first commit

.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
+model_efficientnet_b0.pth filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,72 @@
+
+### Imports and class names setup ###
+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
+
+# Setup class names
+class_names = ["eugene_h_krabs", "gary_the_snail", "karen_plankton", "mrs_puff", "patrick_star", "pearl_krabs", "sandy_cheeks", "sheldon_j_plankton", "spongebob_squarepants", "squidward_tentacles"]
+
+### Model and transforms preparation ###
+# Create EffNetB0 model
+effnetb0, effnetb0_transforms = create_effnetb0_model(
+    num_classes=10
+)
+
+# Load saved weights
+effnetb0.load_state_dict(
+    torch.load(
+        f="model_efficientnet_b0.pth",
+        map_location=torch.device("cpu")
+    )
+)
+
+### Predict function ###
+
+# Create predict function
+def predict(img) -> Tuple[Dict, float]:
+  """Transforms and performs a prediction on img and returns prediction and time taken.
+  """
+  # Start the timer
+  start_time = timer()
+
+  # Transform the target image and add a batch dimension
+  img = effnetb0_transforms(img).unsqueeze(dim=0)
+
+  # Put model into evaluation mode and turn on inference mode
+  effnetb0.eval()
+  with torch.inference_mode():
+    # Pass the transformed image through the model and turn the prediction logits into prediction probabilities
+    pred_probs = torch.softmax(effnetb0(img), dim=1)
+
+  # Create a prediction label and prediction probability dictionary for each prediction class (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)
+
+  # Return the prediction dictionary and prediction time
+  return pred_labels_and_probs, pred_time
+
+### Gradio app ###
+title = "Spongebob Character Identifier 🧽👖🐙🦀🐿️🍍🍔🐳🖥️"
+description = "An EfficientNetB0 feature extractor computer vision model to classify between 10 character from Spongebob Squarepants: Spongebob, Patrick, Squidward, Gary, Mr. Krabs, Mrs.Puff, Sandy, Plankton, Karen, and Pearl"
+article = "Read more at: [Spongebob Character Identifier](https://gulnuravci.github.io/scripts/project_pages/spongebob_identifier.html)"
+
+# Create examples list from "examples/" directory
+example_list = [["examples/" + example] for example in os.listdir("examples")]
+
+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=10, 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 +1,44 @@
+
+import torch
+import torchvision
+
+from torch import nn
+from torchvision.models import efficientnet_b0, EfficientNet_B0_Weights
+from torchvision.models._api import WeightsEnum
+from torch.hub import load_state_dict_from_url
+
+def create_effnetb0_model(num_classes:int=10,
+                          seed:int=42):
+  """Creates an EficientNetB0 feature extractor model and transforms.
+
+  Args:
+    num_classes (int, optional): number of classes in the classifier head. Defaults to 10.
+    seed (int, optional): random seed value. Defaults to 42.
+
+  Returns:
+    model (torch.nn.Module): EffNetB0 feature extractor model.
+    transforms (torchvision.transforms): EfnetB0 image transforms.
+  """
+  # Fix for wrong hash error from: https://github.com/pytorch/vision/issues/7744
+  def get_state_dict(self, *args, **kwargs):
+      kwargs.pop("check_hash")
+      return load_state_dict_from_url(self.url, *args, **kwargs)
+  WeightsEnum.get_state_dict = get_state_dict
+
+  # Create EffNetB0 pretrained weights, transforms and model
+  weights = EfficientNet_B0_Weights.DEFAULT
+  transforms = weights.transforms()
+  model = efficientnet_b0(weights=weights)
+
+  # Freeze all layers in base model
+  for param in model.features.parameters():
+        param.requires_grad = False
+
+  # Change the classifier head with random seed for reproducibility
+  torch.manual_seed(seed)
+  model.classifier = nn.Sequential(
+      nn.Dropout(p=0.3),
+      nn.Linear(in_features=1408, out_features=num_classes)
+  )
+
+  return model, transforms

model_efficientnet_b0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3196ec7d7bbd0b7d39f047edfbcd0e3e279a7937f312ce0416fa7961cc4669f
+size 16384522

requirements.txt

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