ValueError: Cannot feed value of shape (50, 128, 128, 3) for Tensor 'FID_Inception_Net/ExpandDims:0', which has shape '(1, ?, ?, 3)

[uuutty]

I met a error for 'tf.Tensor._shape cannot be assigned', so I change the
o._shape = tf.TensorShape(new_shape)
to
o.set_shape(tf.TensorShape(new_shape)) mentioned by another project's commit
Unfortunately, this work fine for above project, but this time I still get a
ValueError: Cannot feed value of shape (50, 128, 128, 3) for Tensor 'FID_Inception_Net/ExpandDims:0', which has shape '(1, ?, ?, 3).
I find if I print the tensor shape use get_shape() before and after the set_shape call in function _get_inception_layer, the Tensor shape don't change. It seems the set_shape don't work.
Does anyone have any ideas? Thanks

[HRamses]

Hi!
The problem seems to be, that in newer versions of Tf it is not possible to "lower" the information about a dimension of a given tensor, as is explained here: https://stackoverflow.com/questions/35451948/clarification-on-tf-tensor-set-shape
That's why I suspect, that the "fix" you are referring to doesn't really work.
I will try to find a solution.

[foofighter112]

Hi, I also noticed that it is not possible to change shapes of tensors which were created with validate_shape=True (see tensorflow/tensorflow#5492), which might be the culprit here.

I changed the _get_inception_layer function in a hacky way to make it run, and I update the shape by doing o.__dict__['_shape_val'] = tf.TensorShape(new_shape). I also changed if shape._dims is not None: to if shape._dims != []:

Here is my function.

def _get_inception_layer(sess):
    """Prepares inception net for batched usage and returns pool_3 layer. """
    layername = 'FID_Inception_Net/pool_3:0'
    pool3 = sess.graph.get_tensor_by_name(layername)
    ops = pool3.graph.get_operations()
    for op_idx, op in enumerate(ops):
        for o in op.outputs:
            shape = o.get_shape()
            if shape._dims != []:
              shape = [s.value for s in shape]
              new_shape = []
              for j, s in enumerate(shape):
                if s == 1 and j == 0:
                  new_shape.append(None)
                else:
                  new_shape.append(s)
              o.__dict__['_shape_val'] = tf.TensorShape(new_shape)
    return pool3

I suspect the returned FID scores are still correct, but I haven't checked against reported scores.

[goncalomordido]

It seems to match my previous results! Thanks.

[HRamses]

@foofighter112 : Thanks! Would it be ok for you if I adopt your solution after doing some correctness tests?

[foofighter112]

Of course!

…

On 15 May 2018, at 10:23, HRamses ***@***.***> wrote: @foofighter112 : Thanks! Would it be ok for you if I adopt your solution after doing some correctness tests? — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or mute the thread.

[uuutty]

@foofighter112 I find it work well for me, Thanks!

[youkaichao]

@foofighter112 I test your code with batch size 128 on cifar10 real data and get FID of 7.2

Then I test original code with batch size 1 on cifar10 real data and get FID of 7.1

so your code works well.

(I randomly select 10000 images from [0, 25000) and [25000. 50000) in training data and test the FID.)

[congyucn]

@foofighter112 I used your code, but it still doesn't work. My Tf is 1.4.0

[WillSuen]

Tensorflow version 1.4.0, still get the same error
change batch_size to 1 can fix this error, but running speed is slow

[happycoding1996]

@WillSuen I got the same issue on 1.4.0. Super slow running speed when using batch size 1.

[kabef94]

Hi, I also noticed that it is not possible to change shapes of tensors which were created with validate_shape=True (see tensorflow/tensorflow#5492), which might be the culprit here.

I changed the _get_inception_layer function in a hacky way to make it run, and I update the shape by doing o.__dict__['_shape_val'] = tf.TensorShape(new_shape). I also changed if shape._dims is not None: to if shape._dims != []:

Here is my function.

def _get_inception_layer(sess):
    """Prepares inception net for batched usage and returns pool_3 layer. """
    layername = 'FID_Inception_Net/pool_3:0'
    pool3 = sess.graph.get_tensor_by_name(layername)
    ops = pool3.graph.get_operations()
    for op_idx, op in enumerate(ops):
        for o in op.outputs:
            shape = o.get_shape()
            if shape._dims != []:
              shape = [s.value for s in shape]
              new_shape = []
              for j, s in enumerate(shape):
                if s == 1 and j == 0:
                  new_shape.append(None)
                else:
                  new_shape.append(s)
              o.__dict__['_shape_val'] = tf.TensorShape(new_shape)
    return pool3

I suspect the returned FID scores are still correct, but I haven't checked against reported scores.

Hi.. I'm a little new to python.. where exactly should this be changed??

[hhqweasd]

replace
o.dict['_shape_val'] = tf.TensorShape(new_shape)
with
o._shape = tf.TensorShape(new_shape)
Done!

[Sanka-R]

I am still having this issue, this fix didnt work
pyathon 3.6.8
tf 1.5.1

changing the batch size to 1 also didnt work

[youngjung]

Hi, I also noticed that it is not possible to change shapes of tensors which were created with validate_shape=True (see tensorflow/tensorflow#5492), which might be the culprit here.

I changed the _get_inception_layer function in a hacky way to make it run, and I update the shape by doing o.__dict__['_shape_val'] = tf.TensorShape(new_shape). I also changed if shape._dims is not None: to if shape._dims != []:

Here is my function.

def _get_inception_layer(sess):
    """Prepares inception net for batched usage and returns pool_3 layer. """
    layername = 'FID_Inception_Net/pool_3:0'
    pool3 = sess.graph.get_tensor_by_name(layername)
    ops = pool3.graph.get_operations()
    for op_idx, op in enumerate(ops):
        for o in op.outputs:
            shape = o.get_shape()
            if shape._dims != []:
              shape = [s.value for s in shape]
              new_shape = []
              for j, s in enumerate(shape):
                if s == 1 and j == 0:
                  new_shape.append(None)
                else:
                  new_shape.append(s)
              o.__dict__['_shape_val'] = tf.TensorShape(new_shape)
    return pool3

I suspect the returned FID scores are still correct, but I haven't checked against reported scores.

It worked for tf 1.5.0 + python 3.6.7

[zhangxixi0904]

replace
o.dict['_shape_val'] = tf.TensorShape(new_shape)
with
o._shape = tf.TensorShape(new_shape)
Done!

it works for tensorflow 1.14.1 python3.5

[echooooHsu]

replace
o.dict['_shape_val'] = tf.TensorShape(new_shape)
with
o._shape = tf.TensorShape(new_shape)
Done!
it works for tensorflow 1.4.0 python3.6

[jian3xiao]

when using two image files to compute FID, the code use get_activations_from_files() ，there is maybe a mistake in 222 "n_batches = n_imgs//batch_size + 1". I think '+1' should be removed.