def test_conv2d_api(self, batch_size, in_channels_per_group, H, W, out_channels_per_group, groups, kernel_h, kernel_w, stride_h, stride_w, pad_h, pad_w, dilation, X_scale, X_zero_point, W_scale, W_zero_point, Y_scale, Y_zero_point, use_bias, use_fused, use_channelwise): # Tests the correctness of the conv2d module. in_channels = in_channels_per_group * groups out_channels = out_channels_per_group * groups input_feature_map_size = (H, W) kernel_size = (kernel_h, kernel_w) stride = (stride_h, stride_w) padding = (pad_h, pad_w) dilation = (dilation, dilation) if torch.backends.quantized.engine == 'qnnpack': use_channelwise = False if use_fused: module_name = "QuantizedConvReLU2d" qconv_module = nnq_fused.ConvReLU2d(in_channels, out_channels, kernel_size, stride, padding, dilation, groups, use_bias, padding_mode="zeros") else: module_name = "QuantizedConv2d" qconv_module = nnq.Conv2d(in_channels, out_channels, kernel_size, stride, padding, dilation, groups, use_bias, padding_mode="zeros") conv_module = nn.Conv2d(in_channels, out_channels, kernel_size, stride, padding, dilation, groups, use_bias, padding_mode="zeros") if use_fused: relu_module = nn.ReLU() conv_module = nni.ConvReLU2d(conv_module, relu_module) conv_module = conv_module.float() self._test_conv_api_impl( module_name, qconv_module, conv_module, batch_size, in_channels_per_group, input_feature_map_size, out_channels_per_group, groups, kernel_size, stride, padding, dilation, X_scale, X_zero_point, W_scale, W_zero_point, Y_scale, Y_zero_point, use_bias, use_fused, use_channelwise)
def test_conv2d_relu(self): module = nniq.ConvReLU2d(3, 3, kernel_size=3, stride=1, padding=0, dilation=1, groups=1, bias=True, padding_mode="zeros") self._test_op(module, input_size=[1, 3, 6, 6], generate=False)
def test_conv2d_relu(self): for i, qengine in enumerate(supported_qengines): with override_quantized_engine(qengine): module = nniq.ConvReLU2d(3, 3, kernel_size=3, stride=1, padding=0, dilation=1, groups=1, bias=True, padding_mode="zeros") self._test_op(module, input_size=[1, 3, 6, 6], generate=False, iter=i)