tf.variable和tf.constant

Question

I was reading the CNN model for text classification, code link , and I was wondering, in line 70, the code:

b = tf.Variable(tf.constant(0.1, shape=[num_classes]), name="b")

Why it can be defined as Variable and constant at same time? is this equal to:

b = tf.Variable(0.1, shape=[num_classes], name="b")

Answer 1

Yes, both are same. Tensorflow implicitly copies tf.constant value into tf.Variable value. Operations a.op,b.op and c.op explain everything

  import tensorflow as tf

    with tf.Session() as sess:
        a=tf.constant(0.1);
        b = tf.Variable(tf.constant(0.1), name="b");
        c = tf.Variable(0.1, name="b");
        sess.run(tf.global_variables_initializer());
        print(a.dtype);
        print(b.dtype);
        print(c.dtype);
        print("**********************")
        print(a.op);
        print(b.op);
        print(c.op);

Output:

<dtype: 'float32'>
<dtype: 'float32_ref'>
<dtype: 'float32_ref'>
**********************

name: "Const_40"
op: "Const"
attr {
  key: "dtype"
  value {
    type: DT_FLOAT
  }
}
attr {
  key: "value"
  value {
    tensor {
      dtype: DT_FLOAT
      tensor_shape {
      }
      float_val: 0.10000000149
    }
  }
}

name: "b_38"
op: "VariableV2"
attr {
  key: "container"
  value {
    s: ""
  }
}
attr {
  key: "dtype"
  value {
    type: DT_FLOAT
  }
}
attr {
  key: "shape"
  value {
    shape {
    }
  }
}
attr {
  key: "shared_name"
  value {
    s: ""
  }
}

name: "b_39"
op: "VariableV2"
attr {
  key: "container"
  value {
    s: ""
  }
}
attr {
  key: "dtype"
  value {
    type: DT_FLOAT
  }
}
attr {
  key: "shape"
  value {
    shape {
    }
  }
}
attr {
  key: "shared_name"
  value {
    s: ""
  }
}