Update app.py

app.py

@@ -1,7 +1,8 @@
 import os
 
-os.system('pip install --force-reinstall gradio==3.39.0')
-# os.system('pip install gradio_client')
+# Upgrade Gradio to the latest version
+os.system('pip install --upgrade gradio')
+
 import gradio as gr
 import torch
 import torch.nn.functional as F
@@ -14,6 +15,7 @@ from pytorch_grad_cam.utils.model_targets import ClassifierOutputTarget
 from pytorch_grad_cam.utils.image import show_cam_on_image
 import warnings
 warnings.filterwarnings("ignore")
+
 DEVICE = 'cuda:0' if torch.cuda.is_available() else 'cpu'
 
 mtcnn = MTCNN(
@@ -21,6 +23,7 @@ mtcnn = MTCNN(
     post_process=False,
     device=DEVICE
 ).to(DEVICE).eval()
+
 model = InceptionResnetV1(
     pretrained="vggface2",
     classify=True,
@@ -32,15 +35,16 @@ checkpoint = torch.load("resnetinceptionv1_epoch_32.pth", map_location=torch.dev
 model.load_state_dict(checkpoint['model_state_dict'])
 model.to(DEVICE)
 model.eval()
-def predict(input_image:Image.Image):
+
+def predict(input_image: Image.Image):
     """Predict the label of the input_image"""
     face = mtcnn(input_image)
     if face is None:
         raise Exception('No face detected')
-    face = face.unsqueeze(0) # add the batch dimension
+    face = face.unsqueeze(0)  # add the batch dimension
     face = F.interpolate(face, size=(256, 256), mode='bilinear', align_corners=False)
     
-    # convert the face into a numpy array to be able to plot it
+    # Convert the face into a numpy array to be able to plot it
     prev_face = face.squeeze(0).permute(1, 2, 0).cpu().detach().int().numpy()
     prev_face = prev_face.astype('uint8')
 
@@ -49,7 +53,7 @@ def predict(input_image:Image.Image):
     face = face / 255.0
     face_image_to_plot = face.squeeze(0).permute(1, 2, 0).cpu().detach().int().numpy()
 
-    target_layers=[model.block8.branch1[-1]]
+    target_layers = [model.block8.branch1[-1]]
     use_cuda = True if torch.cuda.is_available() else False
     cam = GradCAM(model=model, target_layers=target_layers, use_cuda=use_cuda)
     targets = [ClassifierOutputTarget(0)]
@@ -71,6 +75,7 @@ def predict(input_image:Image.Image):
             'fake': fake_prediction
         }
     return confidences, face_with_mask
+
 interface = gr.Interface(
     fn=predict,
     inputs=[
@@ -80,12 +85,4 @@ interface = gr.Interface(
         gr.outputs.Label(label="Class"),
         gr.outputs.Image(label="Face with Explainability", type="pil")
     ],
-).launch()
-# from gradio_client import Client
-
-# client = Client("https://vikasdeep-deepfacedetection.hf.space/")
-# result = client.predict(
-# 				"https://raw.githubusercontent.com/gradio-app/gradio/main/test/test_files/bus.png",	# str (filepath on your computer (or URL) of image) in 'Input Image' Image component
-# 				api_name="/predict"
-# )
-# print(result)
+).launch(share=True)