Related
I want to resize 3D images with a dynamic shape, for instance go from shape (64,64,64,1) to (128,128,128,1). The idea is to unstack the image along one axis, then use tf.image.resize_images and stack them again.
My issue is that tf.unstack can not handle variable sized inputs. If I run my code I obtain "ValueError: Cannot infer num from shape (?, ?, ?, 1)"
I have considered using tf.split instead, however it expects an integer input. Does anybody know a workaround?
Here is an example:
import tensorflow as tf
import numpy as np
def resize_by_axis(image, dim_1, dim_2, ax):
resized_list = []
# Unstack along axis to obtain 2D images
unstack_img_depth_list = tf.unstack(image, axis = ax)
# Resize 2D images
for i in unstack_img_depth_list:
resized_list.append(tf.image.resize_images(i, [dim_1, dim_2], method=1, align_corners=True))
# Stack it to 3D
stack_img = tf.stack(resized_list, axis=ax)
return stack_img
#X = tf.placeholder(tf.float32, shape=[64,64,64,1])
X = tf.placeholder(tf.float32, shape=[None,None,None,1])
# Get new shape
shape = tf.cast(tf.shape(X), dtype=tf.float32) * tf.constant(2, dtype=tf.float32)
x_new = tf.cast(shape[0], dtype=tf.int32)
y_new = tf.cast(shape[1], dtype=tf.int32)
z_new = tf.cast(shape[2], dtype=tf.int32)
# Reshape
X_reshaped_along_xy = resize_by_axis(X, dim_1=x_new, dim_2=y_new, ax=2)
X_reshaped_along_xyz= resize_by_axis(X_reshaped_along_xy, dim_1=x_new, dim_2=z_new, ax=1)
init = tf.global_variables_initializer()
# Run
with tf.Session() as sess:
sess.run(init)
result = X_reshaped_along_xyz.eval(feed_dict={X : np.zeros((64,64,64,1))})
print(result.shape)
tf.image.resize_images can resize multiple images at the same time, but it does not allow you to pick the batch axis. However, you can manipulate the dimensions of the tensor to put the axis that you want first, so it is used as batch dimension, and then put it back after resizing:
import tensorflow as tf
def resize_by_axis(image, dim_1, dim_2, ax):
# Make permutation of dimensions to put ax first
dims = tf.range(tf.rank(image))
perm1 = tf.concat([[ax], dims[:ax], dims[ax + 1:]], axis=0)
# Transpose to put ax dimension first
image_tr = tf.transpose(image, perm1)
# Resize
resized_tr = tf.image.resize_images(image_tr, [dim_1, dim_2],
method=1, align_corners=True)
# Make permutation of dimensions to put ax in its place
perm2 = tf.concat([dims[:ax] + 1, [0], dims[ax + 1:]], axis=0)
# Transpose to put ax in its place
resized = tf.transpose(resized_tr, perm2)
return resized
In your example:
import tensorflow as tf
import numpy as np
X = tf.placeholder(tf.float32, shape=[None, None, None, 1])
# Get new shape
shape = tf.cast(tf.shape(X), dtype=tf.float32) * tf.constant(2, dtype=tf.float32)
x_new = tf.cast(shape[0], dtype=tf.int32)
y_new = tf.cast(shape[1], dtype=tf.int32)
z_new = tf.cast(shape[2], dtype=tf.int32)
# Reshape
X_reshaped_along_xy = resize_by_axis(X, dim_1=x_new, dim_2=y_new, ax=2)
X_reshaped_along_xyz = resize_by_axis(X_reshaped_along_xy, dim_1=x_new, dim_2=z_new, ax=1)
init = tf.global_variables_initializer()
# Run
with tf.Session() as sess:
sess.run(init)
result = X_reshaped_along_xyz.eval(feed_dict={X : np.zeros((64, 64, 64, 1))})
print(result.shape)
# (128, 128, 128, 1)
I have a Tensor as below:
y = tf.placeholder(tf.float32, [None, 3],name="output")
I want to multiply the last of the 3 dimension tensor.
