MXnet查看参数的权值

　　我们用MXnet训练好模型之后，有时想看看其中参数的权值，可以用model.get_params()函数，具体的操作见下面的例子。

import mxnet as mx
import numpy as np

import logging
logging.getLogger().setLevel(logging.DEBUG)

# Training data
train_data = np.random.uniform(0, 1, [100, 2])
train_label = np.array([train_data[i][0] + 2 * train_data[i][1] for i in range(100)])
batch_size = 3

# Evaluation Data
eval_data = np.array([[7,2],[6,10],[12,2]])
eval_label = np.array([11,26,16])

train_iter = mx.io.NDArrayIter(train_data,train_label, batch_size, shuffle=True,label_name='lin_reg_label')
eval_iter = mx.io.NDArrayIter(eval_data, eval_label, batch_size, shuffle=False)
X = mx.sym.Variable('data')
Y = mx.symbol.Variable('lin_reg_label')
fully_connected_layer  = mx.sym.FullyConnected(data=X, name='fc1', num_hidden = 1)
lro = mx.sym.LinearRegressionOutput(data=fully_connected_layer, label=Y, name="lro")

model = mx.mod.Module(
    symbol = lro ,
    data_names=['data'],
    label_names = ['lin_reg_label']  # network structure
)

mx.viz.plot_network(symbol=lro)

model.fit(train_iter, eval_iter,
            optimizer_params={'learning_rate':0.01, 'momentum': 0.9},
            num_epoch=50,
            eval_metric='mse',
            batch_end_callback = mx.callback.Speedometer(batch_size, 2))
model.predict(eval_iter).asnumpy()
metric = mx.metric.MSE()
model.score(eval_iter, metric)

keys = model.get_params()[0].keys() # 列出所有权重名称
print(keys)
conv_w = model.get_params()[0]['fc1_weight'] # 获取想要查看的权重信息
bias = model.get_params()[0]['fc1_bias']
print(conv_w.asnumpy()) # 查看具体数值
print(bias.asnumpy())