Spaces:
Sleeping
Sleeping
File size: 5,794 Bytes
e5abc2e | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 | """
Custom CNN model architecture for emotion recognition.
Optimized for 48x48 grayscale images.
"""
import tensorflow as tf
from tensorflow.keras.models import Sequential, Model
from tensorflow.keras.layers import (
Conv2D, MaxPooling2D, Dense, Dropout, Flatten,
BatchNormalization, Input, GlobalAveragePooling2D
)
from tensorflow.keras.regularizers import l2
import sys
from pathlib import Path
sys.path.append(str(Path(__file__).parent.parent.parent))
from src.config import IMAGE_SIZE, NUM_CLASSES, NUM_CHANNELS
def build_custom_cnn(
input_shape: tuple = (*IMAGE_SIZE, NUM_CHANNELS),
num_classes: int = NUM_CLASSES,
dropout_rate: float = 0.25,
dense_dropout: float = 0.5,
l2_reg: float = 0.01
) -> Model:
"""
Build a custom CNN architecture for emotion recognition.
Architecture:
- 4 Convolutional blocks with increasing filters (64 -> 128 -> 256 -> 512)
- Each block: Conv2D -> BatchNorm -> ReLU -> MaxPool -> Dropout
- Dense layers for classification
Args:
input_shape: Input image shape (height, width, channels)
num_classes: Number of emotion classes
dropout_rate: Dropout rate for conv blocks
dense_dropout: Dropout rate for dense layers
l2_reg: L2 regularization factor
Returns:
Compiled Keras model
"""
model = Sequential([
# Input layer
Input(shape=input_shape),
# Block 1: 64 filters
Conv2D(64, (3, 3), padding='same', activation='relu',
kernel_regularizer=l2(l2_reg)),
BatchNormalization(),
Conv2D(64, (3, 3), padding='same', activation='relu',
kernel_regularizer=l2(l2_reg)),
BatchNormalization(),
MaxPooling2D(pool_size=(2, 2)),
Dropout(dropout_rate),
# Block 2: 128 filters
Conv2D(128, (3, 3), padding='same', activation='relu',
kernel_regularizer=l2(l2_reg)),
BatchNormalization(),
Conv2D(128, (3, 3), padding='same', activation='relu',
kernel_regularizer=l2(l2_reg)),
BatchNormalization(),
MaxPooling2D(pool_size=(2, 2)),
Dropout(dropout_rate),
# Block 3: 256 filters
Conv2D(256, (3, 3), padding='same', activation='relu',
kernel_regularizer=l2(l2_reg)),
BatchNormalization(),
Conv2D(256, (3, 3), padding='same', activation='relu',
kernel_regularizer=l2(l2_reg)),
BatchNormalization(),
MaxPooling2D(pool_size=(2, 2)),
Dropout(dropout_rate),
# Block 4: 512 filters
Conv2D(512, (3, 3), padding='same', activation='relu',
kernel_regularizer=l2(l2_reg)),
BatchNormalization(),
Conv2D(512, (3, 3), padding='same', activation='relu',
kernel_regularizer=l2(l2_reg)),
BatchNormalization(),
MaxPooling2D(pool_size=(2, 2)),
Dropout(dropout_rate),
# Classification head
Flatten(),
Dense(512, activation='relu', kernel_regularizer=l2(l2_reg)),
BatchNormalization(),
Dropout(dense_dropout),
Dense(256, activation='relu', kernel_regularizer=l2(l2_reg)),
BatchNormalization(),
Dropout(dense_dropout),
Dense(num_classes, activation='softmax')
], name='custom_emotion_cnn')
return model
def build_custom_cnn_v2(
input_shape: tuple = (*IMAGE_SIZE, NUM_CHANNELS),
num_classes: int = NUM_CLASSES
) -> Model:
"""
Alternative CNN architecture with residual-like connections.
Args:
input_shape: Input image shape
num_classes: Number of emotion classes
Returns:
Keras model
"""
inputs = Input(shape=input_shape)
# Initial convolution
x = Conv2D(32, (3, 3), padding='same', activation='relu')(inputs)
x = BatchNormalization()(x)
# Block 1
x = Conv2D(64, (3, 3), padding='same', activation='relu')(x)
x = BatchNormalization()(x)
x = Conv2D(64, (3, 3), padding='same', activation='relu')(x)
x = BatchNormalization()(x)
x = MaxPooling2D(pool_size=(2, 2))(x)
x = Dropout(0.25)(x)
# Block 2
x = Conv2D(128, (3, 3), padding='same', activation='relu')(x)
x = BatchNormalization()(x)
x = Conv2D(128, (3, 3), padding='same', activation='relu')(x)
x = BatchNormalization()(x)
x = MaxPooling2D(pool_size=(2, 2))(x)
x = Dropout(0.25)(x)
# Block 3
x = Conv2D(256, (3, 3), padding='same', activation='relu')(x)
x = BatchNormalization()(x)
x = Conv2D(256, (3, 3), padding='same', activation='relu')(x)
x = BatchNormalization()(x)
x = MaxPooling2D(pool_size=(2, 2))(x)
x = Dropout(0.25)(x)
# Global pooling and classification
x = GlobalAveragePooling2D()(x)
x = Dense(256, activation='relu')(x)
x = BatchNormalization()(x)
x = Dropout(0.5)(x)
outputs = Dense(num_classes, activation='softmax')(x)
model = Model(inputs=inputs, outputs=outputs, name='custom_emotion_cnn_v2')
return model
def get_model_config() -> dict:
"""
Get the default model configuration.
Returns:
Dictionary with model configuration
"""
return {
"name": "Custom CNN",
"input_shape": (*IMAGE_SIZE, NUM_CHANNELS),
"num_classes": NUM_CLASSES,
"expected_accuracy": "60-68%",
"training_time": "~30 minutes (GPU)",
"parameters": "~5M"
}
if __name__ == "__main__":
# Build and display model summary
model = build_custom_cnn()
model.summary()
print("\nModel configuration:")
config = get_model_config()
for key, value in config.items():
print(f" {key}: {value}")
|