QuantizedConv2DTranspose¶

class paddle.nn.quant.quant_layers. QuantizedConv2DTranspose ( layer, weight_bits=8, activation_bits=8, moving_rate=0.9, weight_quantize_type='abs_max', activation_quantize_type='abs_max', weight_pre_layer=None, act_pre_layer=None, weight_quant_layer=None, act_quant_layer=None ) [source]

The computational logic of QuantizedConv2DTranspose is the same with Conv2DTranspose. The only difference is that its inputs are all fake quantized.

Examples

>>> import paddle
>>> import paddle.nn as nn
>>> from paddle.nn.quant.quant_layers import QuantizedConv2DTranspose

>>> x_var = paddle.uniform((2, 4, 8, 8), dtype='float32', min=-1., max=1.)
>>> conv = nn.Conv2DTranspose(4, 6, (3, 3))
>>> conv_quantized = QuantizedConv2DTranspose(conv)
>>> y_quantized = conv_quantized(x_var)
>>> y_var = conv(x_var)
>>> print(y_var.shape)
[2, 6, 10, 10]
>>> print(y_quantized.shape)
[2, 6, 10, 10]

forward ( input, output_size=None )

forward¶

Defines the computation performed at every call. Should be overridden by all subclasses.

Parameters

• *inputs (tuple) – unpacked tuple arguments

• **kwargs (dict) – unpacked dict arguments