def binary_cross_entropy_with_logits(input, target, weight=None, reduction='mean', pos_weight=None):
max_val = ops.maximum(-input, 0)
if pos_weight is not None:
log_weight = ((pos_weight - 1) * target) + 1
loss = (1 - target) * input
loss_1 = ops.log(ops.exp(-max_val) + ops.exp(-input - max_val)) + max_val
loss += log_weight * loss_1
else:
loss = (1 - target) * input
loss += max_val
loss += ops.log(ops.exp(-max_val) + ops.exp(-input - max_val))
if weight is not None:
output = loss * weight
else:
output = loss
if reduction == "mean":
return ops.reduce_mean(output)
elif reduction == "sum":
return ops.reduce_sum(output)
else:
return output
def threshold(input, threshold):
return ops.maximum(input, threshold)
def prelu(input, weight):
return ops.maximum(0, input) + weight * ops.minimum(0, input)
def leaky_relu(input, negative_slope=0.01):
return ops.maximum(0, input) + negative_slope * ops.minimum(0, input)
def celu(input, alpha=1.0):
return ops.maximum(0, input) + ops.minimum(0, alpha * (ops.exp(input / alpha) - 1))
def selu(input):
return 1.0507009873554804934193349852946 * \
(ops.maximum(0, input) + ops.minimum(0, 1.6732632423543772848170429916717 * (ops.exp(input) - 1)))
def hardtanh(input, min_val=- 1.0, max_val=1.0):
return ops.maximum(ops.minimum(input, max_val), min_val)