Final Deployment

app.py

@@ -3,7 +3,6 @@ import gradio as gr
 import torch
 from model import create_effnetb2_model
 from classes import class_names
-from PIL import Image
 
 # Setup DataLoaders
 effnetb2, effnetb2_transforms = create_effnetb2_model(num_classes=525,
@@ -97,5 +96,4 @@ demo = gr.Interface(fn=predict,
                     article=article)
 
 # Launch the demo!
-demo.launch(debug=True,
-            share=True)
+demo.launch(debug=True)

classes.py

@@ -1,4 +1,4 @@
-
+# Bird Classes
 class_names = ['ABBOTTS BABBLER',
  'ABBOTTS BOOBY',
  'ABYSSINIAN GROUND HORNBILL',

model.py

@@ -1,22 +1,21 @@
 import torch
 import torchvision
-
 from torch import nn
 
-
+# creates an EfficientNet-B2 model with a custom classifier head
 def create_effnetb2_model(num_classes:int=525,
                           seed:int=42):
 
-    # 1, 2, 3. Create EffNetB2 pretrained weights, transforms and model
+    # Create EffNetB2 pretrained weights, transforms and model
     weights = torchvision.models.EfficientNet_B2_Weights.DEFAULT
     transforms = weights.transforms()
     model = torchvision.models.efficientnet_b2(weights=weights)
 
-    # 4. Freeze all layers in base model
+    # Freeze all layers in base model
     for param in model.parameters():
         param.requires_grad = False
 
-    # 5. Change classifier head with random seed for reproducibility
+    # Change classifier head with random seed for reproducibility
     torch.manual_seed(seed)
     model.classifier = nn.Sequential(
         nn.Dropout(p=0.3, inplace=True),