Try to update Gradio syntax

.specstory/history/2025-03-27_10-40-gradio-code-update-and-error-fix.md

@@ -0,0 +1,87 @@
+<!-- Generated by SpecStory -->
+
+# Gradio Code Update and Error Fix (2025-03-27 18:40:39)
+
+_**User**_
+
+```
+WARNING:tensorflow:No training configuration found in save file, so the model was *not* compiled. Compile it manually.
+Traceback (most recent call last):
+  File "/home/user/app/app.py", line 59, in <module>
+    input = [gr.inputs.Image(type="filepath", label="Ground Truth - Real Image (jpg)"),
+AttributeError: module 'gradio' has no attribute 'inputs'
+```
+
+Please update @app.py code to use Gradio version 5.23.1 syntax
+
+---
+
+_**Assistant**_
+
+
+
+---
+
+Let me update the code to use Gradio 5.23.1 syntax:
+
+---
+
+```diff
+    return np.array((fake_img+1)/2)
+    
+- # input
+- input = [gr.inputs.Image(type="filepath", label="Ground Truth - Real Image (jpg)"), 
+-          gr.inputs.Image(type="filepath", label="Corresponding Segmentation (png)"),
+-          gr.inputs.Image(type="filepath", label="Corresponding bitmap image (bmp)", image_mode="L")]
++ # Define inputs with modern Gradio syntax
++ ground_truth = gr.Image(type="filepath", label="Ground Truth - Real Image (jpg)")
++ segmentation = gr.Image(type="filepath", label="Corresponding Segmentation (png)")
++ bitmap = gr.Image(type="filepath", label="Corresponding bitmap image (bmp)", image_mode="L")
+  
+  examples = [["facades_data/cmp_b0010.jpg", "facades_data/cmp_b0010.png", "facades_data/cmp_b0010.bmp"],
+              ["facades_data/cmp_b0050.jpg", "facades_data/cmp_b0050.png", "facades_data/cmp_b0050.bmp"]]
+  
+- # output
+- output = [gr.outputs.Image(type="numpy", label="Generated - Conditioned Images")]
+- 
+  title = "GauGAN For Conditional Image Generation"
+  description = "Upload an Image or take one from examples to generate realistic images that are conditioned on cue images and segmentation maps"
+  
+- gr.Interface(fn=predict, inputs = input, outputs = output, examples=examples, allow_flagging=False, analytics_enabled=False,
+-   title=title, description=description, article="<center>Space By: <u><a href='https://github.com/robotjellyzone'><b>Kavya Bisht</b></a></u> \n Based on <a href='https://keras.io/examples/generative/gaugan/'><b>this notebook</b></a></center>").launch(enable_queue=True, debug=True)
++ # Create interface with modern Gradio syntax
++ demo = gr.Interface(
++     fn=predict, 
++     inputs=[ground_truth, segmentation, bitmap],
++     outputs=gr.Image(type="numpy", label="Generated - Conditioned Images"),
++     examples=examples,
++     allow_flagging=False,
++     analytics_enabled=False,
++     title=title,
++     description=description,
++     article="<center>Space By: <u><a href='https://github.com/robotjellyzone'><b>Kavya Bisht</b></a></u> \n Based on <a href='https://keras.io/examples/generative/gaugan/'><b>this notebook</b></a></center>"
++ )
++ 
++ if __name__ == "__main__":
++     demo.launch(enable_queue=True, debug=True)
+```
+
+---
+
+The code has been updated to use Gradio 5.23.1 syntax. The main changes include:
+
+1. Replaced the outdated `gr.inputs.Image()` with just `gr.Image()`
+2. Replaced `gr.outputs.Image()` with `gr.Image()`
+3. Created individual component variables instead of input/output lists
+4. Added proper structure with a named `demo` variable
+5. Added an `if __name__ == "__main__":` guard
+6. Used a more modern and cleaner formatting style
+
+These changes maintain all the same functionality while using the current Gradio component API.
+
+---
+
+
+
+---
+

app.py

@@ -55,10 +55,10 @@ def predict(image_file, segmentation_png, bitmap_img):
 
   return np.array((fake_img+1)/2)
   
-# input
-input = [gr.inputs.Image(type="filepath", label="Ground Truth - Real Image (jpg)"), 
-         gr.inputs.Image(type="filepath", label="Corresponding Segmentation (png)"),
-         gr.inputs.Image(type="filepath", label="Corresponding bitmap image (bmp)", image_mode="L")]
+# Define inputs with modern Gradio syntax
+ground_truth = gr.Image(type="filepath", label="Ground Truth - Real Image (jpg)")
+segmentation = gr.Image(type="filepath", label="Corresponding Segmentation (png)")
+bitmap = gr.Image(type="filepath", label="Corresponding bitmap image (bmp)", image_mode="L")
 
 examples = [["facades_data/cmp_b0010.jpg", "facades_data/cmp_b0010.png", "facades_data/cmp_b0010.bmp"],
             ["facades_data/cmp_b0020.jpg", "facades_data/cmp_b0020.png", "facades_data/cmp_b0020.bmp"],
@@ -66,11 +66,21 @@ examples = [["facades_data/cmp_b0010.jpg", "facades_data/cmp_b0010.png", "facade
             ["facades_data/cmp_b0040.jpg", "facades_data/cmp_b0040.png", "facades_data/cmp_b0040.bmp"], 
             ["facades_data/cmp_b0050.jpg", "facades_data/cmp_b0050.png", "facades_data/cmp_b0050.bmp"]]
 
-# output
-output = [gr.outputs.Image(type="numpy", label="Generated - Conditioned Images")]
-
 title = "GauGAN For Conditional Image Generation"
 description = "Upload an Image or take one from examples to generate realistic images that are conditioned on cue images and segmentation maps"
 
-gr.Interface(fn=predict, inputs = input, outputs = output, examples=examples, allow_flagging=False, analytics_enabled=False,
-  title=title, description=description, article="<center>Space By: <u><a href='https://github.com/robotjellyzone'><b>Kavya Bisht</b></a></u> \n Based on <a href='https://keras.io/examples/generative/gaugan/'><b>this notebook</b></a></center>").launch(enable_queue=True, debug=True)
+# Create interface with modern Gradio syntax
+demo = gr.Interface(
+    fn=predict, 
+    inputs=[ground_truth, segmentation, bitmap],
+    outputs=gr.Image(type="numpy", label="Generated - Conditioned Images"),
+    examples=examples,
+    allow_flagging=False,
+    analytics_enabled=False,
+    title=title,
+    description=description,
+    article="<center>Space By: <u><a href='https://github.com/robotjellyzone'><b>Kavya Bisht</b></a></u> \n Based on <a href='https://keras.io/examples/generative/gaugan/'><b>this notebook</b></a></center>"
+)
+
+if __name__ == "__main__":
+    demo.launch(enable_queue=True, debug=True)