Update app.py

app.py

@@ -4,6 +4,7 @@ import os
 import torch
 import numpy as np
 from roboflow import Roboflow
+import cv2
 rf = Roboflow(api_key="gjZE3lykkitagkxHplyJ")
 project = rf.workspace().project("rideit")
 model = project.version(1).model
@@ -47,10 +48,11 @@ def predict(img) -> Tuple[Dict, float]:
     start_time = timer()
     
     # Transform the target image and add a batch dimension
-    img1 = effnetb2_transforms(img).unsqueeze(0)
+    img1=PIL.Image.open(img, mode=’r’)
+    img1 = effnetb2_transforms(img1).unsqueeze(0)
     pix = normalize_2d(np.array(img))
 
-    pix1=model.predict(str(img.jpg), confidence=40, overlap=30)
+    pix1=model.predict(img, confidence=40, overlap=30)
 
     
     # Put model into evaluation mode and turn on inference mode
@@ -78,12 +80,20 @@ article = "(https://www.learnpytorch.io/)."
 # Create examples list from "examples/" directory
 example_list = [["examples/" + example] for example in os.listdir("examples")]
 
+inputs_image = [
+    gr.components.Image(type="filepath", label="Input Image"),
+]
+
+outputs_image = [
+    gr.components.Image(type="numpy", label="Output Image"),
+]
+
 # Create the Gradio demo
 demo = gr.Interface(fn=predict, # mapping function from input to output
-                    inputs=gr.Image(type="pil"), # what are the inputs?
+                    inputs=inputs_image, # what are the inputs?
                     outputs=[gr.Label(num_top_classes=2, label="Predictions"), # what are the outputs?
                              gr.Number(label="Prediction time (s)"),
-                             (gr.Image(shape=(300,400)))], # our fn has two outputs, therefore we have two outputs
+                             outputs_image], # our fn has two outputs, therefore we have two outputs
                     # Create examples list from "examples/" directory
                     examples=example_list, 
                     title=title,