This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
class FaceClassifier(nn.Module): | |
def __init__(self, n_vid_features, n_aud_features, n_head, n_layers, n_linear_hidden=30, dropout=0.1): | |
super(FaceClassifier, self).__init__() | |
# video | |
self.vid_pos_encoder = PositionalEncoding(d_model=n_vid_features) | |
vid_encoder_layer = nn.TransformerEncoderLayer(d_model=n_vid_features, nhead=n_head) | |
self.vid_transformer_encoder = nn.TransformerEncoder(vid_encoder_layer, num_layers=n_layers) | |
#self.dropout = nn.Dropout(p=dropout) | |
self.vid_pred = nn.Linear(n_vid_features, 1) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
class FaceAutoencoder(nn.Module): | |
def __init__(self, n_out_channels1=4, n_out_channels2=4, n_out_channels3=1, \ | |
kernel_size1=5, kernel_size2=5, kernel_size3=5): | |
super(FaceAutoencoder, self).__init__() | |
self.encoder = nn.Sequential( | |
nn.Conv2d(N_IN_CHANNELS, out_channels=n_out_channels1, kernel_size=kernel_size1, stride=2, padding=2), # [3,160,160] -> [4, 80, 80] | |
nn.ReLU(), | |
nn.Dropout(0.3), |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Train BCE | Test classification error | ||
---|---|---|---|
Classifier with face crop | 0.693 | 49% | |
Classifier with face crop and aggregation | 0.693 | 47% | |
Classifier without face crop | 0.704 | 51% | |
Classifier without face crop with aggregation | 0.697 | 50% |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Train MSE | Test MSE | ||
---|---|---|---|
Face cropped CAE (hidden dim = 1296) | 0.039 | 0.045 | |
Un-preprocessed CAE (hidden dim = 3600) | 0.014 | 0.014 |