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

System Message: ERROR/3 (/usr/local/lib/python3.8/site-packages/paddle/nn/quant/quant_layers.py:docstring of paddle.nn.quant.quant_layers.QuantizedConv2DTranspose, line 6)

Error in “code-block” directive: maximum 1 argument(s) allowed, 52 supplied.

.. code-block:: python
   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)
   y_quantized_np = y_quantized.numpy()
   y_np = y_var.numpy()
   print(y_np.shape, y_quantized_np.shape)
   # (2, 6, 10, 10), (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