Embedding量化

import paddle
import paddle.fluid as fluid
import paddleslim.quant as quant
paddle.enable_static()
train_program = fluid.Program()
with fluid.program_guard(train_program):
    input_word = fluid.data(name="input_word", shape=[None, 1], dtype='int64')
    input_emb = fluid.embedding(
        input=input_word,
        is_sparse=False,
        size=[100, 128],
        param_attr=fluid.ParamAttr(name='emb',
        initializer=fluid.initializer.Uniform(-0.005, 0.005)))

infer_program = train_program.clone(for_test=True)

use_gpu = True
place = fluid.CUDAPlace(0) if use_gpu else fluid.CPUPlace()
exe = fluid.Executor(place)
exe.run(fluid.default_startup_program())

# 量化为8比特，Embedding参数的体积减小4倍，精度有轻微损失
config = {
         'quantize_op_types': ['lookup_table'],
         'lookup_table': {
             'quantize_type': 'abs_max',
             'quantize_bits': 8,
             'dtype': 'int8'
             }
         }

'''
# 量化为16比特，Embedding参数的体积减小2倍，精度损失很小
config = {
         'quantize_op_types': ['lookup_table'],
         'lookup_table': {
             'quantize_type': 'abs_max',
             'quantize_bits': 16,
             'dtype': 'int16'
             }
         }
'''

quant_program = quant.quant_embedding(infer_program, place, config)