add new model architectures

models/baseline.py

+import torch.nn as nn
+
+from utils import *
+from datasets import MelSpecDataset
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from torch.utils.data import DataLoader
+import pytorch_lightning as pl
+
+from sklearn.metrics import roc_auc_score
+
+# TODO pr-auc
+# TODO f1-score
+
+class CNN(pl.LightningModule):
+    def __init__(self, num_class):
+        super(CNN, self).__init__()
+
+        # init bn
+        self.bn_init = nn.BatchNorm2d(1)
+
+        # layer 1
+        self.conv_1 = nn.Conv2d(1, 64, 3, padding=1)
+        self.bn_1 = nn.BatchNorm2d(64)
+        self.mp_1 = nn.MaxPool2d((2, 4))
+
+        # layer 2
+        self.conv_2 = nn.Conv2d(64, 128, 3, padding=1)
+        self.bn_2 = nn.BatchNorm2d(128)
+        self.mp_2 = nn.MaxPool2d((2, 4))
+
+        # layer 3
+        self.conv_3 = nn.Conv2d(128, 128, 3, padding=1)
+        self.bn_3 = nn.BatchNorm2d(128)
+        self.mp_3 = nn.MaxPool2d((2, 4))
+
+        # layer 4
+        self.conv_4 = nn.Conv2d(128, 128, 3, padding=1)
+        self.bn_4 = nn.BatchNorm2d(128)
+        self.mp_4 = nn.MaxPool2d((3, 5))
+
+        # layer 5
+        self.conv_5 = nn.Conv2d(128, 64, 3, padding=1)
+        self.bn_5 = nn.BatchNorm2d(64)
+        self.mp_5 = nn.MaxPool2d((4, 4))
+
+        # classifier
+        self.dense = nn.Linear(64, num_class)
+        self.dropout = nn.Dropout(0.5)
+
+    def forward(self, x):
+        x = x.unsqueeze(1)
+
+        # init bn
+        x = self.bn_init(x)
+
+        # layer 1
+        x = self.mp_1(nn.ELU()(self.bn_1(self.conv_1(x))))
+
+        # layer 2
+        x = self.mp_2(nn.ELU()(self.bn_2(self.conv_2(x))))
+
+        # layer 3
+        x = self.mp_3(nn.ELU()(self.bn_3(self.conv_3(x))))
+
+        # layer 4
+        x = self.mp_4(nn.ELU()(self.bn_4(self.conv_4(x))))
+
+        # layer 5
+        x = self.mp_5(nn.ELU()(self.bn_5(self.conv_5(x))))
+
+        # classifier
+        x = x.view(x.size(0), -1)
+        x = self.dropout(x)
+        logit = nn.Sigmoid()(self.dense(x))
+
+        return logit
+
+    def my_loss(self, y_hat, y):
+        return F.binary_cross_entropy(y_hat, y)
\ No newline at end of file

models/resnet18.py

+from utils import *
+from datasets import MelSpecDataset
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from torch.utils.data import DataLoader
+import pytorch_lightning as pl
+
+from sklearn.metrics import roc_auc_score
+
+# TODO pr-auc
+# TODO f1-score
+
+from torchvision.models import resnet18
+
+class Network(pl.LightningModule):
+
+    def __init__(self, num_tags):
+        super(Network, self).__init__()
+        self.num_tags = num_tags
+        self.model = resnet18(False)
+        num_features = self.model.fc.in_features
+        self.model.fc = nn.Linear(num_features, self.num_tags)  # overwriting fc layer
+        self.sig = nn.Sigmoid(self.num_tags)
+
+    def forward(self, x):
+        x = self.model(x)
+        x = self.sig(x)
+        return x
+
+    def my_loss(self, y_hat, y):
+        return F.binary_cross_entropy(y_hat, y)
\ No newline at end of file