- 25 Jul, 2018 2 commits
-
-
derekjchow authored
Object detection: Added explanation how to manually download and use protoc
-
aquariusjay authored
PiperOrigin-RevId: 205684720
-
- 24 Jul, 2018 6 commits
-
-
Raymond Yuan authored
A3C Blog Post
-
pkulzc authored
-
SRIRAM VETURI authored
The following error doesn't occur with the above change in code. Error: Argument must be a dense tensor: range(0, 3) - got shape [3], but wanted [] The range function on the vairable 'num_boundaries' should be a list! Please merge this request!
-
Raymond Yuan authored
-
Hui Hui authored
-
Liang-Chieh Chen authored
-
- 23 Jul, 2018 22 commits
-
-
Asim Shankar authored
Use float32 metrics in mnist_eager
-
Lukasz Kaiser authored
Deep Contextual Bandits code for tensorflow/models
-
Carlos Riquelme authored
-
Carlos Riquelme authored
-
Carlos Riquelme authored
-
Carlos Riquelme authored
-
Carlos Riquelme authored
-
Carlos Riquelme authored
-
Carlos Riquelme authored
-
Carlos Riquelme authored
-
Carlos Riquelme authored
-
Carlos Riquelme authored
-
Carlos Riquelme authored
-
Carlos Riquelme authored
-
Carlos Riquelme authored
-
Carlos Riquelme authored
-
Carlos Riquelme authored
-
Carlos Riquelme authored
-
Carlos Riquelme authored
-
Raymond Yuan authored
-
Raymond Yuan authored
-
Raymond Yuan authored
-
- 21 Jul, 2018 6 commits
-
-
sauercrowd authored
-
Billy Lamberta authored
Fix notebook text
-
pkulzc authored
Updating comments in export_tflite_ssd_graph scripts
-
Raymond Yuan authored
-
Igor Ganichev authored
float32 should be fine for mnist loss and accuracy metrics and float64 is not available on TPUs.
-
Raymond Yuan authored
-
- 20 Jul, 2018 4 commits
-
-
Hyungjun Lim authored
* Sentiment analysis implmenttion in pure Keras. - This is an update for the sentiment analysis model's pure Keras version. -- Converting it from the version using Tensorflow's estimator, as it has a issue that affects the accuracy of the model negatively. - The implementation is with the reference to paddle version. -- Adjustment of the hyperparameters was done to achieve the accuracy of ~90% * addressing comments * addressig comments also adding from __future__ import absolute_import from __future__ import division from __future__ import print_function for each module as it seemingly is a standard in the repo. * addressing the final comment.
-
Raymond Yuan authored
-
Lukasz Kaiser authored
Fixed minor bug in STEVE which sometimes prevented resuming experiments.
-
Mark Daoust authored
-