- When creating a TestCase, all vars set up in setUp should belong to the class –
- The functions run in alphabetical order but it’s not something I should depend on
- Is there a way in Keras to apply different weights to a cost function? · Issue #2115 · keras-team/keras is a really nice discussion with options, especially the latter part of it.
- ValueError: No gradients provided for any variable in Tensorflow - Stack Overflow
When you do
annotation_pred = tf.to_float(tf.argmax(out, dimension=4, name='prediction')), you get an index of the max value in your tensor. This index can’t be derivated, thus the gradient can’t flow throught this operation.
So as your loss is only defined by this value, and the gradient can’t flow throught it, no gradient can be calculated for your network.
- GitHub - fchollet/keras-resources: Directory of tutorials and open-source code repositories for working with Keras, the Python deep learning library
Tensorflow eager execution
Makes everything slower by about 2-4 times.
tf.keras.backend.in_train_phase | TensorFlow Core r2.0 selects x if training, y otherwise. This will be very handy later.Read more...
Tensorflow object has no attribute
Zsh calculator inside CLI
(As suggested by arzzen/calc.plugin.zsh: zsh calculator - with support for basic math)Read more...
Python shell get last value
_ does the magic. Can be used in expressions too.
Mixing keras and tf.keras is bad karma; only the same one should be used and it should be tf.keras.Read more...
Intellij idea breakpoints
I should read this sometime: Breakpoints - Help | IntelliJ IDEARead more...
Tensorflow custom metrics return
Keras custom metrics raises error when update_state returns an op. · Issue #30711 · tensorflow/tensorflow · GitHub - forget about returning ops in custom metrics, internal Google TPU issue thing. It’s supposed not to work. Error was:
TypeError: To be compatible with tf.contrib.eager.defun, Python functions must return zero or more Tensors; in compilation of <function Function._defun_with_scope.
.wrapped_fn at 0xb34ec5d08>, found return value of type <class 'tensorflow.python.framework.ops.Operation'>, which is not a Tensor.
CRF and probability tutorial / explanation / presentation
I really should resurrect my link DB.Read more...
Tensorflow custom cost functions with different weights
Taskwarrior modifier .isnt for “not equal”
Edited my “someday” report:Read more...
Moving to a new apt
Ausstattung für die erste eigene Wohnung - Checkliste is a nice checklist :)
Remark.js presentation change font size inside slideRead more...
Tensorflow gradient propagation
Intellij ideavim toggle case
Added the following to
map <leader>c :action EditorToggleCase<CR>
Tensorflow metrics ignored if loss doesn’t get defined
So I don’t forget, Metrics ignored when using
model.add_loss() (like in VAE example) · Issue #9459 · keras-team/keras · GitHub currently happens.
gt command to search tabs
:buffer works as a best-match tab filtering thingy, this in nice with 30+ tabs when tab number doesn’t cut it anymore