Upload 3 files

app.py

@@ -0,0 +1,35 @@
+import torch
+import torch.nn as nn
+from PIL import Image
+from torchvision import transforms
+import torchvision
+import gradio as gr
+
+agirliklar=torchvision.models.EfficientNet_B2_Weights.DEFAULT
+eff_don=agirliklar.transforms()
+
+model=torchvision.models.efficientnet_b2(weights=agirliklar)
+model.classifier=nn.Sequential(nn.Dropout(p=0.2),nn.Linear(1408,5))
+model.load_state_dict(torch.load("model.pth"))
+
+class_names=['a_bir', 'b_iki', 'c_üç', 'd_dört', 'e_beş']
+def predict(img):
+    """Transforms and performs a prediction on img and returns prediction and time taken.
+    """
+    # Start the timer
+   # img=Image.open(img)
+    # Transform the target image and add a batch dimension
+    img = eff_don(img).unsqueeze(0)
+
+    # Put model into evaluation mode and turn on inference mode
+    model.eval()
+    with torch.inference_mode():
+        # Pass the transformed image through the model and turn the prediction logits into prediction probabilities
+        pred_probs = torch.softmax(model(img), dim=1)
+
+    # Create a prediction label and prediction probability dictionary for each prediction class (this is the required format for Gradio's output parameter)
+    pred_labels_and_probs = {class_names[i]: float(pred_probs[0][i]) for i in range(len(class_names))}
+
+
+    # Return the prediction dictionary and prediction time
+    return pred_labels_and_probs

model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:243ccb95ae6eed067f0529729734b86535d21b85c0affcb433d0e9d4cffa4efe
+size 31253178

requirements.txt

@@ -0,0 +1,4 @@
+torch
+gradio
+torchvision
+pillow