Upload 9 files

README.md

@@ -1,13 +1,13 @@
----
-title: FoodVision3
-emoji: ⚡
-colorFrom: red
-colorTo: purple
-sdk: gradio
-sdk_version: 4.38.1
-app_file: app.py
-pinned: false
-license: apache-2.0
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: FoodVision Mini
+emoji: 📈
+colorFrom: red
+colorTo: yellow
+sdk: gradio
+sdk_version: 4.38.1
+app_file: app.py
+pinned: false
+license: mit
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,69 @@
+# 1. Imports and class names setup
+import gradio as gr
+import os
+import torch
+
+from model import create_effnetb2_model
+from timeit import default_timer as timer
+from typing import Tuple , Dict
+
+# Setup class names
+class_names = ['pizza','steak','sushi']
+
+# Model and transforms preparation
+# Create EffNetB2 model
+effnetb2 , effnetb2_transforms = create_effnetb2_model(num_classes=len(class_names))
+
+# load and save weights
+<<<<<<< HEAD
+effnetb2.load_state_dict(torch.load(os.path.join("effnetb2.pth"),map_location=torch.device('cpu')))
+=======
+effnetb2.load_state_dict(torch.load("effnetb2.pth",map_location=torch.device('cpu')))
+>>>>>>> f57d3888756f20e9db37eb8ce02739685876fb20
+
+# Predict function
+def predict(img):
+  """
+  Transforms and performs a prediction on img and returns prediction and time taken.
+  """
+  # Start timer
+  start_time = timer()
+
+  # transform the target image and add a batch dimension
+  img = effnetb2_transforms(img).unsqueeze(0)
+
+  # put model into evaluation mode and turn on inference mode
+  effnetb2.eval()
+  with torch.inference_mode():
+    # pass the transformed image through the model and turn the pred logits into prediction probabilities
+    pred_probs = torch.softmax(effnetb2(img), dim=1)
+  # create a prediction label and prediction probability dictionary
+  pred_labels_and_probs = {class_names[i]: float(pred_probs[0][i]) for i in range(len(class_names))}
+  # calculate time
+  pred_time = round(timer() - start_time , 5)
+  # return the prediction dictionary
+  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 "
+
+# 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()

effnetb2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56ae45551ee9305afa43726d6802c0d97701a32641b6a8adab6c3e9e023018ae
+size 31274298

model.py

@@ -0,0 +1,31 @@
+import torch
+import torchvision
+from torch import nn
+def create_effnetb2_model(num_classes : int ,
+                          seed : int=42):
+  """
+  Create an EffNetB2 feature extractor model and move it to the target device.
+  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)
+
+  # Freeze all layers in base model
+  for param in model.parameters():
+    param.requires_grad = False
+  # change classifier head with random seed for reproducilityù
+  torch.manual_seed(seed)
+  model.classifier = nn.Sequential(
+      nn.Dropout(p=0.2, inplace=True),
+      nn.Linear(in_features=1408, out_features=num_classes, bias=True)
+  )
+  return model, transforms

requirements.txt

@@ -0,0 +1,3 @@
+gradio==3.21.0
+torch==1.13.1
+torchvision==0.14.1