Karpathy 的 LSTM 批处理网络LSTM 批处理网络以批处理方式操作
def checkSequentialMatchesBatch():
""" check LSTM I/O forward/backward interactions """
n,b,d = (5, 3, 4) # sequence length, batch size, hidden size
input_size = 10
WLSTM = LSTM.init(input_size, d) # input size, hidden size
X = np.random.randn(n,b,input_size)
#...
def checkBatchGradient():
""" check that the batch gradient is correct """
# lets gradient check this beast
n,b,d = (5, 3, 4) # sequence length, batch size, hidden size
input_size = 10
WLSTM = LSTM.init(input_size, d) # input size, hidden size
X = np.random.randn(n,b,input_size)
#...
批量申请什么?我只熟悉输入一个热词表示向量,无法理解批量的 LSTM 学习过程。请在文本处理方面进行说明。
提前致谢。