Can not squeeze dim[3], expected a dimension of 1, got 2 for 'generator/Squeeze'

[lyzhangjm]

Hi, when I run the generate,
.sg_upconv(dim=2, act='sigmoid', bn=False).sg_squeeze()
there is a error:
ValueError: Can not squeeze dim[3], expected a dimension of 1, got 2 for 'generator/Squeeze' (op: 'Squeeze') with input shapes: [?,384,1,2].
what is it?
thank you.

[YazhouZhang0709]

@lyzhangjm Hi, did you solve this problem? I met the same error here.

[lyzhangjm]

@YazhouZhang0709 ， I have not solved the problem. I don't know the reason.

[zhiweiSunday]

@YazhouZhang0709 Hi,I have also met this problem.Do you have any method to solve this？

[jchook]

I am also getting this issue after a successful train on 100k rows. Same error in both Python 2.7 and 3.5.

It seems the issue may be a Tensorflow version mismatch. Seems there have been some breaking changes.

Traceback (most recent call last):
  File "generate.py", line 55, in <module>
    .sg_upconv(dim=2, act='sigmoid', bn=False).sg_squeeze())
  File "/usr/local/lib/python2.7/dist-packages/sugartensor/sg_main.py", line 170, in wrapper
    out = func(tensor, tf.sg_opt(kwargs))
  File "/usr/local/lib/python2.7/dist-packages/sugartensor/sg_transform.py", line 119, in sg_squeeze
    return tf.squeeze(tensor, opt.axis, name=opt.name)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/array_ops.py", line 2394, in squeeze
    return gen_array_ops._squeeze(input, axis, name)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_array_ops.py", line 5202, in _squeeze
    "Squeeze", input=input, squeeze_dims=squeeze_dims, name=name)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
    op_def=op_def)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2958, in create_op
    set_shapes_for_outputs(ret)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2209, in set_shapes_for_outputs
    shapes = shape_func(op)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2159, in call_with_requiring
    return call_cpp_shape_fn(op, require_shape_fn=True)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/common_shapes.py", line 627, in call_cpp_shape_fn
    require_shape_fn)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/common_shapes.py", line 691, in _call_cpp_shape_fn_impl
    raise ValueError(err.message)
ValueError: Can not squeeze dim[3], expected a dimension of 1, got 2 for 'generator/Squeeze' (op: 'Squeeze') with input shapes: [?,384,1,2].

[jeanjerome]

Hi, did anybody solves that ?
Stop at same error with tensorflow 1.0.0 as sugartensor requirement.
That's a real bag of bones between variable parameters values and hard-coded values...

@buriburisuri Any help on that ?

[jeanjerome]

Well, found that to make it work but should be used with caution !!

[yiyetingyu]

I met the same problem, I don't know how to solve it.

[maakvolunteer]

raise ValueError(err.message)
ValueError: Can not squeeze dim[2], expected a dimension of 1, got 150 for 'QAModel/Squeeze_300' (op: 'Squeeze') with input shapes: [?,300,150].

[anshen666]

@lyzhangjm Hi, did you solve this problem? I met the same error here.

你好，请问你解决了这个问题了吗？可以和你交流一下吗？我的邮箱：[email protected] 微信：loveanshen QQ:519838354

[anshen666]

I met the same problem, I don't know how to solve it.

你好，请问你解决了这个问题了吗？可以和你交流一下吗？我的邮箱：[email protected] 微信：loveanshen QQ:519838354

[ouzzane]

avez-vous résolu ce problème? J'ai rencontré la même erreur ici
tensorflow.python.framework.errors_impl.InvalidArgumentError: Can not squeeze dim[3], expected a dimension of 1, got 3