Update app.py

app.py

@@ -23,8 +23,7 @@ os.system("wget https://github.com/AK391/models/raw/main/vision/object_detection
 sess = rt.InferenceSession("fcn-resnet101-11.onnx")
 
 outputs = sess.get_outputs()
-output_names = list(map(lambda output: output.name, outputs))
-input_name = sess.get_inputs()[0].name
+
 
 classes = [line.rstrip('\n') for line in open('voc_classes.txt')]
 num_classes = len(classes)
@@ -78,10 +77,13 @@ def inference(img):
   input_tensor = preprocess(input_image)
   input_tensor = input_tensor.unsqueeze(0)
   input_tensor = input_tensor.detach().cpu().numpy()
-  
+  output_names = list(map(lambda output: output.name, outputs))
+  input_name = sess.get_inputs()[0].name
   detections = sess.run(output_names, {input_name: input_tensor})
   output, aux = detections
   conf, result_img, blended_img, _ = visualize_output(orig_tensor, output[0])
   return blended_img
   
-gr.Interface(inference,gr.inputs.Image(type="filepath"),gr.outputs.Image(type="pil")).launch(enable_queue=True)
+title="Fully Convolutional Network"
+description="FCNs are a model for real-time neural network for class-wise image segmentation. As the name implies, every weight layer in the network is convolutional. The final layer has the same height/width as the input image, making FCNs a useful tool for doing dense pixel-wise predictions without a significant amount of postprocessing. Being fully convolutional also provides great flexibility in the resolutions this model can handle. This specific model detects 20 different classes. The models have been pre-trained on the COCO train2017 dataset on this class subset."
+gr.Interface(inference,gr.inputs.Image(type="filepath"),gr.outputs.Image(type="pil"),title=title,description=description).launch(enable_queue=True)