first commit

.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
+09_pretrained_effnetb2_feature_extractor_pizza_steak_sushi_20_percent.pth filter=lfs diff=lfs merge=lfs -text

09_pretrained_effnetb2_feature_extractor_pizza_steak_sushi_20_percent.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37b329ab24c80214f862782cf003468562f4f3eef4b96ebe1296bb096e5e2c36
+size 31313869

app.py

@@ -0,0 +1,44 @@
+# Imports
+import gradio as gr
+import os
+import torch
+from model import create_effnetb2_model
+from timeit import deafult_timer as timer
+from typing import Tuple,Dict
+
+class_names=["pissa", "steak", "sushi"]
+effnetb2, effnetb2_transforms = create_effnetb2_model(num_classes=3)
+effnetb2.load_state_dict(
+    torch.load(f="09_pretrained_effnetb2_feature_extractor_pizza_steak_sushi_20_percent.pth",
+               map_location=torch.device("cpu")
+               )
+)
+
+#Predict fn
+def predict(img):
+  start_time = timer()
+  img = effnetb2_transforms(img).unsqueeze(0)
+  effnetb2.eval()
+  with torch.inference_mode():
+    preds = torch.softmax(effnetb2(img), dim=1)
+  pred_labels_and_probs = {class_names[i]: float(preds[0][i]) for i in range(len(class_names))}
+  pred_time = round(timer()-start_time, 5)
+  return pred_labels_and_probs, pred_time
+
+#Gradio app
+# Create title, description and article strings
+title = "FoodVision Mini 🍕🥩🍣"
+description = "An EfficientNetB2 feature extractor computer vision model to classify images of food as pizza, steak or sushi."
+article = "Created at [09. PyTorch Model Deployment](https://www.learnpytorch.io/09_pytorch_model_deployment/)."
+example_list = [[str(filepath)] for filepath in random.sample(test_data_paths, k=3)]
+# 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
+                    examples=example_list, 
+                    title=title,
+                    description=description,
+                    article=article)
+
+demo.launch()

model.py

@@ -0,0 +1,36 @@
+import torch
+import torchvision
+
+from torch import nn
+
+
+def create_effnetb2_model(num_classes:int=3, 
+                          seed:int=42):
+    """Creates an EfficientNetB2 feature extractor model and transforms.
+
+    Args:
+        num_classes (int, optional): number of classes in the classifier head. 
+            Defaults to 3.
+        seed (int, optional): random seed value. Defaults to 42.
+
+    Returns:
+        model (torch.nn.Module): EffNetB2 feature extractor model. 
+        transforms (torchvision.transforms): EffNetB2 image transforms.
+    """
+    # Create EffNetB2 pretrained weights, transforms and model
+    weights = torchvision.models.EfficientNet_B2_Weights.DEFAULT
+    transforms = weights.transforms()
+    model = torchvision.models.efficientnet_b2(weights=weights)
+
+    # Freeze all layers in base model
+    for param in model.parameters():
+        param.requires_grad = False
+
+    # Change classifier head with random seed for reproducibility
+    torch.manual_seed(seed)
+    model.classifier = nn.Sequential(
+        nn.Dropout(p=0.3, inplace=True),
+        nn.Linear(in_features=1408, out_features=num_classes),
+    )
+    
+    return model, transforms

requirements.txt

@@ -0,0 +1,3 @@
+torch==1.12.0
+torchvision==0.13.0
+gradio==3.1.4