H4_New / app /Hackathon_setup /exp_recognition_model.py
gopikrishnait's picture
Upload 2 files
01bc20c verified
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'}
# Example Network
class facExpRec(nn.Module):
def __init__(self, num_classes):
super(facExpRec, self).__init__()
self.conv1 = nn.Conv2d(in_channels=1, out_channels=32, kernel_size=3, padding=1)
self.relu1 = nn.ReLU()
self.pool1 = nn.MaxPool2d(kernel_size=2, stride=2)
self.conv2 = nn.Conv2d(in_channels=32, out_channels=64, kernel_size=3, padding=1)
self.relu2 = nn.ReLU()
self.pool2 = nn.MaxPool2d(kernel_size=2, stride=2)
self.conv3 = nn.Conv2d(in_channels=64, out_channels=128, kernel_size=3, padding=1)
self.relu3 = nn.ReLU()
self.pool3 = nn.MaxPool2d(kernel_size=2, stride=2)
# Calculate the size of the flattened layer after convolutional and pooling layers
# Assuming input image size is 48x48
self.fc1 = nn.Linear(128 * 6 * 6, 512) # 48 / 2 / 2 / 2 = 6
self.relu4 = nn.ReLU()
self.dropout = nn.Dropout(0.5)
self.fc2 = nn.Linear(512, num_classes)
def forward(self, x):
x = self.pool1(self.relu1(self.conv1(x)))
x = self.pool2(self.relu2(self.conv2(x)))
x = self.pool3(self.relu3(self.conv3(x)))
x = x.view(-1, 128 * 6 * 6) # Flatten the output for the fully connected layers
x = self.dropout(self.relu4(self.fc1(x)))
x = self.fc2(x)
return x
# Sample Helper function
def rgb2gray(image):
return image.convert('L')
# Enhanced Transformation function with augmentations
trnscm = transforms.Compose([
rgb2gray, # Convert to grayscale
transforms.Resize((48, 48)), # Resize to model input size
transforms.RandomHorizontalFlip(p=0.3), # Random horizontal flip
transforms.RandomRotation(10), # Slight random rotation
transforms.ColorJitter( # Adjust image properties
brightness=0.2,
contrast=0.2
),
transforms.ToTensor(), # Convert to tensor
transforms.Normalize(mean=[0.485], # Normalize the grayscale image
std=[0.229])
])