Create app.py

app.py

@@ -0,0 +1,101 @@
+from keras.models import load_model
+from PIL import Image, ImageOps
+import numpy as np
+import gradio as gr
+import pandas as pd
+import torch
+import json
+
+# Load the model
+classify_model = load_model('keras_model.h5')
+detect_model = torch.hub.load('ultralytics/yolov5', 'custom', path='best.pt', force_reload=True, _verbose=False)
+
+def detect(image):
+  # Inference
+  results = detect_model(image)
+  try:
+    results = json.loads(results.pandas().xyxy[0].to_json(orient="records"))[0]
+    top = int(results['ymin'])
+    left = int(results['xmin'])
+    width = int(results['xmax'] - results['xmin'])
+    height = int(results['ymax'] - results['ymin'])
+    return top, left, width, height
+  except:
+    return 0,0,0,0
+
+def format_label(label):
+  """
+  From '0 class 1\n' to 'class 1'
+  """
+  return label[:-1]
+
+
+def predict(image):
+  top, left, width, height = detect(image)
+
+  if (top == 0) and (left == 0) and (width == 0) and (height==0):
+    return {
+      "predictions": {}, 
+      'bbox': {
+          "top": 0,
+          "left": 0,
+          "width": 0,
+          "height": 0
+      }
+    }
+
+  if width > height:
+    height = width
+  else:
+    width = height
+  
+  # Crop the turtle
+  image = image.crop((left, top, left + width, top + height))
+
+  # Create the array of the right shape to feed into the keras model
+  # The 'length' or number of images you can put into the array is
+  # determined by the first position in the shape tuple, in this case 1.
+  data = np.ndarray(shape=(1, 224, 224, 3), dtype=np.float32)
+  
+  #resize the image to a 224x224 with the same strategy as in TM2:
+  #resizing the image to be at least 224x224 and then cropping from the center
+  size = (224, 224)
+  image = ImageOps.fit(image, size, Image.ANTIALIAS)
+
+  #turn the image into a numpy array
+  image_array = np.asarray(image)
+  # Normalize the image
+  normalized_image_array = (image_array.astype(np.float32) / 127.0) - 1
+  # Load the image into the array
+  data[0] = normalized_image_array
+
+  # run the inference
+  pred = classify_model.predict(data)
+  pred = pred.tolist()
+
+  with open('labels.txt','r') as f:
+    labels = f.readlines()
+    
+  result = {format_label(labels[i]): round(pred[0][i],2) for i in range(len(pred[0]))}
+  sorted_result = {k: v for k, v in sorted(result.items(), key=lambda item: item[1], reverse=True) if v > 0}
+
+  
+  return json.dumps({
+      "predictions": sorted_result, 
+      'bbox': {
+          "top": top,
+          "left": left,
+          "width": width,
+          "height": height
+      }
+    })
+    
+title = "🐆"
+
+gr.Interface(
+    fn=predict, 
+    inputs=gr.Image(type="pil", label="Input Image"),
+    outputs=[gr.JSON()],
+  #  live=True,
+    title=title,
+).launch(share=True, debug=False)