Use tf.boolean_mask to filter out values at indices that don't meet the required threshold.
# remove values from `X` in interval(lo, hi) mask = tf.math.logical_or(tf.lesser(X, lo), tf.greater(X, hi)) X = tf.boolean_mask(X, mask)
In your case, you would define soft_acc as
def soft_acc(y_true, y_pred):
mask = tf.math.logical_or(tf.greater(y_pred, 0.55), tf.lesser(y_pred, 0.45))
y_true2 = tf.boolean_mask(y_true, mask)
y_pred2 = tf.boolean_mask(y_pred, mask)
return K.mean(K.equal(K.round(y_true2), K.round(y_pred2)))Use tf.boolean_mask to filter out values anycodings_tensorflow at indices that don't meet the required anycodings_tensorflow threshold.,I tried using the soft_acc function on anycodings_tensorflow stackoverflow and adding an if else to the anycodings_tensorflow beginning to filter out the near 50/50s.,I want to be able to know the rounded anycodings_tensorflow accuracy of my neural network when the anycodings_tensorflow prediction is above or below a certain anycodings_tensorflow threshold. For example, I want it to only anycodings_tensorflow calculate accuracy when the prediction is anycodings_tensorflow above 0.55 or below 0.45 in order to filter anycodings_tensorflow out near 50/50 cases.,TypeError: Using a tf.Tensor as a Python anycodings_tensorflow bool is not allowed. Use if t is not None: anycodings_tensorflow instead of if t: to test if a tensor is anycodings_tensorflow defined, and use TensorFlow ops such as anycodings_tensorflow tf.cond to execute subgraphs conditioned on anycodings_tensorflow the value of a tensor.
I tried using the soft_acc function on anycodings_tensorflow stackoverflow and adding an if else to the anycodings_tensorflow beginning to filter out the near 50/50s.
def soft_acc(y_true, y_pred):
if y_pred > 0.55 or y_pred < 0.45:
return K.mean(K.equal(K.round(y_true), K.round(y_pred)))Use tf.boolean_mask to filter out values anycodings_tensorflow at indices that don't meet the required anycodings_tensorflow threshold.
# remove values from `X` in interval(lo, hi) mask = tf.math.logical_or(tf.lesser(X, lo), tf.greater(X, hi)) X = tf.boolean_mask(X, mask)
In your case, you would define soft_acc anycodings_tensorflow as
def soft_acc(y_true, y_pred):
mask = tf.math.logical_or(tf.greater(y_pred, 0.55), tf.lesser(y_pred, 0.45))
y_true2 = tf.boolean_mask(y_true, mask)
y_pred2 = tf.boolean_mask(y_pred, mask)
return K.mean(K.equal(K.round(y_true2), K.round(y_pred2)))So I have a 1-d tensor T and an index i and need to remove i-th element from a tensor T, much like in pure python T.remove(i).,How about removing more than 1 elements by indices? Is there a faster way than looping ?,Thank you guys, this solves the problem. But there must be a way less clunky solution, I believe.,One possible way would be to index the tensor for all other values:
I’ve tried to do this:
i = 2 T = torch.tensor([1, 2, 3, 4, 5]) T = torch.cat([T[0: i], T[i + 1: -1]])
Update, this works
i = 2 T = torch.tensor([1, 2, 3, 4, 5]) T = torch.cat([T[0: i], T[i + 1: ]])
One possible way would be to index the tensor for all other values:
x = torch.arange(10) value = 5 x = x[x != value]
I’m getting this error
Expected object of scalar type Float but got scalar type Long for argument #2 'other'
For example
i = [0, 100, 2, 5, 10, 200, 500] T = torch.randn(1000) T_new = T[whose elements not equal to elements in i]
Hello, I think, A more elegant way will be to use a function like:
import torch as th
def th_delete(tensor, indices):
mask = th.ones(tensor.numel(), dtype = th.bool)
mask[indices] = False
return tensor[mask]It can be used like this:
>>> a = th.arange(5) >>> a tensor([0, 1, 2, 3, 4]) >>> th_delete(a, [0, 3, 4]) tensor([1, 2]) >>> th_delete(a, [1]) tensor([0, 2, 3, 4]) >>> th_delete(a, th.tensor([1, 4])) tensor([0, 2, 3])
And even like this:
>>> a = th.arange(5) >>> a tensor([0, 1, 2, 3, 4]) >>> th_delete(a, 1) tensor([0, 2, 3, 4])
Last updated 2022-06-28 UTC.
View aliases
Compat aliases for migration
See Migration guide for more details.
tf.where( condition, x = None, y = None, name = None )
Here condition is a 1-axis bool tensor with 2 True values. The result
has a shape of [2,1]
tf.where([True, False, False, True]).numpy() array([ [0], [3] ])
Here condition is a 2-axis integer tensor, with 3 non-zero values. The
result has a shape of [3, 2].
tf.where([ [1, 0, 0], [1, 0, 1] ]).numpy() array([ [0, 0], [1, 0], [1, 2] ])
These indices are the same that tf.sparse.SparseTensor would use to
represent the condition tensor:
sparse = tf.sparse.from_dense(float_tensor) sparse.indices.numpy() array([ [0, 0, 0], [0, 1, 1], [0, 2, 0], [0, 2, 1], [1, 2, 0] ])
A complex number is considered non-zero if either the real or imaginary component is non-zero:
tf.where([complex(0.), complex(1.), 0 + 1 j, 1 + 1 j]).numpy() array([ [1], [2], [3] ])
Last Updated : 18 Jul, 2021,GATE CS 2021 Syllabus
Syntax:
index_add_(dim, index, ensor) -- - > Tensor
Output:
tensor([ [1., 3., 5., 7., 9.], [0., 0., 0., 0., 0.], [1., 3., 5., 7., 9.], [0., 0., 0., 0., 0.], [1., 3., 5., 7., 9.] ])
Output:
tensor([
[1., 1., 1., 1.],
[1., 1., 1., 1.],
[1., 1., 1., 1.],
[1., 1., 1., 1.]
])