I have tried this:
outputs_with_multiplier = y
outputs_with_multiplier[-1] = tf.multiply(outputs_with_multiplier[-1],tf.constant(2.0))
I received the following error:
outputs_with_multiplier[-1] = tf.multiply(outputs_with_multiplier[-1],tf.constant(2.0))
TypeError: 'Tensor' object does not support item assignment
I have check the following questions for reference, but I didn't found them helpful, may be because I didn't understood them.
1) Tensorflow - matmul of input matrix with batch data
2) Tensor multiplication in Tensorflow
Kindly, help me multiply the Tensors dimension so that it work smoothly.
For example if this is my y = [[1,2,3],[2,3,4],[3,4,5],[2,5,7],[8,9,10],[0,3,2]] So I want to make it outputs_with_multiplier = [[1,2,6],[2,3,8],[3,4,10],[2,5,14],[8,9,20],[0,3,4]]
Please let me know if there is any solution to this.
You can't do an item assignment but you can create a new Tensor. The key is to multiply the first 2 columns by 1 and the 3rd column by 2.
x = tf.placeholder(tf.float32, [None, 3], name="output")
y = tf.constant([[1.0, 1.0, 2.0]])
z = tf.multiply(x, y)
sess = tf.Session()
sess.run(z, feed_dict={x: [[1,2,3],[2,3,4],[3,4,5],[2,5,7],[8,9,10],[0,3,2]]})
This is my piece of code for GAN where the model is being initialized, everything is working and only the relevant code to the problem is present here:
z = Input(shape=(100+384,))
img = self.generator(z)
print("before: ",img) #128x128x3 shape, dtype=tf.float32
temp = tf.get_variable("temp", [1, 128, 3],dtype=tf.float32)
img=tf.concat(img,temp)
print("after: ",img) #error ValueError: Incompatible type conversion requested to type 'int32' for variable of type 'float32_ref'
valid = self.discriminator(img)
self.combined = Model(z, valid)
I have 128x128x3 images to generate, what I want to do is give 129x128x3 images to discriminator and the 1x128x3 text-embedding matrix is concatenated with the image while training. But I have to specify at the start the shape of tensors and input value that each model i.e. GEN and DISC will get. Gen takes 100noise+384embedding matrix and generates 128x128x3 image which is again embeded by some embedding i.e. 1x128x3 and is fed to DISC. So my question is that whether this approach is correct or not? Also, if it is correct or it makes sense then how can I specific the stuff needed at the start so that it does not give me errors like incompatible shape because at the start I have to add these lines:-
z = Input(shape=(100+384,))
img = self.generator(z) #128x128x3
valid = self.discriminator(img) #should be 129x128x3
self.combined = Model(z, valid)
But img is of 128x128x3 and is later during training changed to 129x128x3 by concatenating embedding matrix. So how can I change "img" from 128,128,3 to 129,128,3 in the above code either by padding or appending another tensor or by simply reshaping which of course is not possible. Any help will be much much appreciated. Thanks.
The first argument of tf.concat should be the list of tensors, while the second is the axis along which to concatenate. You could concatenate the img and temp tensors as follows:
import tensorflow as tf
img = tf.ones(shape=(128, 128, 3))
temp = tf.get_variable("temp", [1, 128, 3], dtype=tf.float32)
img = tf.concat([img, temp], axis=0)
with tf.Session() as sess:
print(sess.run(tf.shape(img)))
UPDATE: Here you have a minimal example showing why you get the error "AttributeError: 'Tensor' object has no attribute '_keras_history'". This error pops up in the following snippet:
from keras.layers import Input, Lambda, Dense
from keras.models import Model
import tensorflow as tf
img = Input(shape=(128, 128, 3)) # Shape=(batch_size, 128, 128, 3)
temp = Input(shape=(1, 128, 3)) # Shape=(batch_size, 1, 128, 3)
concat = tf.concat([img, temp], axis=1)
print(concat.get_shape())
dense = Dense(1)(concat)
model = Model(inputs=[img, temp], outputs=dense)
This happens because tensor concatis not a Keras tensor, and therefore some of the typical Keras tensors' attributes (such as _keras_history) are missing. To overcome this problem, you need to encapsulate all TensorFlow tensors into a Keras Lambda layer:
from keras.layers import Input, Lambda, Dense
from keras.models import Model
import tensorflow as tf
img = Input(shape=(128, 128, 3)) # Shape=(batch_size, 128, 128, 3)
temp = Input(shape=(1, 128, 3)) # Shape=(batch_size, 1, 128, 3)
concat = Lambda(lambda x: tf.concat([x[0], x[1]], axis=1))([img, temp])
print(concat.get_shape())
dense = Dense(1)(concat)
model = Model(inputs=[img, temp], outputs=dense)
I want to slice a tensor in "None" dimension.
