-
Notifications
You must be signed in to change notification settings - Fork 2.7k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Master #98
Closed
Closed
Master #98
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
* hotfix: label and backprop * fix: data label must start from 0 tf.one_hot requires Y data labels begin with 0
1) Fix softmax cross entropy 2) Pretty Print Format 3) Fix typo
* Fix to get the correct next close price * Fix to get the correct next close price #2
* Ensure data consistency over Keras and TF in 02-1. * Renamed file (flow, not fflow) * Changed X and y to [1, 2, 3]
* Let's fix travis cost -> cost/loss Revert "cost -> cost/loss" This reverts commit 92a12aa. annotation change cost -> cost/loss * change comment cost -> cost/loss
to do annotation "import matplotlib.pyplot as plt" code. modified an annotation for describing this file on line 1. to erase useless tags on tf.variable_scope() lines. modified "Savor -> Saver" on line 113.
* refactor: add a FC layer 1. Add a FC Layer - #73 2. Add a numpy doc style 3. Explicitly define an activation function in LSTMCell - default is tanh 4. Change to AdamOptimizer 5. Use `with` statement else the session must be closed explicitly 6. No linebreak for the 79 char limit * refactor: nn.tanh -> tanh * add: MNIST Batchnormalization layer * fix: image
* Added XOR Tensorboard Updated .gitignore file to ignore logs directory * Renamed lab-09-7 to lab-09-3
* modify code for compatability with keras 2.x. * change requirement Keras 1.2.2 to 2.0.2. * fix Travis CI Build Error(First try) * Fix Travis CI Build Error(Second try). * Fix Travis CI Build Error(Third try). * Fix Travis CI Build Error(Forth try).
1. pylint does not support py3.6...
Update lab-13-3-mnist_save_restore.py
* - add klab-10-1-mnist_softmax.py based on lab-10-1-mnist_softmax.py ( tested on Ubuntu 14.04 ) * Update klab-10-1-mnist_softmax.py - Update to version Keras 2.0.2 - Tested on Ubuntu 16.04
* Added PyTorch PyTorch code based on TF-Lab code Rest of lab codes will be added. * Update lab-02-1&2-linear_regression.py * Update lab-04-2-multi_variable_linear_regression.py * Update lab-04-3-file_input_linear_regression.py * Update lab-05-1-logistic_regression.py * Update lab-05-2-logistic_regression_diabetes.py * Update lab-06-1-softmax_classifier.py * Update lab-06-2-softmax_zoo_classifier.py * Update lab-09-1-xor.py * Update lab-09-2-xor-nn.py
* Lab 10 MNIST and High-level TF API(dropout, batchnorm, xavier) * PyTorch version lab codes (#88) * Added PyTorch PyTorch code based on TF-Lab code Rest of lab codes will be added. * Update lab-02-1&2-linear_regression.py * Update lab-04-2-multi_variable_linear_regression.py * Update lab-04-3-file_input_linear_regression.py * Update lab-05-1-logistic_regression.py * Update lab-05-2-logistic_regression_diabetes.py * Update lab-06-1-softmax_classifier.py * Update lab-06-2-softmax_zoo_classifier.py * Update lab-09-1-xor.py * Update lab-09-2-xor-nn.py * add Lab 10 MNIST and High-level TF API(dropout, batchnorm, xavier) * add Lab 10 MNIST and High-level TF API(dropout, batchnorm, xavier) * Remove Pytorch files
Update parameters of compute_gradients for TypeError.
W_val and cost_val to W_record and cost_record To understand the purpose of variables easily
This reverts commit d75f37f.
W_val and cost_val to W_record and cost_record To understand the purpose of variables easily
I'm so Sorry to send this PR... I send PR to Master by mistake. Please don't accept this PR |
Please Understand My Mistake... |
W_val and cost_val to W_record and cost_record To understand the purpose of variables easily #99 wasn't refactored by mistake
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Change Variable name of W_val and cost_val
W_val and cost_val to W_record and cost_record
To understand the purpose of variables easily
I did three commits by mistake...