Upload 18 files

TinyCNN.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebe4d82d0b37c4f3c04f924f426505d96ff0880693d6eefe29268a2504479590
+size 40675386

app.py

@@ -0,0 +1,120 @@
+### 1. Imports and class names setup ### 
+import gradio as gr
+import os
+import torch
+
+from timeit import default_timer as timer
+from typing import Tuple, Dict
+
+# Setup class names
+with open("class_names.txt", "r") as f: # reading them in from class_names.txt
+    class_names = [food_name.strip() for food_name in  f.readlines()]
+    
+### 2. Model and transforms preparation ###    
+
+# Create model
+TinyCNN_model = TinyCNN(input_shape=3, # number of color channels (3 for RGB) 
+                  hidden_units=64, 
+                  output_shape=len(class_names))
+
+loss_fn = nn.CrossEntropyLoss() # measure how wrong our model is
+optimizer = torch.optim.Adam(params = TinyCNN_model.parameters() ,lr=0.001)
+
+transform = transforms.Compose([
+    transforms.Resize((128, 128)),
+    transforms.Grayscale(num_output_channels=3)
+])
+
+# Load saved weights
+TinyCNN_model.load_state_dict(
+    torch.load(
+        f="TinyCNN.pth",
+        map_location=torch.device("cpu"),  # load to CPU
+    )
+)
+
+### 3. 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 = transform(img).unsqueeze(0)
+    
+    # Put model into evaluation mode and turn on inference mode
+    TinyCNN_model.eval()
+    with torch.inference_mode():
+        # Pass the transformed image through the model and turn the prediction logits into prediction probabilities
+        pred_probs = torch.softmax(TinyCNN_model(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)
+    emoji_list = [["emojis/" + example] for example in os.listdir("emojis")]
+    
+    emoji_1 =  torch.argmax(pred_probs)
+    emoji = class_names[emoji_1]
+    if emoji == 'angry':
+        a = example_list[0]
+        a = a[0]
+        return pred_labels_and_probs,a
+    elif emoji == 'disgust':
+        a = example_list[1]
+        a = a[0]
+        return pred_labels_and_probs,a
+    elif emoji == 'fear':
+        a = example_list[2]
+        a = a[0]
+        return pred_labels_and_probs,a
+    elif emoji == 'happy':
+        a = example_list[3]
+        a = a[0]
+        return pred_labels_and_probs,a
+    elif emoji == 'neutral':
+        a = example_list[4]
+        a = a[0]
+        return pred_labels_and_probs,a
+    elif emoji == 'sad':
+        a = example_list[5]
+        a = a[0]
+        return pred_labels_and_probs,a
+    elif emoji == 'surprise':
+        a = example_list[6]
+        a = a[0]
+        return pred_labels_and_probs,a
+    
+    # Return the prediction dictionary and prediction time 
+
+
+### 4. Gradio app ###
+
+# Create title, description and article strings
+title = "Expression Detection"
+description = "An app to predict emotions from the list.[Angry, Disgust, Fear, Happy, Neutral, Sad, Surprise]"
+article = "Created as a college  project."
+
+# Create examples list from "examples/" directory
+example_list = [["examples/" + example] for example in os.listdir("examples")]
+
+# Create Gradio interface 
+demo = gr.Interface(
+    fn=predict,
+    inputs=gr.Image(type="pil"),
+    outputs=[
+        gr.Label(num_top_classes=5, label="Predictions"),
+        gr.Image(label="Emotion"),
+    ],
+    examples=example_list,
+    title=title,
+    description=description,
+    article=article,
+)
+
+# Launch the app!
+demo.launch()

class_names.txt

@@ -0,0 +1,7 @@
+angry
+disgust
+fear
+happy
+neutral
+sad
+surprise

model.py

@@ -0,0 +1,89 @@
+import torch
+import torchvision
+
+from torch import nn
+class TinyCNN(nn.Module):
+  
+  
+  def __init__(self, input_shape: int, hidden_units: int, output_shape: int) -> None:
+      super().__init__()
+      self.conv_block_1 = nn.Sequential(
+        nn.Conv2d(in_channels=input_shape, 
+                out_channels=hidden_units, 
+                kernel_size=3, 
+                stride=1, 
+                padding=0), 
+        nn.ReLU(),
+        nn.Conv2d(in_channels=hidden_units, 
+                out_channels=128,
+                kernel_size=3,
+                stride=1,
+                padding=0),
+        nn.BatchNorm2d(128),
+        nn.ReLU(),
+        nn.MaxPool2d(kernel_size=2,
+                        stride=2), 
+        nn.Dropout(p=0.25)
+      )
+      self.conv_block_2 = nn.Sequential(
+          nn.Conv2d(128, 128, kernel_size=3, padding=0),
+          nn.ReLU(),
+          nn.Conv2d(128, 128, kernel_size=3, padding=0),
+          nn.BatchNorm2d(128),
+          nn.ReLU(),
+          nn.MaxPool2d(2),
+          nn.Dropout(p=0.25)
+      )
+      
+      self.conv_block_3 = nn.Sequential(
+          nn.Conv2d(128, 128, kernel_size=3, padding=0),
+          nn.ReLU(),
+          nn.Conv2d(128, 512, kernel_size=3, padding=0),
+          nn.BatchNorm2d(512),
+          nn.ReLU(),
+          nn.MaxPool2d(2),
+          nn.Dropout(p=0.25)
+      )
+      
+      self.conv_block_4 = nn.Sequential(
+          nn.Conv2d(512, 512, kernel_size=3, padding=0),
+          nn.ReLU(),
+          nn.Conv2d(512, 512, kernel_size=3, padding=0),
+          nn.BatchNorm2d(512),
+          nn.ReLU(),
+          nn.MaxPool2d(2),
+          nn.Dropout(p=0.25)
+      )
+      
+      self.fc_1 = nn.Sequential(
+          nn.Flatten(),
+          nn.Linear(in_features=512*16, out_features = 512),
+          nn.BatchNorm1d(512),
+          nn.ReLU(),
+          nn.Dropout(p=0.25)
+      )
+      
+      self.fc_2 = nn.Sequential(
+          
+
+          nn.Linear(in_features=512,
+                    out_features=256),
+          nn.BatchNorm1d(256),
+          nn.ReLU(),
+          nn.Dropout(p=0.25)
+      )
+      
+      self.classifier = nn.Sequential(
+          nn.Linear(in_features=256,
+                  out_features=output_shape)
+      )
+    
+  def forward(self, x):
+      x = self.conv_block_1(x)
+      x = self.conv_block_2(x)
+      x = self.conv_block_3(x)
+      x = self.conv_block_4(x)
+      x = self.fc_1(x)
+      x = self.fc_2(x)
+      x = self.classifier(x)
+      return x