You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert
TensorFlow workshops A few exercises for use at events. How-to run these notebooks Click on the links below to open these notebooks in Colaboratory, a hosted Jupyter notebook environment that's free to use and requires no setup. MNIST IMDB Housing prices Overfitting vs underfitting Text generation Translation Would you like to contribute, or report a bug? Thanks! Can you please file an issue, or e
Release 1.6.0 Breaking Changes Prebuilt binaries are now built against CUDA 9.0 and cuDNN 7. Prebuilt binaries will use AVX instructions. This may break TF on older CPUs. Major Features And Improvements New Optimizer internal API for non-slot variables. Descendants of AdamOptimizer that access _beta[12]_power will need to be updated. tf.estimator.{FinalExporter,LatestExporter} now export stripped
With this change we withdraw our support for the ECMA import keyword hitherto mandated by certain tools. In doing so, TensorBoard compiles in seconds, rather than taking a minute. The ES6 import standard only defines / and ./ prefixed paths. All other paths that exist are undefined. Since most tooling and early-adopter codebases rely on the undefined behavior, the standard itself is mostly syntact
Hi all, I have a question regarding the configuration of SSD. An interesting task for me is to fine-tuning the SSD_mobilenet_v1_coco_2017_11_17 with Bosch small traffic light dataset. However, the default setting is to resize the image into 300 x 300 (image_resizer). Here is the total loss during training. It loss maintains around 6. (Please ignore the overlapping at 5000 steps, due to some re-lau
Release 1.5.0 Breaking Changes Prebuilt binaries are now built against CUDA 9 and cuDNN 7. Starting from 1.6 release, our prebuilt binaries will use AVX instructions. This may break TF on older CPUs. Major Features And Improvements Eager execution preview version is now available. TensorFlow Lite dev preview is now available. CUDA 9 and cuDNN 7 support. Accelerated Linear Algebra (XLA): Add comple
Show and Tell: A Neural Image Caption Generator A TensorFlow implementation of the image-to-text model described in the paper: "Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge." Oriol Vinyals, Alexander Toshev, Samy Bengio, Dumitru Erhan. IEEE transactions on pattern analysis and machine intelligence (2016). Full text available at: http://arxiv.org/abs/1609.06647 Con
System information Have I written custom code (as opposed to using a stock example script provided in TensorFlow): No OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Linux Ubuntu 14.04 TensorFlow installed from (source or binary): Source TensorFlow version (use command below): Python version: Python3.6 Bazel version (if compiling from source): GCC/Compiler version (if compiling from sourc
This change moves //tensorflow/contrib/lite to //tensorflow/lite in preparation for TensorFlow 2.0's deprecation of contrib/. If you refer to TF Lite build targets or headers, you will need to update them manually. If you use TF Lite from the TensorFlow python package, "tf.contrib.lite" now points to "tf.lite". Please update your imports as soon as possible. For more details, see https://groups.go
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
処理を実行中です
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く