add dataloaders to resnet, make resnet experiment work

experiments/experiment_resnets.py

 from utils import CURR_RUN_PATH, USE_GPU, logger
 from pytorch_lightning import Trainer
-from pytorch_lightning.callbacks import EarlyStopping
+from pytorch_lightning.callbacks import EarlyStopping, ModelCheckpoint
 from test_tube import Experiment
 from models.resnet18 import Network
+import os
 
 
 def run():
@@ -13,21 +14,30 @@ def run():
 
     # callbacks
     early_stop = EarlyStopping(
-        monitor='val_loss',  # TODO: check if this exists
+        monitor='val_loss',
         patience=50,
         verbose=True,
-        mode='min'  # TODO: check if correct
+        mode='min'
+    )
+
+    checkpoint_callback = ModelCheckpoint(
+        filepath=os.path.join(CURR_RUN_PATH, 'best.ckpt'),
+        save_best_only=True,
+        verbose=True,
+        monitor='val_loss',
+        mode='min'
     )
 
     if USE_GPU:
         trainer = Trainer(gpus=[0], distributed_backend='ddp',
                           experiment=exp, max_nb_epochs=500, train_percent_check=1.0,
-                          fast_dev_run=False, early_stop_callback=early_stop)
+                          fast_dev_run=False, early_stop_callback=early_stop,
+                          checkpoint_callback=checkpoint_callback)
     else:
         trainer = Trainer(experiment=exp, max_nb_epochs=1, train_percent_check=0.1,
                           fast_dev_run=True)
 
-    model = Network()  # TODO num_tags
+    model = Network(56)  # TODO num_tags
 
     print(model)
 

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 models.shared_stuff import tng_dataloader, val_dataloader, test_dataloader, \
+    validation_end, training_step, validation_step
 
 from sklearn.metrics import roc_auc_score
 
 # TODO pr-auc
 # TODO f1-score
 
-from torchvision.models import resnet18
+from models.resnet_arch import ResNet, BasicBlock
 
 class Network(pl.LightningModule):
 
     def __init__(self, num_tags):
         super(Network, self).__init__()
         self.num_tags = num_tags
-        self.model = resnet18(False)  # TODO: need to check if optimizer recognizes these parameters
-        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)
+        self.model = nn.Sequential(
+            ResNet(BasicBlock, [2, 2, 2, 2], num_classes=self.num_tags),
+            nn.Sigmoid())
+        # TODO: need to check if optimizer recognizes these parameters
+        # num_features = self.model.fc.in_features
+        # self.model.fc = nn.Linear(num_features, self.num_tags)  # overwriting fc layer
+        # self.sig = nn.Sigmoid()
 
     def forward(self, x):
         x = self.model(x)
-        x = self.sig(x)
+        # x = self.sig(x)
         return x
 
     def my_loss(self, y_hat, y):
         return F.binary_cross_entropy(y_hat, y)
 
     def configure_optimizers(self):
-        return [torch.optim.Adam(self.parameters(), lr=0.001)]
\ No newline at end of file
+        return [torch.optim.Adam(self.parameters(), lr=0.001)]
+
+    def training_step(self, data_batch, batch_nb):
+        return training_step(self, data_batch, batch_nb)
+
+    def validation_step(self, data_batch, batch_nb):
+        return validation_step(self, data_batch, batch_nb)
+
+    def validation_end(self, outputs):
+        return validation_end(outputs)
+
+    @pl.data_loader
+    def tng_dataloader(self):
+        return tng_dataloader()
+
+    @pl.data_loader
+    def val_dataloader(self):
+        return val_dataloader()
+
+    @pl.data_loader
+    def test_dataloader(self):
+        return test_dataloader()

