commit app files

.gitattributes

@@ -32,3 +32,4 @@ 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
+pretrained_effnetb1_feature_extractor_pizza_steak_sushi_20_percent.pth filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,72 @@
+### 1. Imports and class names setup ###
+import gradio as gr
+import os
+import torch
+
+from model import create_effnetb1_model
+from timeit import default_timer as timer
+from typing import Tuple, Dict
+
+# Setup class names
+class_names = ["pizza", "steak", "sushi"]
+
+### 2. Model and transforms preparation ###
+
+# Create EffNetB2 model
+effnetb1, effnetb1_transforms = create_effnetb1_model(num_classes=len(class_names) )
+
+# Load saved weights
+effnetb1.load_state_dict(torch.load(f="pretrained_effnetb1_feature_extractor_pizza_steak_sushi_20_percent.pth",
+                                    map_location=torch.device("cpu"),))
+### 3. Predict function ###
+# Create predict function
+def predict(img) -> Tuple[Dict, float]:
+    """
+    Transforms and performs a prediction on img.
+    :param img: target image .
+    :return: prediction and time taken.
+    """
+    # Start the timer
+    start_time = timer()
+
+    # Transform the target image and add a batch dimension
+    img = effnetb1_transforms(img).unsqueeze(0)
+
+    # Put model into evaluation mode and turn on inference mode
+    effnetb1.eval()
+    with torch.inference_mode():
+        # Pass the transformed image through the model and turn the prediction logits into prediction probabilities
+        pred_probs = torch.softmax(effnetb1(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))}
+
+    # Calculate the prediction time
+    pred_time = round(timer() - start_time, 5)
+
+    # Return the prediction dictionary and prediction time
+    return pred_labels_and_probs, pred_time
+
+### 4. Gradio app ###
+
+# Create title, description and article strings
+title = "FoodVision Mini 🍕🥩🍣"
+description = "An EfficientNetB1 feature extractor computer vision model to classify images of food as pizza, steak or sushi."
+article = "I will add it soon wait.."
+
+# Create examples list from "examples/" directory
+example_list = [["examples/" + example] for example in os.listdir("examples")]
+
+# Create the Gradio demo
+demo = gr.Interface(fn=predict, # mapping function from input to output
+                    inputs=gr.Image(type="pil"), # what are the inputs?
+                    outputs=[gr.Label(num_top_classes=3, label="Predictions"), # what are the outputs?
+                             gr.Number(label="Prediction time (s)")], # our fn has two outputs, therefore we have two outputs
+                    # Create examples list from "examples/" directory
+                    examples=example_list,
+                    title=title,
+                    description=description,
+                    article=article)
+
+# Launch the demo!
+demo.launch()

model.py

@@ -0,0 +1,33 @@
+import torch
+import torchvision
+
+from torch import nn
+
+
+def create_effnetb1_model(num_classes:int=3,seed:int=42):
+    """
+    Creates an EFFicientNetB1 feature extractor model and transforms.
+    :param num_classes: number of classes in classifier head.
+                        Defaults to 3.
+    :param seed: random seed value.
+                 Defaults to 42.
+    :return: feature extractor model.
+         transforms (torchvision.transforms): EffNetB1 image transforms.
+    """
+    # 1. Setup pretrained EffNetB1 weights
+    weigts = torchvision.models.EfficientNet_B1_Weights.DEFAULT
+    # 2. Get EffNetB2 transforms
+    transforms= weigts.transforms()
+
+    # 3. Setup pretrained model
+    model=torchvision.models.efficientnet_b1(weights= "DEFAULT")
+
+    # 4. Freeze the base layers in the model (this will freeze all layers to begin with)
+    for param in model.parameters():
+        param.requires_grad=False
+
+    # 5. Change classifier head with random seed for reproducibility
+    torch.manual_seed(seed)
+    model.classifier=nn.Sequential(nn.Dropout(p=0.2,inplace=True),
+                                   nn.Linear(in_features=1280,out_features=num_classes))
+    return model,transforms

pretrained_effnetb1_feature_extractor_pizza_steak_sushi_20_percent.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2b5243d08f41bba16d28533e61036a578e494d4bf31b5f2705c78121cc7b297
+size 26536531

requirements.txt

@@ -0,0 +1,3 @@
+torch==1.13.1
+torchvision==0.14.1
+gradio==3.16.2