XAI implementation added

app.py

@@ -7,28 +7,14 @@ Original file is located at
     https://colab.research.google.com/drive/1XRB_m0JRoi0KugiHw5WSPJzV0udfU69O
 """
 
-# !nvidia-smi
-
-# Commented out IPython magic to ensure Python compatibility.
-# %reload_ext autoreload
-# %autoreload 2
-# %matplotlib inline
-
-
-# Commented out IPython magic to ensure Python compatibility.
-# %cd /content/drive/MyDrive/Bengali Fish Recognizer/
-
 
 import cv2
-import torch
 import numpy as np
 import gradio as gr
 import matplotlib as plt
 from fastai.vision.all import *
 from torchvision import transforms
-from torchvision.io import read_image
 from pytorch_grad_cam import GradCAM
-from pytorch_grad_cam.utils.image import show_cam_on_image
 from pytorch_grad_cam.utils.model_targets import ClassifierOutputTarget
 
 import pathlib
@@ -52,20 +38,22 @@ def xai_visualization(image, image_tensor, targeted_category, model, target_laye
 
   mask = grayscale_cam[0, :]
 
+  plt.figure(figsize=(5,5))
+
+  plt.axis('off')
+
   plt.imshow(image)
 
-  plt.imshow(mask*255, cmap="plasma", alpha=0.6)
+  plt.imshow(mask*255, cmap="plasma", alpha=0.7)
+
+  plt.savefig("xai/xai_visualization.png", dpi=150)
 
-  plt.show()
 
 def preprocess_image(image_path):
-  # Reading image
-  # image = cv2.imread(image_path)
-  image = torchvision.io.read_image(image_path)
 
   # Resizing an image
   image = cv2.resize(
-      image,
+      image_path,
       dsize=(224, 224),
       interpolation=cv2.INTER_CUBIC)
 
@@ -103,17 +91,26 @@ def classify_image(image_path):
   xai_visualization(image, img_tensor, targeted_category, pytorch_model, target_layer)
 
   # print(f"Category with most probability: {np.argmax(probs)}")
+  xai_image = "xai/xai_visualization.png"
 
-  return image_path, dict(zip(labels, map(float, probs)))
+  return xai_image, dict(zip(labels, map(float, probs)))
 
 # classify_image('test images/unknown_01.jpg')
 
 
-inputs = gr.Image()
+inputs = gr.Image(
+  label = "Input Image"
+)
 
 outputs = [
-    gr.Image(),
-    gr.Label(num_top_classes=5)
+    gr.Image(
+      label = "GradCAM visualization", 
+      show_label = True
+    ),
+    gr.Label(
+      num_top_classes=5, 
+      label="Predicted Category"
+    )
   ]
 
 examples = [