Class | Description |
---|---|
Dequantize |
Dequantize the 'input' tensor into a float Tensor.
|
Dequantize.Options |
Optional attributes for
Dequantize |
FakeQuantWithMinMaxArgs |
Fake-quantize the 'inputs' tensor, type float to 'outputs' tensor of same type.
|
FakeQuantWithMinMaxArgs.Options |
Optional attributes for
FakeQuantWithMinMaxArgs |
FakeQuantWithMinMaxArgsGradient |
Compute gradients for a FakeQuantWithMinMaxArgs operation.
|
FakeQuantWithMinMaxArgsGradient.Options |
Optional attributes for
FakeQuantWithMinMaxArgsGradient |
FakeQuantWithMinMaxVars |
Fake-quantize the 'inputs' tensor of type float via global float scalars `min`
|
FakeQuantWithMinMaxVars.Options |
Optional attributes for
FakeQuantWithMinMaxVars |
FakeQuantWithMinMaxVarsGradient |
Compute gradients for a FakeQuantWithMinMaxVars operation.
|
FakeQuantWithMinMaxVarsGradient.Options |
Optional attributes for
FakeQuantWithMinMaxVarsGradient |
FakeQuantWithMinMaxVarsPerChannel |
Fake-quantize the 'inputs' tensor of type float and one of the shapes: `[d]`,
|
FakeQuantWithMinMaxVarsPerChannel.Options |
Optional attributes for
FakeQuantWithMinMaxVarsPerChannel |
FakeQuantWithMinMaxVarsPerChannelGradient |
Compute gradients for a FakeQuantWithMinMaxVarsPerChannel operation.
|
FakeQuantWithMinMaxVarsPerChannelGradient.Options |
Optional attributes for
FakeQuantWithMinMaxVarsPerChannelGradient |
Quantize<T> |
Quantize the 'input' tensor of type float to 'output' tensor of type 'T'.
|
Quantize.Options |
Optional attributes for
Quantize |
QuantizeAndDequantize<T extends Number> |
Quantizes then dequantizes a tensor.
|
QuantizeAndDequantize.Options |
Optional attributes for
QuantizeAndDequantize |
QuantizeDownAndShrinkRange<U> |
Convert the quantized 'input' tensor into a lower-precision 'output', using the
|
RequantizationRange |
Computes a range that covers the actual values present in a quantized tensor.
|
Requantize<U> |
Converts the quantized `input` tensor into a lower-precision `output`.
|
Copyright © 2022. All rights reserved.