models/resnet_arch.py

+import torch.nn as nn
+import torch
+
+def conv3x3(in_planes, out_planes, stride=1, groups=1, dilation=1):
+    """3x3 convolution with padding"""
+    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
+                     padding=dilation, groups=groups, bias=False, dilation=dilation)
+
+
+def conv1x1(in_planes, out_planes, stride=1):
+    """1x1 convolution"""
+    return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False)
+
+
+class BasicBlock(nn.Module):
+    expansion = 1
+    __constants__ = ['downsample']
+
+    def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1,
+                 base_width=64, dilation=1, norm_layer=None):
+        super(BasicBlock, self).__init__()
+        if norm_layer is None:
+            norm_layer = nn.BatchNorm2d
+        if groups != 1 or base_width != 64:
+            raise ValueError('BasicBlock only supports groups=1 and base_width=64')
+        if dilation > 1:
+            raise NotImplementedError("Dilation > 1 not supported in BasicBlock")
+        # Both self.conv1 and self.downsample layers downsample the input when stride != 1
+        self.conv1 = conv3x3(inplanes, planes, stride)
+        self.bn1 = norm_layer(planes)
+        self.relu = nn.ReLU(inplace=True)
+        self.conv2 = conv3x3(planes, planes)
+        self.bn2 = norm_layer(planes)
+        self.downsample = downsample
+        self.stride = stride
+
+    def forward(self, x):
+        identity = x
+
+        out = self.conv1(x)
+        out = self.bn1(out)
+        out = self.relu(out)
+
+        out = self.conv2(out)
+        out = self.bn2(out)
+
+        if self.downsample is not None:
+            identity = self.downsample(x)
+
+        out += identity
+        out = self.relu(out)
+
+        return out
+
+
+class Bottleneck(nn.Module):
+    expansion = 4
+
+    def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1,
+                 base_width=64, dilation=1, norm_layer=None):
+        super(Bottleneck, self).__init__()
+        if norm_layer is None:
+            norm_layer = nn.BatchNorm2d
+        width = int(planes * (base_width / 64.)) * groups
+        # Both self.conv2 and self.downsample layers downsample the input when stride != 1
+        self.conv1 = conv1x1(inplanes, width)
+        self.bn1 = norm_layer(width)
+        self.conv2 = conv3x3(width, width, stride, groups, dilation)
+        self.bn2 = norm_layer(width)
+        self.conv3 = conv1x1(width, planes * self.expansion)
+        self.bn3 = norm_layer(planes * self.expansion)
+        self.relu = nn.ReLU(inplace=True)
+        self.downsample = downsample
+        self.stride = stride
+
+    def forward(self, x):
+        identity = x
+
+        out = self.conv1(x)
+        out = self.bn1(out)
+        out = self.relu(out)
+
+        out = self.conv2(out)
+        out = self.bn2(out)
+        out = self.relu(out)
+
+        out = self.conv3(out)
+        out = self.bn3(out)
+
+        if self.downsample is not None:
+            identity = self.downsample(x)
+
+        out += identity
+        out = self.relu(out)
+
+        return out
+
+class ResNet(nn.Module):
+
+    def __init__(self, block, layers, num_classes=1000, zero_init_residual=False,
+                 groups=1, width_per_group=64, replace_stride_with_dilation=None,
+                 norm_layer=None):
+        super(ResNet, self).__init__()
+        if norm_layer is None:
+            norm_layer = nn.BatchNorm2d
+        self._norm_layer = norm_layer
+
+        self.inplanes = 64
+        self.dilation = 1
+        if replace_stride_with_dilation is None:
+            # each element in the tuple indicates if we should replace
+            # the 2x2 stride with a dilated convolution instead
+            replace_stride_with_dilation = [False, False, False]
+        if len(replace_stride_with_dilation) != 3:
+            raise ValueError("replace_stride_with_dilation should be None "
+                             "or a 3-element tuple, got {}".format(replace_stride_with_dilation))
+        self.groups = groups
+        self.base_width = width_per_group
+        self.conv1 = nn.Conv2d(1, self.inplanes, kernel_size=7, stride=2, padding=3,
+                               bias=False)
+        self.bn1 = norm_layer(self.inplanes)
+        self.relu = nn.ReLU(inplace=True)
+        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
+        self.layer1 = self._make_layer(block, 64, layers[0])
+        self.layer2 = self._make_layer(block, 128, layers[1], stride=2,
+                                       dilate=replace_stride_with_dilation[0])
+        self.layer3 = self._make_layer(block, 256, layers[2], stride=2,
+                                       dilate=replace_stride_with_dilation[1])
+        self.layer4 = self._make_layer(block, 512, layers[3], stride=2,
+                                       dilate=replace_stride_with_dilation[2])
+        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
+        self.fc = nn.Linear(512 * block.expansion, num_classes)
+
+        for m in self.modules():
+            if isinstance(m, nn.Conv2d):
+                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
+            elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
+                nn.init.constant_(m.weight, 1)
+                nn.init.constant_(m.bias, 0)
+
+        # Zero-initialize the last BN in each residual branch,
+        # so that the residual branch starts with zeros, and each residual block behaves like an identity.
+        # This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677
+        if zero_init_residual:
+            for m in self.modules():
+                if isinstance(m, Bottleneck):
+                    nn.init.constant_(m.bn3.weight, 0)
+                elif isinstance(m, BasicBlock):
+                    nn.init.constant_(m.bn2.weight, 0)
+
+    def _make_layer(self, block, planes, blocks, stride=1, dilate=False):
+        norm_layer = self._norm_layer
+        downsample = None
+        previous_dilation = self.dilation
+        if dilate:
+            self.dilation *= stride
+            stride = 1
+        if stride != 1 or self.inplanes != planes * block.expansion:
+            downsample = nn.Sequential(
+                conv1x1(self.inplanes, planes * block.expansion, stride),
+                norm_layer(planes * block.expansion),
+            )
+
+        layers = []
+        layers.append(block(self.inplanes, planes, stride, downsample, self.groups,
+                            self.base_width, previous_dilation, norm_layer))
+        self.inplanes = planes * block.expansion
+        for _ in range(1, blocks):
+            layers.append(block(self.inplanes, planes, groups=self.groups,
+                                base_width=self.base_width, dilation=self.dilation,
+                                norm_layer=norm_layer))
+
+        return nn.Sequential(*layers)
+
+    def forward(self, x):
+        x = self.conv1(x)
+        x = self.bn1(x)
+        x = self.relu(x)
+        x = self.maxpool(x)
+
+        x = self.layer1(x)
+        x = self.layer2(x)
+        x = self.layer3(x)
+        x = self.layer4(x)
+
+        x = self.avgpool(x)
+        x = torch.flatten(x, 1)
+        x = self.fc(x)
+
+        return x
\ No newline at end of file