown("## 5. Drop the image in the input image box and run the inference")
+    gr.Markdown("## 4. Drop the image in the input image box and run the inference")
     with gr.Row():
         with gr.Column():
-            image = gr.Image(type="numpy", label= "Input image")
-            
+            image = gr.Image(type="numpy", label= "Input image")  
             
         with gr.Column():
             output_img = gr.outputs.Image(type="numpy", label="Anomalib Output")
 
-    inference_btn = gr.Button("Run Inference")
+    compile_inference_btn = gr.Button("Compile Model + Run Inference")
     
     with gr.Row():
         # Create your output components
@@ -116,17 +135,16 @@ with gr.Blocks() as demo:
         output_confidence = gr.Textbox(label="Confidence [%]")
         output_time = gr.Textbox(label="Inference Time [ms]")
     
-    gr.Markdown("Note: Change the image and run the inference again. If you want to change the object you need to recompile the model, that means you need to start from step 1.")    
-    gr.Markdown("## Image Examples")
-    
+    gr.Markdown("Changing your choice of category or device will recompile the model.")    
+
+    gr.Markdown("## OR use our image examples for a quick start")
     gr.Examples(
         examples=example_list,
         inputs=[image, output_choice, category_choice, device_choice],
         outputs=[output_img, output_time, output_confidence],
-        fn=OV_inference,
-    )
-    
-    compile_btn.click(OV_compilemodel, inputs=[category_choice, device_choice])
-    inference_btn.click(OV_inference, inputs=[image, output_choice], outputs=[output_img, output_time, output_confidence])
+        fn=OV_compile_run_model)
+
+    compile_inference_btn.click(OV_compile_run_model, inputs=[category_choice, device_choice, image, output_choice], 
+        outputs=[output_img, output_time, output_confidence])
 
 demo.launch(enable_queue=True)