GitHub - tensorflow/model-analysis: Model analysis tools for TensorFlow
The recommended way to install TFMA is using the PyPI package: pip install tensorflow-model-analysis pip install from https://pypi-nightly.tensorflow.org pip install -i https://pypi-nightly.tensorflow.org/simple tensorflow-model-analysis pip install from the HEAD of the git: pip install git+https://github.com/tensorflow/model-analysis.git#egg=tensorflow_model_analysis pip install from a released v
GitHub - tensorflow/transform: Input pipeline framework
TensorFlow Transform is a library for preprocessing data with TensorFlow. tf.Transform is useful for data that requires a full-pass, such as: Normalize an input value by mean and standard deviation. Convert strings to integers by generating a vocabulary over all input values. Convert floats to integers by assigning them to buckets based on the observed data distribution. TensorFlow has built-in su
Swift for TensorFlow
Swift for TensorFlow was an experiment in the next-generation platform for machine learning, incorporating the latest research across machine learning, compilers, differentiable programming, systems design, and beyond. It was archived in February 2021. Some significant achievements from this project include: Added language-integrated differentiable programming into the Swift language. This work co
Release TensorFlow 1.7.0 · tensorflow/tensorflow
Release 1.7.0 Major Features And Improvements Eager mode is moving out of contrib, try tf.enable_eager_execution(). Graph rewrites emulating fixed-point quantization compatible with TensorFlow Lite, supported by new tf.contrib.quantize package. Easily customize gradient computation with tf.custom_gradient. TensorBoard Debugger Plugin, the graphical user interface (GUI) of TensorFlow Debugger (tfdb
workshops/README.md at master · tensorflow/workshops · GitHub
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 TensorFlow 1.6.0 · tensorflow/tensorflow
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
Make TensorBoard work in raw sources mode by jart · Pull Request #747 · tensorflow/tensorboard
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
[SSD] Small object detection · Issue #3196 · tensorflow/models
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
![[SSD] Small object detection · Issue #3196 · tensorflow/models](https://cdn-ak-scissors.b.st-hatena.com/image/square/7fa77e2ffd3cb56820bf76c6fd466475fef17a54/height=288;version=1;width=512/https%3A%2F%2Fopengraph.githubassets.com%2Fb7c8208b6eaf821bb335c55c1e935cef9ceaf8136e31ce011a0682d71ba2f942%2Ftensorflow%2Fmodels%2Fissues%2F3196)
Release TensorFlow 1.5.0 · tensorflow/tensorflow
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
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
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
GitHub - tensorflow/tfjs: A WebGL accelerated JavaScript library for training and deploying ML models.
tensorflow/Makefile at master · tensorflow/tensorflow · GitHub
tensorflow/tensorflow/tools/graph_transforms/README.md at master · tensorflow/tensorflow
models/research/deeplab at master · tensorflow/models
GitHub - tensorflow/lucid: A collection of infrastructure and tools for research in neural network interpretability.
models/research/astronet at master · tensorflow/models · GitHub
Releases · tensorflow/tensorflow
models/research/object_detection/g3doc/running_pets.md at master · tensorflow/models
GitHub - NVIDIA/FastPhotoStyle: Style transfer, deep learning, feature transform
magenta/magenta/models/music_vae at main · magenta/magenta
Running on Google Cloud found : No module named tensorflow.tensorboard · Issue #392 · tensorflow/tensorboard