For example,
tensor = tf.placeholder(tf.float32, shape=[None, None, 10], name="seq_holder")
sliced_tensor = tensor[:,1:,:] # it works well!
but
# Assume that tensor's shape will be [3,10, 10]
tensor = tf.placeholder(tf.float32, shape=[None, None, 10], name="seq_holder")
sliced_seq = tf.slice(tensor, [0,1,0],[3, 9, 10]) # it doens't work!
It is same that i get a message when i used another place_holder to feed size parameter for tf.slice().
The second methods gave me "Input size (depth of inputs) must be accessible via shape inference" error message.
I'd like to know what's different between two methods and what is more tensorflow-ish way.
[Edited]
Whole code is below
import tensorflow as tf
import numpy as np
print("Tensorflow for tests!")
vec_dim = 5
num_hidden = 10
# method 1
input_seq1 = np.random.random([3,7,vec_dim])
# method 2
input_seq2 = np.random.random([5,10,vec_dim])
shape_seq2 = [5,9,vec_dim]
# seq: [batch, seq_len]
seq = tf.placeholder(tf.float32, shape=[None, None, vec_dim], name="seq_holder")
# Method 1
sliced_seq = seq[:,1:,:]
# Method 2
seq_shape = tf.placeholder(tf.int32, shape=[3])
sliced_seq = tf.slice(seq,[0,0,0], seq_shape)
cell = tf.contrib.rnn.GRUCell(num_units=num_hidden)
init_state = cell.zero_state(tf.shape(seq)[0], tf.float32)
outputs, last_state = tf.nn.dynamic_rnn(cell, sliced_seq, initial_state=init_state)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
# method 1
# states = sess.run([sliced_seq], feed_dict={seq:input_seq1})
# print(states[0].shape)
# method 2
states = sess.run([sliced_seq], feed_dict={seq:input_seq2, seq_shape:shape_seq2})
print(states[0].shape)
Your problem is exactly described by issue #4590
The problem is that tf.nn.dynamic_rnn needs to know the size of the last dimension in the input (the "depth"). Unfortunately, as the issue points out, currently tf.slice cannot infer any output size if any of the slice ranges are not fully known at graph construction time; therefore, sliced_seq ends up having a shape (?, ?, ?).
In your case, the first issue is that you are using a placeholder of three elements to determine the size of the slice; this is not the best approach, since the last dimension should never change (even if you later pass vec_dim, it could cause errors). The easiest solution would be to turn seq_shape into a placeholder of size 2 (or even two separate placeholders), and then do the slicing like:
sliced_seq = seq[:seq_shape[0], :seq_shape[1], :]
For some reason, the NumPy-style indexing seems to have better shape inference capabilities, and this will preserve the size of the last dimension in sliced_seq.
I've found that indexing still is an open issue in tensorflow (#206), so I'm wondering what I could use as a workaround at the moment. I want to index/slice a row/column of a matrix based on a variable that changes for every training example.
What I've tried so far:
Slicing based on placeholder (doesn't work)
The following (working) code slices based on a fixed number.
import tensorflow as tf
import numpy as np
x = tf.placeholder("float")
y = tf.slice(x,[0],[1])
#initialize
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)
#run
result = sess.run(y, feed_dict={x:[1,2,3,4,5]})
print(result)
However, it seems that I can't simply replace one of these fixed numbers with a tf.placeholder. The following code gives me the error "TypeError: List of Tensors when single Tensor expected."
import tensorflow as tf
import numpy as np
x = tf.placeholder("float")
i = tf.placeholder("int32")
y = tf.slice(x,[i],[1])
#initialize
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)
#run
result = sess.run(y, feed_dict={x:[1,2,3,4,5],i:0})
print(result)
This sounds like the brackets around [i] are too much, but removing them doesn't help either. How to use a placeholder/variable as index?
