TypeError: ('An update must have the same type as the original shared variable about deeplearningbook HOT 14 CLOSED

from deeplearningbook.

@innovation-cat 您好！这段代码来自您那本书的第29页2.3.2节Logistic回归。请问该如何修正这个错误呢？

from deeplearningbook.

from deeplearningbook.

@innovation-cat 您好！第29页的完整代码如下

import numpy as np
import theano
import theano.tensor as T

N, M = 1000, 78
X = np.random.randn(N, M)
Y = np.random.randint(low=0, high=2, size=N)

train_X = theano.shared(value = X)
train_Y = theano.shared(value = Y)

batch_size = 100
w_value = np.random.randn(M)

w = theano.shared(value=w_value, name='w')
b = theano.shared(value=0.0, name='b')

x = T.dmatrix('x')
y = T.ivector('y')

index = T.iscalar('index')
output = 1.0 / (1.0 + T.exp(-T.dot(x, w)-b))
predict = output > 0.5

loss = -y * T.log(output) - (1-y)*T.log(1-output)

cost = T.mean(loss)+0.001*(w**2).sum()
gw, gb = T.grad(cost, [w, b])

train = theano.function(
inputs = [index],
outputs = cost,
updates = [(w, w-0.1 * gw), (b, b-0.1 * gb)],
givens = {x : train_X[index * batch_size : (index + 1)*batch_size],
y : train_Y[index * batch_size : (index + 1) * batch_size]}
)

from deeplearningbook.

这个运行后并没有报错误

from deeplearningbook.

Hi @innovation-cat 我刚又用Python3.5运行了一遍，依然有错误提示。

/usr/bin/python3.5 demo_01.py
Using cuDNN version 6021 on context None
Mapped name None to device cuda0: GeForce GTX 970 (0000:01:00.0)
Traceback (most recent call last):
File "/home/xxx/demo_01.py", line 33, in
y : train_Y[index * batch_size : (index + 1) * batch_size]})
File "/usr/local/lib/python3.5/dist-packages/Theano-0.10.0.dev1-py3.5.egg/theano/compile/function.py", line 325, in function
output_keys=output_keys)
File "/usr/local/lib/python3.5/dist-packages/Theano-0.10.0.dev1-py3.5.egg/theano/compile/pfunc.py", line 449, in pfunc
no_default_updates=no_default_updates)
File "/usr/local/lib/python3.5/dist-packages/Theano-0.10.0.dev1-py3.5.egg/theano/compile/pfunc.py", line 219, in rebuild_collect_shared
cloned_v = clone_v_get_shared_updates(v, copy_inputs_over)
File "/usr/local/lib/python3.5/dist-packages/Theano-0.10.0.dev1-py3.5.egg/theano/compile/pfunc.py", line 93, in clone_v_get_shared_updates
clone_v_get_shared_updates(i, copy_inputs_over)
File "/usr/local/lib/python3.5/dist-packages/Theano-0.10.0.dev1-py3.5.egg/theano/compile/pfunc.py", line 93, in clone_v_get_shared_updates
clone_v_get_shared_updates(i, copy_inputs_over)
File "/usr/local/lib/python3.5/dist-packages/Theano-0.10.0.dev1-py3.5.egg/theano/compile/pfunc.py", line 93, in clone_v_get_shared_updates
clone_v_get_shared_updates(i, copy_inputs_over)
File "/usr/local/lib/python3.5/dist-packages/Theano-0.10.0.dev1-py3.5.egg/theano/compile/pfunc.py", line 93, in clone_v_get_shared_updates
clone_v_get_shared_updates(i, copy_inputs_over)
File "/usr/local/lib/python3.5/dist-packages/Theano-0.10.0.dev1-py3.5.egg/theano/compile/pfunc.py", line 93, in clone_v_get_shared_updates
clone_v_get_shared_updates(i, copy_inputs_over)
File "/usr/local/lib/python3.5/dist-packages/Theano-0.10.0.dev1-py3.5.egg/theano/compile/pfunc.py", line 96, in clone_v_get_shared_updates
[clone_d[i] for i in owner.inputs], strict=rebuild_strict)
File "/usr/local/lib/python3.5/dist-packages/Theano-0.10.0.dev1-py3.5.egg/theano/gof/graph.py", line 239, in clone_with_new_inputs
new_inputs[i] = curr.type.filter_variable(new)
File "/usr/local/lib/python3.5/dist-packages/Theano-0.10.0.dev1-py3.5.egg/theano/tensor/type.py", line 234, in filter_variable
self=self))
TypeError: Cannot convert Type TensorType(int64, vector) (of Variable Subtensor{int32:int32:}.0) into Type TensorType(int32, vector). You can try to manually convert Subtensor{int32:int32:}.0 into a TensorType(int32, vector).

Process finished with exit code 1

from deeplearningbook.

我分别在python2.7+theano0.8和python3.6+theano0.9两个环境运行过，代码并没有报错，我看了你用的是theano0.10dev，这个版本还是一个测试版本，估计起码明年才正式发布，试试安装0.8或者0.9，不要用0.10，这个版本可能还不稳定

from deeplearningbook.

Hi @innovation-cat 谢谢！我看到最后一句提示说TypeError: Cannot convert Type TensorType(int64, vector) (of Variable Subtensor{int32:int32:}.0) into Type TensorType(int32, vector). You can try to manually convert Subtensor{int32:int32:}.0 into a TensorType(int32, vector). 请问下这个提示是针对哪条语句的？为什么会有这样的提示？我Theano不太熟，请问这个类型转换应怎么写？

from deeplearningbook.

from deeplearningbook.

Hi @innovation-cat 加上allow_input_downcast=True后，仍有错误提示，而且提示内容没有变化。请问下

Type TensorType(int64, vector) (of Variable Subtensor{int32:int32:}.0) into Type TensorType(int32, vector)

这句是由哪个参数引起的？TensorType(int64, vector) (of Variable Subtensor{int32:int32:}.0)具体是指哪个变量？另外为什么会需要转换成 TensorType(int32, vector)？怎么用cast实现这个转换？谢谢！

from deeplearningbook.

from deeplearningbook.

Hi @innovation-cat 谢谢您的回复。请问下TensorType(int64, vector) (of Variable Subtensor{int32:int32:}.0)具体是指y : train_Y[index * batch_size : (index + 1) * batch_size]}中的哪个变量？如果是y的话，我在y的定义语句之后加上y=T.cast(y, 'int32')也不起作用。

from deeplearningbook.

不是说y，而是说train_Y[index * batch_size : (index + 1) * batch_size]的结果是TensorType(int64, vector)，但y的定义是TensorType(int32, vector)，所以报了这个类型错误，不过这里面 train_Y[index * batch_size : (index + 1) * batch_size]的结果应该也是TensorType(int32, vector)，所以应该是版本的bug，不是你的代码有bug

from deeplearningbook.

@innovation-cat 是版本bug的说法有道理，我之前把train_Y的定义修改为train_Y = theano.shared(value=Y, allow_downcast=True)也还是会报这个错误，谢谢！

from deeplearningbook.