mindspore.nn.Conv2dBnFoldQuantOneConv
- class mindspore.nn.Conv2dBnFoldQuantOneConv(in_channels, out_channels, kernel_size, stride=1, pad_mode='same', padding=0, dilation=1, group=1, eps=1e-05, momentum=0.997, has_bias=False, weight_init='normal', bias_init='zeros', beta_init='zeros', gamma_init='ones', mean_init='zeros', var_init='ones', fake=True, quant_config=quant_config_default, quant_dtype=QuantDtype.INT8)[source]
2D convolution which use the convolution layer statistics once to calculate Batch Normalization operation folded construct.
This part is a more detailed overview of Conv2d operation. For more details about Quantization, please refer to the implementation of class of FakeQuantWithMinMaxObserver,
FakeQuantWithMinMaxObserver
.\[ \begin{align}\begin{aligned}w_{q}=quant(\frac{w}{\sqrt{var_{G}+\epsilon}}*\gamma )\\b=\frac{-\mu _{G} }{\sqrt{var_{G}+\epsilon }}*\gamma +\beta\\y=w_{q}\times x+b\end{aligned}\end{align} \]where \(quant\) is the continuous execution of quant and dequant, you can refer to the implementation of subclass of FakeQuantWithMinMaxObserver,
mindspore.nn.FakeQuantWithMinMaxObserver
. mu _{G} and var_{G} represent the global mean and variance respectively.- Parameters
in_channels (int) – The number of input channel \(C_{in}\).
out_channels (int) – The number of output channel \(C_{out}\).
kernel_size (Union[int, tuple[int]]) – Specifies the height and width of the 2D convolution window.
stride (Union[int, tuple[int]]) – Specifies stride for all spatial dimensions with the same value. Default: 1.
pad_mode (str) – Specifies padding mode. The optional values are “same”, “valid”, “pad”. Default: “same”.
padding (Union[int, tuple[int]]) – Implicit paddings on both sides of the x. Default: 0.
dilation (Union[int, tuple[int]]) – Specifies the dilation rate to use for dilated convolution. Default: 1.
group (int) – Splits filter into groups, in_ channels and out_channels must be divisible by the number of groups. Default: 1.
eps (float) – Parameters for Batch Normalization. Default: 1e-5.
momentum (float) – Parameters for Batch Normalization op. Default: 0.997.
has_bias (bool) – Specifies whether the layer uses a bias vector, which is temporarily invalid. Default: False.
weight_init (Union[Tensor, str, Initializer, numbers.Number]) – Initializer for the convolution kernel. Default: ‘normal’.
bias_init (Union[Tensor, str, Initializer, numbers.Number]) – Initializer for the bias vector. Default: ‘zeros’.
beta_init (Union[Tensor, str, Initializer, numbers.Number]) – Initializer for the beta vector. Default: ‘zeros’.
gamma_init (Union[Tensor, str, Initializer, numbers.Number]) – Initializer for the gamma vector. Default: ‘ones’.
mean_init (Union[Tensor, str, Initializer, numbers.Number]) – Initializer for the mean vector. Default: ‘zeros’.
var_init (Union[Tensor, str, Initializer, numbers.Number]) – Initializer for the variance vector. Default: ‘ones’.
fake (bool) – Whether Conv2dBnFoldQuant Cell adds FakeQuantWithMinMaxObserver. Default: True.
quant_config (QuantConfig) – Configures the types of quant observer and quant settings of weight and activation. Note that, QuantConfig is a special namedtuple, which is designed for quantization and can be generated by
mindspore.compression.quant.create_quant_config()
method. Default: QuantConfig with both items set to defaultFakeQuantWithMinMaxObserver
.quant_dtype (QuantDtype) – Specifies the FakeQuant datatype. Default: QuantDtype.INT8.
- Inputs:
x (Tensor) - Tensor of shape \((N, C_{in}, H_{in}, W_{in})\).
- Outputs:
Tensor of shape \((N, C_{out}, H_{out}, W_{out})\).
- Raises
TypeError – If in_channels, out_channels or group is not an int.
TypeError – If kernel_size, stride, padding or dilation is neither an int nor a tuple.
TypeError – If has_bias or fake is not a bool.
TypeError – If data_format is not a string.
ValueError – If in_channels, out_channels, kernel_size, stride or dilation is less than 1.
ValueError – If padding is less than 0.
ValueError – If pad_mode is not one of ‘same’, ‘valid’, ‘pad’.
- Supported Platforms:
Ascend
GPU
Examples
>>> import mindspore >>> from mindspore.compression import quant >>> from mindspore import Tensor >>> qconfig = quant.create_quant_config() >>> conv2d_bnfold = nn.Conv2dBnFoldQuantOneConv(1, 1, kernel_size=(2, 2), stride=(1, 1), pad_mode="valid", ... weight_init="ones", quant_config=qconfig) >>> x = Tensor(np.array([[[[1, 0, 3], [1, 4, 7], [2, 5, 2]]]]), mindspore.float32) >>> result = conv2d_bnfold(x) >>> print(result) [[[[5.9296875 13.8359375] [11.859375 17.78125]]]]