Slicing based on python variable (doesn't backprop/update properly)
I've also tried using a normal python variable as index. This does not lead to an error, but the network doesn't learn anything while training. I suppose because the changing variable is not properly registered, the graph is malformed and updates don't work?
Slicing via one-hot vector + multiplication (works, but is slow)
One workaround I found is using a one-hot vector. Making a one-hot vector in numpy, passing this using a placeholder, then doing the slicing via matrix multiplication. This works, but is quite slow.
Any ideas how to efficiently slice/index based on a variable?
Slicing based on a placeholder should work just fine. It looks like you are running into a type error, due to some subtle issues of shapes and types. Where you have the following:
x = tf.placeholder("float")
i = tf.placeholder("int32")
y = tf.slice(x,[i],[1])
...you should instead have:
x = tf.placeholder("float")
i = tf.placeholder("int32")
y = tf.slice(x,i,[1])
...and then you should feed i as [0] in the call to sess.run().
To make this a little clearer, I would recommend rewriting the code as follows:
import tensorflow as tf
import numpy as np
x = tf.placeholder(tf.float32, shape=[None]) # 1-D tensor
i = tf.placeholder(tf.int32, shape=[1])
y = tf.slice(x, i, [1])
#initialize
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)
#run
result = sess.run(y, feed_dict={x: [1, 2, 3, 4, 5], i: [0]})
print(result)
The additional shape arguments to the tf.placeholder op help to ensure that the values you feed have the appropriate shapes, and also that TensorFlow will raise an error if the shapes are not correct.
If you have an extra dimension, this works.
import tensorflow as tf
import numpy as np
def reorder0(e, i, length):
'''
e: a two dimensional tensor
i: a one dimensional int32 tensor, of shape (e.shape[0])
returns: a tensor of the same shape as e, where the jth entry is entry i[j] from e
'''
return tf.concat(
[ tf.expand_dims( e[i[j],:], axis=0) for j in range(length) ],
axis=0
)
e = tf.placeholder(tf.float32, shape=(2,3,5), name='e' ) # sentences, words, embedding
i = tf.placeholder(tf.int32, shape=(2,3), name='i' ) # for each word, index of parent
p = tf.concat(
[ tf.expand_dims(reorder0(e[k,:,:], i[k,:], 3), axis=0) for k in range(2) ],
axis=0,
name='p'
)
#initialize
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)
#run
result = sess.run(p, feed_dict={
e: [
( (1.0,1.1,1.2,1.3,1.4),(2.0,2.1,2.2,2.3,2.4),(3.0,3.1,3.2,3.3,3.4) ),
( (21.0,21.1,21.2,21.3,21.4),(22.0,22.1,22.2,22.3,22.4),(23.0,23.1,23.2,23.3,23.4) ),
],
i: [ (1,1,1), (2,0,2)]
})
print(result)
If the sizes are not known when building the model, use TensorArray.
e = tf.placeholder(tf.float32, shape=(3,5) ) # words, embedding
i = tf.placeholder(tf.int32, shape=(3) ) # for each word, index of parent
#p = reorder0(e, i, 3)
a = tf.TensorArray(
tf.float32,
size=e.get_shape()[0],
dynamic_size=True,
infer_shape= True,
element_shape=e.get_shape()[1],
clear_after_read = False
)
#initialize
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)
#run
result = sess.run(
a.unstack(e).gather(i),
feed_dict={
e: ( (1.0,1.1,1.2,1.3,1.4),(2.0,2.1,2.2,2.3,2.4),(3.0,3.1,3.2,3.3,3.4) ),
#( (21.0,21.1,21.2,21.3,21.4),(22.0,22.1,22.2,22.3,22.4),(23.0,23.1,23.2,23.3,23.4) ),
i: (2,0,2)
}
)
print(result)