- class paddle.nn. CTCLoss ( blank=0, reduction='mean' )
An operator integrating the open source Warp-CTC library (https://github.com/baidu-research/warp-ctc) to compute Connectionist Temporal Classification (CTC) loss. It can be aliased as softmax with CTC, since a native softmax activation is interated to the Warp-CTC library to normalize values for each row of the input tensor.
blank (int, optional) – The blank label index of Connectionist Temporal Classification (CTC) loss, which is in the half-opened interval [0, num_classes + 1). The data type must be int32. Default is 0.
reduction (string, optional) – Indicate how to average the loss, the candicates are
'mean', the output loss will be divided by the label_lengths, and then return the mean of quotient; If
'sum', return the sum of loss; If
'none', no reduction will be applied. Default is
log_probs (Tensor): The unscaled probability sequence with padding, which is a 3-D Tensor. The tensor shape is [max_logit_length, batch_size, num_classes + 1], where max_logit_length is the longest length of input logit sequence. The data type should be float32 or float64. labels (Tensor): The ground truth sequence with padding, which must be a 3-D Tensor. The tensor shape is [batch_size, max_label_length], where max_label_length is the longest length of label sequence. The data type must be int32. input_lengths (Tensor): The length for each input sequence, it should have shape [batch_size] and dtype int64. label_lengths (Tensor): The length for each label sequence, it should have shape [batch_size] and dtype int64. norm_by_times (bool, default false) – Whether to normalize the gradients by the number of time-step, which is also the sequence’s length. There is no need to normalize the gradients if reduction mode is ‘mean’.
'none', the shape of loss is [batch_size], otherwise, the shape of loss is . Data type is the same as
- Return type
Tensor, The Connectionist Temporal Classification (CTC) loss between
labels. If attr
# declarative mode import numpy as np import paddle # length of the longest logit sequence max_seq_length = 4 #length of the longest label sequence max_label_length = 3 # number of logit sequences batch_size = 2 # class num class_num = 3 np.random.seed(1) log_probs = np.array([[[4.17021990e-01, 7.20324516e-01, 1.14374816e-04], [3.02332580e-01, 1.46755889e-01, 9.23385918e-02]], [[1.86260208e-01, 3.45560730e-01, 3.96767467e-01], [5.38816750e-01, 4.19194520e-01, 6.85219526e-01]], [[2.04452246e-01, 8.78117442e-01, 2.73875929e-02], [6.70467496e-01, 4.17304814e-01, 5.58689833e-01]], [[1.40386939e-01, 1.98101491e-01, 8.00744593e-01], [9.68261600e-01, 3.13424170e-01, 6.92322612e-01]], [[8.76389146e-01, 8.94606650e-01, 8.50442126e-02], [3.90547849e-02, 1.69830427e-01, 8.78142476e-01]]]).astype("float32") labels = np.array([[1, 2, 2], [1, 2, 2]]).astype("int32") input_lengths = np.array([5, 5]).astype("int64") label_lengths = np.array([3, 3]).astype("int64") log_probs = paddle.to_tensor(log_probs) labels = paddle.to_tensor(labels) input_lengths = paddle.to_tensor(input_lengths) label_lengths = paddle.to_tensor(label_lengths) loss = paddle.nn.CTCLoss(blank=0, reduction='none')(log_probs, labels, input_lengths, label_lengths) print(loss) #[3.9179852 2.9076521] loss = paddle.nn.CTCLoss(blank=0, reduction='mean')(log_probs, labels, input_lengths, label_lengths) print(loss) #[1.1376063]
Defines the computation performed at every call. Should be overridden by all subclasses.
*inputs (tuple) – unpacked tuple arguments
**kwargs (dict) – unpacked dict arguments