uploaded gradio app

app.py

@@ -0,0 +1,51 @@
+import time
+import gradio as gr
+from pathlib import Path
+import pickle as pkl
+from models import *
+
+
+examples = [[str(path)] for path in Path(r"examples").glob("*")]
+
+with open('class_names_to_idx.pkl', 'rb') as fp:
+    class_idx_to_names = pkl.load(fp)
+
+def predict_one(model, transforms, image, device, class_idx_to_names):
+    model.eval()
+    model = model.to(device)
+    with torch.inference_mode():
+            
+        start_time = time.perf_counter()
+        image_transformed = transforms(image).unsqueeze(dim = 0).to(device)
+        
+        y_logits = model(image_transformed)
+        y_preds = torch.softmax(y_logits, dim = 1)
+        
+        end_time = time.perf_counter()
+
+        predictions = {class_idx_to_names[index]: x.item() for index, x in enumerate(y_preds[0])}
+
+    return predictions, end_time - start_time
+
+def predict(image, model_choice):
+
+    if model_choice is None or model_choice == "effnet_b2":
+        model, transforms = get_effnet_b2()
+    else:
+        model, transforms = get_vit_16_base_transformer()
+    
+    predictions, time_taken = predict_one(model, transforms, image, "cpu", class_idx_to_names)
+    return predictions, time_taken
+
+
+title = "Food Recognition 🍕🍕"
+desc = "A dual model app ft. EfficientNetB2 Feature Extractor and VisionTransformer. Now, bigger than ever. featuring 101 classes"
+
+demo = gr.Interface(fn = predict, 
+                    inputs = [gr.Image(type = "pil", label = "upload an Jpeg or Png"), gr.Radio(["effnet_b2", "ViT (Vision Transformer)"], label = "choose model (default on effnet)")],
+                    outputs = [gr.Label(num_top_classes = 5, label = "predictions"), gr.Number(label = "Prediction Time in seconds")], 
+                    examples = examples, 
+                    title = title,
+                    description=desc)
+
+demo.launch(debug = False)

class_names_to_idx.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:299cd0f46194deac09e3487c45b93acf02c991f09417cea83149ab5ff0cbc3a5
+size 1604

models.py

@@ -0,0 +1,15 @@
+import torch
+from torchvision.models import  ViT_B_16_Weights, EfficientNet_B2_Weights
+
+
+def get_vit_16_base_transformer():
+    vit_b_16_model = torch.load(r"models\ViT_16_base_101_classes_pretrained_custom_head.pth")
+    vit_b_16_transforms = ViT_B_16_Weights.DEFAULT.transforms()
+
+    return vit_b_16_model, vit_b_16_transforms
+
+def get_effnet_b2():
+    eff_net_b2_model = torch.load(r"models\effnet_b2_101_classes_pretrained_custom_head.pth")
+    eff_net_b2_transforms = EfficientNet_B2_Weights.DEFAULT.transforms()
+
+    return eff_net_b2_model, eff_net_b2_transforms

models/ViT_16_base_101_classes_pretrained_custom_head.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97648542d2e7c33c5467761db056c936de506c73db0723381e2681fa44d2f667
+size 343593351

models/effnet_b2_101_classes_pretrained_custom_head.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:638192c9b6e0f533e2a514739c903d564b6f0563bb270213e3160e166ece5def
+size 31924415