gradio demo working fine

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+07_effnetb0_data_20_percent_10_epochs.pth filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+__pycache__

07_effnetb0_data_20_percent_10_epochs.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b1d222b609c6e0928d890cc4a17d429727e9623503d5a478b6cf6f50cba69f2
+size 16354890

app.py

@@ -0,0 +1,53 @@
+import gradio as gr
+import os
+import torch
+
+from model import create_effnetb0_model
+from timeit import default_timer as timer
+from typing import Tuple, Dict
+
+
+class_names = ["pizza", "steak", "sushi"]
+
+effnetb0, effnetb0_transforms = create_effnetb0_model()
+
+effnetb0.load_state_dict(torch.load(
+    "07_effnetb0_data_20_percent_10_epochs.pth"))
+
+
+def predict(img) -> Tuple[Dict, float]:
+    pred_list = []
+
+    pred_dict = {}
+
+    start_time = timer()
+
+    img = effnetb0_transforms(img).unsqueeze(0)
+
+    effnetb0.eval()
+
+    with torch.inference_mode():
+        pred_probs = torch.softmax(effnetb0(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))}
+
+    pred_time = round(timer() - start_time, 4)
+
+    pred_list.append(pred_dict)
+
+    return pred_labels_and_probs, pred_time
+
+
+title = "FoodVision Mini 🍕🥩🍣"
+description = "An EfficientNetB0 feature extractor computer vision model to classify images of food as pizza, steak or sushi."
+article = "Full Source code from scratch [deployment.ipynb](https://github.com/Victoran0/food-vision.git)."
+
+# Create examples list from "examples/" directory
+example_list = [["examples/" + example] for example in os.listdir("examples")]
+
+demo = gr.Interface(fn=predict, inputs=gr.Image(type='pil'), outputs=[gr.Label(num_top_classes=3, label='Predictions'), gr.Number(
+    label="Prediction time (s)")], examples=example_list, title=title, description=description, article=article)
+
+demo.launch()

model.py

@@ -0,0 +1,22 @@
+import torch
+import torchvision
+
+from torch import nn
+
+def create_effnetb0_model(num_classes: int=3, seed: int=42):
+    effnetb0_weights = torchvision.models.EfficientNet_B0_Weights.DEFAULT
+    effnetb0_transforms = effnetb0_weights.transforms()
+    effnetb0 = torchvision.models.efficientnet_b0(weights=effnetb0_weights)
+
+    for param in effnetb0.parameters():
+        param.required_grad = False
+    
+    torch.manual_seed(seed)
+
+    effnetb0.classifier = nn.Sequential(
+        nn.Dropout(p=0.3, inplace=True),
+        nn.Linear(in_features=1280, out_features=num_classes)
+    )
+
+    return effnetb0, effnetb0_transforms
+

playground.py

@@ -0,0 +1,4 @@
+import os
+
+
+print(os.listdir("C:/Users/User/Data Science/Deep Learning/Pytorch/food-vision/data/pizza_steak_sushi_20_percent"))

requirements.txt

@@ -0,0 +1,3 @@
+torch==2.4.1
+torchvision==0.19.1
+gradio==4.44.0