Update app.py

app.py

@@ -1,27 +1,28 @@
-import gradio as gr
-import torch
-import torchvision
-from model import create_model
-from timeit import default_timer as timer
-
-model,transform=create_model()
-model.load_state_dict(torch.load("deneme_modeli.pth"))
-class_names = ["pizza","steak","sushi"]
-def predict(model,image):
-    start=timer()
-    image=transform(image.to("cpu")).unsqueeze(0)
-    model=model.to("cpu")
-    pred=model(image)
-    pred = {class_names[i]:torch.softmax(pred)[0][i] for i in range(3)}
-    td=timer()-start
-    return pred,td
-
-inputs = gr.Image(type="pil", label = "Resim")
-outputs = [gr.Label(num_top_classes=3,label="Tahminler"),gr.Number(label="Süre")]
-demo=gr.Interface(fn = predict,
-                 inputs=inputs,
-                 outputs=outputs,
-                 examples=["examples/673127.jpg","examples/690177.jpg"],
-                 title="Yeni Model")
-
-demo.launch()
+import gradio as gr
+import torch
+import torchvision
+from model import create_model
+from timeit import default_timer as timer
+
+model,transform=create_model()
+model=model.to("cpu")
+model.load_state_dict(torch.load("deneme_modeli.pth").to("cpu"))
+class_names = ["pizza","steak","sushi"]
+def predict(model,image):
+    start=timer()
+    image=transform(image.to("cpu")).unsqueeze(0)
+    model=model.to("cpu")
+    pred=model(image)
+    pred = {class_names[i]:torch.softmax(pred)[0][i] for i in range(3)}
+    td=timer()-start
+    return pred,td
+
+inputs = gr.Image(type="pil", label = "Resim")
+outputs = [gr.Label(num_top_classes=3,label="Tahminler"),gr.Number(label="Süre")]
+demo=gr.Interface(fn = predict,
+                 inputs=inputs,
+                 outputs=outputs,
+                 examples=["examples/673127.jpg","examples/690177.jpg"],
+                 title="Yeni Model")
+
+demo.launch()