CV-Expression-Recognition / app /Hackathon_setup /exp_recognition_model.py
npuliga's picture
updated print messages
e8d631e
import torch
import torchvision
import torch.nn as nn
from torchvision import transforms
## Add more imports if required
####################################################################################################################
# Define your model and transform and all necessary helper functions here #
# They will be imported to the exp_recognition.py file #
####################################################################################################################
# Definition of classes as dictionary
classes = {0: 'ANGER', 1: 'DISGUST', 2: 'FEAR', 3: 'HAPPINESS', 4: 'NEUTRAL', 5: 'SADNESS', 6: 'SURPRISE'}
# Grayscale-compatible Expression CNN from notebook
# CNN model for Expression Recognition - Clean architecture with BatchNorm
class ExpressionCNN(nn.Module):
def __init__(self, num_classes=7):
super(ExpressionCNN, self).__init__()
# Conv Block 1
self.conv1 = nn.Conv2d(1, 32, kernel_size=3, padding=1)
self.bn1 = nn.BatchNorm2d(32)
self.relu1 = nn.ReLU()
self.pool1 = nn.MaxPool2d(kernel_size=2, stride=2)
# Conv Block 2
self.conv2 = nn.Conv2d(32, 64, kernel_size=3, padding=1)
self.bn2 = nn.BatchNorm2d(64)
self.relu2 = nn.ReLU()
self.pool2 = nn.MaxPool2d(kernel_size=2, stride=2)
# Conv Block 3
self.conv3 = nn.Conv2d(64, 128, kernel_size=3, padding=1)
self.bn3 = nn.BatchNorm2d(128)
self.relu3 = nn.ReLU()
self.pool3 = nn.MaxPool2d(kernel_size=2, stride=2)
# Fully Connected Layers
self.fc1 = nn.Linear(128 * 6 * 6, 512)
self.bn4 = nn.BatchNorm1d(512)
self.relu4 = nn.ReLU()
self.fc2 = nn.Linear(512, 256)
self.bn5 = nn.BatchNorm1d(256)
self.relu5 = nn.ReLU()
self.fc3 = nn.Linear(256, num_classes)
def forward(self, x):
# Conv Block 1
x = self.conv1(x)
x = self.bn1(x)
x = self.relu1(x)
x = self.pool1(x)
# Conv Block 2
x = self.conv2(x)
x = self.bn2(x)
x = self.relu2(x)
x = self.pool2(x)
# Conv Block 3
x = self.conv3(x)
x = self.bn3(x)
x = self.relu3(x)
x = self.pool3(x)
# Flatten
x = x.view(x.size(0), -1)
# FC layers
x = self.fc1(x)
x = self.bn4(x)
x = self.relu4(x)
x = self.fc2(x)
x = self.bn5(x)
x = self.relu5(x)
x = self.fc3(x)
return x
# Backward compatibility alias
facExpRec = ExpressionCNN
# Sample Helper function
def rgb2gray(image):
return image.convert('L')
# Transformation function - normalized grayscale
trnscm = transforms.Compose([
rgb2gray, # Convert to grayscale
transforms.Resize((48, 48)), # Resize to model input size
transforms.ToTensor(), # Convert to tensor
transforms.Normalize(mean=[0.5], std=[0.5]) # Normalize grayscale image
])