def __init__(self, network):
super(NetWithLossClass, self).__init__(auto_prefix=False)
self.loss = P.CTCLoss(ctc_merge_repeated=True)
self.network = network
self.ReduceMean_false = P.ReduceMean(keep_dims=False)
self.squeeze_op = P.Squeeze(0)
self.cast_op = P.Cast()
def __init__(self):
super(ctc_loss, self).__init__()
self.loss = P.CTCLoss(preprocess_collapse_repeated=False,
ctc_merge_repeated=True,
ignore_longer_outputs_than_inputs=False)
self.mean = P.ReduceMean()
self.transpose = P.Transpose()
self.reshape = P.Reshape()
def __init__(self, max_sequence_length, max_label_length, batch_size):
super(CTCLoss, self).__init__()
self.sequence_length = Parameter(Tensor(np.array([max_sequence_length] * batch_size), mstype.int32),
name="sequence_length")
labels_indices = []
for i in range(batch_size):
for j in range(max_label_length):
labels_indices.append([i, j])
self.labels_indices = Parameter(Tensor(np.array(labels_indices), mstype.int64), name="labels_indices")
self.reshape = P.Reshape()
self.ctc_loss = P.CTCLoss(ctc_merge_repeated=True)
def __init__(self):
super(Net, self).__init__()
self.ctc_loss = P.CTCLoss()
'desc_bprop': [3, 3],
'skip': ['backward']}),
('ApplyRMSProp', {
'block': P.ApplyRMSProp(),
'desc_const': [0.9, 0.0, 1e-10, 0.001],
'desc_inputs': [[3, 3], [3, 3], [3, 3], [3, 3]],
'desc_bprop': [3, 3],
'skip': ['backward']}),
('ApplyCenteredRMSProp', {
'block': P.ApplyCenteredRMSProp(),
'desc_const': [0.9, 0.0, 1e-10, 0.001],
'desc_inputs': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3]],
'desc_bprop': [3, 3],
'skip': ['backward']}),
('CTCLoss', {
'block': P.CTCLoss(),
'desc_inputs': [Tensor(np.ones([6, 4, 6]).astype(np.float32)),
Tensor(np.array([[0, 1], [1, 0], [2, 3], [3, 2]]).astype(np.int64)),
Tensor(np.array([1, 2, 3, 4]).astype(np.int32)),
Tensor(np.array([6, 6, 6, 6]).astype(np.int32))],
'desc_bprop': [[4], [6, 4, 6]]}),
('L2Loss_1', {
'block': P.L2Loss(),
'desc_inputs': [Tensor(np.array([1, 2, 3, 4]), mstype.float32)],
'desc_bprop': []}),
('L2Loss_2', {
'block': P.L2Loss(),
'desc_inputs': [Tensor(np.array([[1, 1], [2, 2], [3, 3], [4, 4]]), mstype.float16)],
'desc_bprop': []}),
('ResizeBilinear', {
'block': P.ResizeBilinear((5, 5)),
def __init__(self):
super(Net, self).__init__()
self.loss = P.CTCLoss()
self.div = P.RealDiv()
self.mean = P.ReduceMean()