update xai params

yolov5.py

@@ -8,6 +8,18 @@ from pytorch_grad_cam import EigenCAM
 from pytorch_grad_cam.utils.image import show_cam_on_image, scale_cam_image
 import gradio as gr
 import os
+from typing import Callable, List, Tuple, Optional
+from sklearn.decomposition import NMF
+from pytorch_grad_cam.activations_and_gradients import ActivationsAndGradients
+from pytorch_grad_cam.utils.image import scale_cam_image, create_labels_legend, show_factorization_on_image
+import matplotlib.pyplot as plt
+from pytorch_grad_cam.utils.image import show_factorization_on_image
+import requests    
+import yaml
+import matplotlib.patches as patches
+
+
+
 # Global Color Palette
 COLORS = np.random.uniform(0, 255, size=(80, 3))
 
@@ -56,7 +68,7 @@ def generate_cam_image(model, target_layers, tensor, rgb_img, boxes):
     return cam_image, renormalized_cam_image
 
 
-def xai_yolov5(image):
+def xai_yolov5(image,target_lyr = -5, n_components = 8):
     model = torch.hub.load('ultralytics/yolov5', 'yolov5s', pretrained=True)
     model.eval()
     model.cpu()
@@ -86,21 +98,6 @@ def xai_yolov5(image):
     return Image.fromarray(final_image), caption, result
 
 
-
-import numpy as np
-from PIL import Image
-import torch
-import cv2
-from typing import Callable, List, Tuple, Optional
-from sklearn.decomposition import NMF
-from pytorch_grad_cam.activations_and_gradients import ActivationsAndGradients
-from pytorch_grad_cam.utils.image import scale_cam_image, create_labels_legend, show_factorization_on_image
-import matplotlib.pyplot as plt
-from pytorch_grad_cam.utils.image import show_factorization_on_image
-import requests    
-import yaml
-import matplotlib.patches as patches
-
 def dff_l(activations,  model,  n_components):
     batch_size, channels, h, w = activations.shape
     print('activation', activations.shape)