updated

app.py

@@ -5,7 +5,8 @@ import numpy as np
 from lime import lime_image
 from skimage.segmentation import mark_boundaries
 import matplotlib.pyplot as plt
-from vit import CNN_ViT
+from tensorflow.keras.models import load_model
+from grad_cam import GradCam
 
 hp = {}
 hp['image_size'] = 512
@@ -24,12 +25,13 @@ hp['num_heads'] = 12
 hp['dropout_rate'] = 0.1
 hp['class_names'] = ["breast_benign", "breast_malignant"]
 
-model = CNN_ViT(hp)
-model.load_weights("model/ResViT_for_breast_cancer_classification.keras")
+model = load_model("model/resnet_for_breast_cancer-v1.h5")
 print("Model initiated")
 explainer = lime_image.LimeImageExplainer()
 
 
+
+
 def main():
     st.title("Breast Cancer Classification")
 
@@ -39,13 +41,14 @@ def main():
     if uploaded_file is not None:
         # Convert the uploaded file to OpenCV format
         image = convert_to_opencv(uploaded_file)
+        gradCam = GradCam(model, image, last_conv_layer_name='conv5_block3_3_conv')
         
         # Display the uploaded image
         st.image(image, channels="BGR", caption="Uploaded Image", use_column_width=True)
 
         # Display the image shape
         image_class = predict_single_image(image, model, hp)
-        xai_result("lime_Ex.png")
+        gradCam.save_and_display_gradcam()
         st.write(f"Image Class: {image_class}")
         
 
@@ -81,17 +84,7 @@ def predict_single_image(image, model, hp):
     return class_name
 
 
-def xai_result(image):
-    path = "lime_explanation.png"
-    tem = cv2.resize(image, [512,512])
-    gray_img = cv2.cvtColor(tem, cv2.COLOR_BGR2GRAY)
-    explanation = explainer.explain_instance(gray_img.astype('double'),
-    model.predict,
-    top_labels=1000, hide_color=0,  num_samples=1000)
-    temp, mask = explanation.get_image_and_mask(explanation.top_labels[0], positive_only=True, num_features=5, hide_rest=True)
-    plt.imshow(mark_boundaries(temp / 2 + 0.5, mask), interpolation='nearest')
-    plt.savefig(path)
-    
+
 
 if __name__ == "__main__":
     main()