/tfjs

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
296 Open 661 Closed
Author
Filter by author
Labels
Filter by label
Projects
Filter by project
Milestones
Filter by milestone
Assignee
Filter by who’s assigned
Sort
Sort by
Newest
Oldest
Most commented
Least commented
Recently updated
Least recently updated
Most reactions
👍 👎 😄 🎉 😕 ❤️
@tensorflow/tfjs 0.14.2 invalid maxPool and avgPool tests for TensorFlow backend comp:core comp:node.js
#1077 opened Jan 10, 2019 by nkreeger
@nkreeger @dsmilkov
Undocumented exposed API : csvDataset.columnNames() comp:data comp:website
#1075 opened Jan 9, 2019 by bileschi
@kangyizhang
2
Explore using fewer buckets for WebGL texture manager to improve texture reuse. type:performance
#1074 opened Jan 9, 2019 by annxingyuan
@annxingyuan
tf.sqrt() function returns wrong value on Raspberry Pi (3B+) if backend is using "webgl" comp:core type:bug
#1073 opened Jan 9, 2019 by bertlea
@dsmilkov
Should tf.oneHot be available as a chainable op? api comp:core stat:contributions welcome
#1070 opened Jan 7, 2019 by bileschi
3
depthToSpace dataformat comparison not conside about lower case letters may raise exception when use pretrained model by python comp:converter type:bug
#1069 opened Jan 7, 2019 by Frankdog
@pyu10055
tf.data.csv("BAD_URL").forEach iterates over the lines of index.html comp:data type:bug
#1067 opened Jan 3, 2019 by bileschi
@kangyizhang
2
Error: node-gyp; ./Release/libtensorflow.so: file not recognized: File format not recognized type:build/install type:support
#1065 opened Jan 3, 2019 by FarhanMS123
@nkreeger
1
Request to implement correlation layer comp:layers type:feature
#1063 opened Jan 3, 2019 by zboldyga
@caisq
Fix Keras deserialization when using TF eager mode comp:layers type:bug
#1060 opened Jan 2, 2019 by dsmilkov
@caisq
QR-decomposition fails on a specific matrix. type:bug type:support
#1058 opened Dec 28, 2018 by jarno-r
@bileschi
3
Log tensor creation in benchmarking page comp:core
#1057 opened Dec 26, 2018 by annxingyuan
@annxingyuan
tensorflowjs_converter - Cannot convert to keras when kernelInitializer in conv2d setup is string value comp:converter type:bug
#1056 opened Dec 26, 2018 by dsherret
@caisq
Error rebuilding @tensorflow/tfjs-node-gpu with electron comp:node.js type:bug
#1054 opened Dec 24, 2018 by iacovlev-pavel
@nkreeger
1
Updated @tensorflow/tfjs-node-gpu from 0.1.21 to 0.2.1 got: Cannot read property 'name' of null. type:bug
#1053 opened Dec 24, 2018 by iacovlev-pavel
@nkreeger @bileschi
2
Add packed operations testing environment type:performance
#1050 opened Dec 21, 2018 by astojilj
@annxingyuan
Need a util function similar to np.range and np.arange type:feature
#1049 opened Dec 21, 2018 by caisq
Mechanism to enforce use of gl.HALF_FLOAT with both WebGL backends type:performance
#1047 opened Dec 20, 2018 by astojilj
@annxingyuan @rthadur
4
FrozenModel loader handle weight loading for current level relative path comp:converter type:bug
#1045 opened Dec 20, 2018 by pyu10055
@pyu10055
Only upload values to tensors that can be represented on the current device comp:core
#1044 opened Dec 20, 2018 by annxingyuan
@annxingyuan
Converter should warn users if their model weights overflow or underflow float16 bounds comp:converter
#1042 opened Dec 20, 2018 by annxingyuan
@pyu10055
[tfjs-data] tf.data.array()'s batching doesn't handle typed arrays correctly comp:data type:bug
#1041 opened Dec 19, 2018 by caisq
@kangyizhang
2
Implement causal padding in Conv1d comp:models
#1040 opened Dec 19, 2018 by cpury
@dsmilkov @rthadur
dataset.batch() doesn't handle arbitrary nested arrays comp:data
#1038 opened Dec 19, 2018 by dsmilkov
@davidsoergel
7
[Website] Subheadings under Dataset are not alphabetized comp:data comp:website small-project type:docs
#1036 opened Dec 19, 2018 by bileschi
@kangyizhang
ProTip! Exclude everything labeled bug with -label:bug.