Merge pull request #1072 from lemonviv/dev-postgresql

add cnn model for malaria detection

examples/malaria_cnn/model/cnn.py

@@ -0,0 +1,77 @@
+
+from singa import layer
+from singa import model
+
+
+class CNN(model.Model):
+
+    def __init__(self, num_classes=10, num_channels=1):
+        super(CNN, self).__init__()
+        self.num_classes = num_classes
+        self.input_size = 128
+        self.dimension = 4
+        self.conv1 = layer.Conv2d(num_channels, 32, 3, padding=0, activation="RELU")
+        self.conv2 = layer.Conv2d(32, 64, 3, padding=0, activation="RELU")
+        self.conv3 = layer.Conv2d(64, 64, 3, padding=0, activation="RELU")
+        self.linear1 = layer.Linear(128)
+        self.linear2 = layer.Linear(num_classes)
+        self.pooling1 = layer.MaxPool2d(2, 2, padding=0)
+        self.pooling2 = layer.MaxPool2d(2, 2, padding=0)
+        self.pooling3 = layer.MaxPool2d(2, 2, padding=0)
+        self.relu = layer.ReLU()
+        self.flatten = layer.Flatten()
+        self.softmax_cross_entropy = layer.SoftMaxCrossEntropy()
+        self.sigmoid = layer
+
+    def forward(self, x):
+        y = self.conv1(x)
+        y = self.pooling1(y)
+        y = self.conv2(y)
+        y = self.pooling2(y)
+        y = self.conv3(y)
+        y = self.pooling3(y)
+        y = self.flatten(y)
+        y = self.linear1(y)
+        y = self.relu(y)
+        y = self.linear2(y)
+        return y
+
+    def train_one_batch(self, x, y, dist_option, spars):
+        out = self.forward(x)
+        loss = self.softmax_cross_entropy(out, y)
+
+        if dist_option == 'plain':
+            self.optimizer(loss)
+        elif dist_option == 'half':
+            self.optimizer.backward_and_update_half(loss)
+        elif dist_option == 'partialUpdate':
+            self.optimizer.backward_and_partial_update(loss)
+        elif dist_option == 'sparseTopK':
+            self.optimizer.backward_and_sparse_update(loss,
+                                                      topK=True,
+                                                      spars=spars)
+        elif dist_option == 'sparseThreshold':
+            self.optimizer.backward_and_sparse_update(loss,
+                                                      topK=False,
+                                                      spars=spars)
+        return out, loss
+
+    def set_optimizer(self, optimizer):
+        self.optimizer = optimizer
+
+
+def create_model(**kwargs):
+    """Constructs a CNN model.
+
+    Args:
+        pretrained (bool): If True, returns a pre-trained model.
+
+    Returns:
+        The created CNN model.
+    """
+    model = CNN(**kwargs)
+
+    return model
+
+
+__all__ = ['CNN', 'create_model']