singa-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From GitBox <...@apache.org>
Subject [GitHub] [singa] nudles commented on a change in pull request #662: CUDNN LSTM
Date Sat, 11 Apr 2020 14:41:55 GMT
nudles commented on a change in pull request #662: CUDNN LSTM
URL: https://github.com/apache/singa/pull/662#discussion_r407071481
 
 

 ##########
 File path: python/singa/autograd.py
 ##########
 @@ -3330,6 +3330,94 @@ def step_forward(self, x, h, c, Wx, Wh, Bx, Bh):
         return hout, cout
 
 
+class _RNN(Operation):
+    """ RNN operation with c++ backend
+    """
+    def __init__(self, handle):
+        assert singa.USE_CUDA is True, "Not able to run without CUDA"
+        super(_RNN, self).__init__()
+        self.handle = handle
+
+    def forward(self, x, W):
+        # TODO: CPU forward
+
+        # GPU forward
+        if training:
+            y = singa.GpuRNNForwardTraining(x, W, self.handle)
+            self.inputs = (x, W, y)
+        else:
+            y = singa.GpuRNNForwardInference(x, W, self.handle)
+
+        return y
+
+    def backward(self, dy):
+        assert training is True and hasattr(
+            self, "inputs"), "Please set training as True before do BP. "
+
+        # TODO: CPU backward
+
+        # GPU backward
+        dx = singa.GpuRNNBackwardx(self.inputs[2], dy, self.inputs[1], self.handle)
+        dW = singa.GpuRNNBackwardW(self.inputs[0], self.inputs[2], self.handle)
+        return dx, dW
+
+class RNN_direct(Layer):
+    """ `RNN_direct` class implements with c++ backend and run the operation
+          directly on cuDNN
+
+        While `RNN` class implements with high level singa API
+    """
+    def __init__(self, input_size, hidden_size, rnn_mode="lstm"):
+        """
+            Args:
+                input_size: input feature dim
+                hidden_size: hidden feature dim
+                rnn_mode: accepted value: "vanilla", "tanh", "relu",  "lstm", "gru"
+        """
+        assert singa.USE_CUDA is True, "Not able to run without CUDA"
+
+        self.rnn_mode = rnn_mode
+        self.input_size = input_size
+        self.hidden_size = hidden_size
+
+        # TODO: CPU parameter
+
+        # GPU parameter
+        # cudnn_rnn_mode: 0 - RNN RELU, 1 - RNN TANH, 2 - LSTM, 3 - GRU
+        if self.rnn_mode == "lstm":
+            self.cudnn_rnn_mode = 2
+        elif self.rnn_mode == "vanilla" or self.rnn_mode == "tanh":
+            self.cudnn_rnn_mode = 1
+        elif self.rnn_mode == "relu":
+            self.cudnn_rnn_mode = 0
+        elif self.rnn_mode == "gru":
+            self.cudnn_rnn_mode = 3
+
+    def __call__(self, x):
+        if not hasattr(self, "handle"):
+            cpp_x = singa.VecTensor()
+            [cpp_x.append(i.data) for i in x]
+
+            # TODO: CPU handle
+
+            # GPU handle
+            self.handle = singa.CudnnRNNHandle(cpp_x, self.input_size, self.hidden_size,
self.cudnn_rnn_mode)
+
+            self.W = Tensor(shape=(self.handle.weights_size,),
 
 Review comment:
   if the layer parameters are set outside (e.g., after loading the checkpoint file) via set_params,
there is no need to randomly initialize W.

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services

Mime
View raw message