446
@schani now ,I want to traning my transformer model wtih corpus chinese-japanese,I have corpus about 10 million, 1 ,generator traing and dev data,the code adding my data in word2def.py , as follows: from future import absolute_import from future import division from future import print_function import os import tarfile from tensor2tensor.data_generators import problem from tensor2tensor.data_gener
probability/tensorflow_probability/python/edward2/Upgrading_From_Edward_To_Edward2.md at 22cb49d4b7d70a96a46f3a230792eab7ef793cb8 · tensorflow/probability
This guide outlines how to port code from the Edward probabilistic programming system to Edward2, a probabilistic programming language available in TensorFlow Probability. We recommend Edward users use Edward2 for specifying models and other TensorFlow Probability primitives for performing downstream computation. Edward2 is a distillation of Edward. It is a low-level language for specifying probab
TypeError with GetNext() for TF 1.8+ or 1.7 source · Issue #1111 · tensorflow/tensorboard · GitHub
Hi, I upgraded my tensorflow library to 1.7, and now I get an error when executing tensorboard. System description: TensorBoard version: 1.7 TensorFlow version: 1.7 (compiled from source) OS Platform and version: Linux Ubuntu 16.04.2 Python version: 3.5.3 Error: (tensorflow)/home/username$ tensorboard --logdir=/mydir/log 2018-04-07 01:56:45.493235: I tensorflow/stream_executor/cuda/cuda_gpu_execut
[object detection] TypeError: can't pickle dict_values objects · Issue #4780 · tensorflow/models
creating index... index created! 2018-07-16 22:12:38.626883: W T:\src\github\tensorflow\tensorflow\core\framework \op_kernel.cc:1306] Invalid argument: TypeError: can't pickle dict_values objects Traceback (most recent call last): File "d:\Program Files\Anaconda3\lib\site-packages\tensorflow\python\ops\scrip t_ops.py", line 158, in call ret = func(*args) File "D:\Program Files\Anaconda3\Lib\site-p
![[object detection] TypeError: can't pickle dict_values objects · Issue #4780 · tensorflow/models](https://cdn-ak-scissors.b.st-hatena.com/image/square/727b49a86aabd1a024673d851fdd3145d2aeb677/height=288;version=1;width=512/https%3A%2F%2Fopengraph.githubassets.com%2Fefad88dafd104f991b24eac0c2bb3cc2a36e9d5b947f0921e91c7be1193da333%2Ftensorflow%2Fmodels%2Fissues%2F4780)
Mac OS X Python 3.5 binary runtime warning for Tensorflow 1.5.0+ · Issue #18850 · tensorflow/tensorflow
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): Mac OS X 10.13.4 TensorFlow installed from (source or binary): binary (or whatever pip is) TensorFlow version (use command below): 1.5.0+ Python version: 3.5.2 Bazel version (if compiling from source): GCC/Compiler version (i
tensorflow/tensorflow/contrib/lite/experimental/micro at master · tensorflow/tensorflow · GitHub
TensorFlow Lite for Microcontrollers This an experimental port of TensorFlow Lite aimed at micro controllers and other devices with only kilobytes of memory. It doesn't require any operating system support, any standard C or C++ libraries, or dynamic memory allocation, so it's designed to be portable even to 'bare metal' systems. The core runtime fits in 16KB on a Cortex M3, and with enough operat
models/running_locally.md at master · tensorflow/models · GitHub
Running Locally This page walks through the steps required to train an object detection model on a local machine. It assumes the reader has completed the following prerequisites: The Tensorflow Object Detection API has been installed as documented in the installation instructions. This includes installing library dependencies, compiling the configuration protobufs and setting up the Python environ
tensorflow/README.md at master · tensorflow/tensorflow · GitHub
Quantization-aware training Quantization-aware model training ensures that the forward pass matches precision for both training and inference. There are two aspects to this: Operator fusion at inference time are accurately modeled at training time. Quantization effects at inference are modeled at training time. For efficient inference, TensorFlow combines batch normalization with the preceding con
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
models/model_params.py at master · tensorflow/models · GitHub
GitHub - tensorflow/tensorboard: TensorFlow's Visualization Toolkit
models/object_detection_tutorial.ipynb at master · tensorflow/models · GitHub
from_generator feedback and questions · Issue #13101 · tensorflow/tensorflow · GitHub
models/research/slim at master · tensorflow/models
mesh/README.md at master · tensorflow/mesh · GitHub
GitHub - tensorflow/tfjs-vis: A set of utilities for in browser visualization with TensorFlow.js
Open Inference graph file as a binary file by yukoba · Pull Request #5065 · tensorflow/models
gradient function missing for odeint · Issue #15833 · tensorflow/tensorflow
[Tuning] Results are GPU-number and batch-size dependent · Issue #444 · tensorflow/tensor2tensor![[Tuning] Results are GPU-number and batch-size dependent · Issue #444 · tensorflow/tensor2tensor](https://cdn-ak-scissors.b.st-hatena.com/image/square/83c710754d6fc8f8b0c37dfc13e83b0be7fa25eb/height=288;version=1;width=512/https%3A%2F%2Fopengraph.githubassets.com%2F30697ce491150b3fc49868a1a567e238fefba38267e4d599149020b5b7c92145%2Ftensorflow%2Ftensor2tensor%2Fissues%2F444)
tpu/models/official/resnet at master · tensorflow/tpu
GitHub - tensorflow/ranking: Learning to Rank in TensorFlow
