tf.raw_ops.UniformQuantizedConvolution

Perform quantized convolution of quantized Tensor lhs and quantized Tensor rhs. to make quantized output.

tf.raw_ops.UniformQuantizedConvolution(
    lhs,
    rhs,
    lhs_scales,
    lhs_zero_points,
    rhs_scales,
    rhs_zero_points,
    output_scales,
    output_zero_points,
    Tout,
    padding,
    lhs_quantization_min_val,
    lhs_quantization_max_val,
    rhs_quantization_min_val,
    rhs_quantization_max_val,
    output_quantization_min_val,
    output_quantization_max_val,
    window_strides=[],
    explicit_padding=[],
    lhs_dilation=[],
    rhs_dilation=[],
    batch_group_count=1,
    feature_group_count=1,
    dimension_numbers='',
    lhs_quantization_axis=-1,
    rhs_quantization_axis=-1,
    output_quantization_axis=-1,
    name=None
)

Given quantized lhs and quantized rhs, performs quantized dot on lhs and rhs to make quantized output.

lhs and rhs must be Tensors of same rank, and meet following shape conditions.

• lhs_feature % feature_group_count == 0
• lhs_feature % rhs_input_feature == 0
• lhs_feature / feature_group_count == rhs_input_feature
• rhs_output_feature % feature_group_count == 0
• lhs_batch % batch_group_count == 0
• rhs_output_feature % batch_group_count == 0

lhs and rhs must be quantized Tensor, where data value is quantized using the formula:

quantized_data = clip(original_data / scale + zero_point, quantization_min_val, quantization_max_val)

output is also quantized, using the same formula. If rhs is per-tensor quantized, output must be also per-tensor quantized.