Tensorflow中流式F1分數計算中的數據類型不匹配

Question

我試圖在Tensorflow 1.13.1上使用此代碼 。 但是，它會引發以下錯誤：

sherlock@mybox:~/cs273/autocat/bert$ python streaming2.py 
Traceback (most recent call last):
  File "streaming2.py", line 233, in <module>
    tf_f1 = tf_f1_score(t, p)
  File "streaming2.py", line 161, in tf_f1_score
    f1s[2] = tf.reduce_sum(f1 * weights)
  File "/home/sherlock/.virtualenvs/autocat/local/lib/python2.7/site-packages/tensorflow/python/ops/math_ops.py", line 812, in binary_op_wrapper
    return func(x, y, name=name)
  File "/home/sherlock/.virtualenvs/autocat/local/lib/python2.7/site-packages/tensorflow/python/ops/math_ops.py", line 1078, in _mul_dispatch
    return gen_math_ops.mul(x, y, name=name)
  File "/home/sherlock/.virtualenvs/autocat/local/lib/python2.7/site-packages/tensorflow/python/ops/gen_math_ops.py", line 5860, in mul
    "Mul", x=x, y=y, name=name)
  File "/home/sherlock/.virtualenvs/autocat/local/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 547, in _apply_op_helper
    inferred_from[input_arg.type_attr]))
TypeError: Input 'y' of 'Mul' Op has type float64 that does not match type int64 of argument 'x'.

嘗試修復強制轉換一段時間，但未能找到使代碼工作的最小變化。 有人可以幫我這個嗎？

Answer 1

我可以重現你的錯誤：它發生在Python 2但不是3。

因此，要么切換到Python 3，要么使用tf.cast更改代碼

f1 = tf.cast(f1, tf.float64)
f1s[2] = tf.reduce_sum(f1 * weights)

也許在其他地方，但這是個主意