From f7412a180b2ea694e910e915a531766f0bbf010e Mon Sep 17 00:00:00 2001 From: Oceania2018 Date: Sat, 12 Dec 2020 09:10:50 -0600 Subject: [PATCH] Release TF.NET v0.31.0, TF.Keras v0.2.0 --- README.md | 37 ++++++++---------- src/TensorFlowNET.Keras/Open.snk | Bin 0 -> 596 bytes .../Tensorflow.Keras.csproj | 5 ++- 3 files changed, 20 insertions(+), 22 deletions(-) create mode 100644 src/TensorFlowNET.Keras/Open.snk diff --git a/README.md b/README.md index f067f9a4..7f27b42c 100644 --- a/README.md +++ b/README.md @@ -26,19 +26,17 @@ In comparison to other projects, like for instance [TensorFlowSharp](https://www ### How to use -| TensorFlow | tf native1.14 | tf native 1.15 | tf native 2.3 | -| ------------------------- | ------------- | -------------- | ------------- | -| tf.net 0.30, tf.keras 0.1 | | | x | -| tf.net 0.20 | | x | x | -| tf.net 0.15 | x | x | | -| tf.net 0.14 | x | | | - -Read the docs & book [The Definitive Guide to Tensorflow.NET](https://tensorflownet.readthedocs.io/en/latest/FrontCover.html). - -There are many examples reside at [TensorFlow.NET Examples](https://github.com/SciSharp/TensorFlow.NET-Examples). +| TensorFlow | tf native1.14 | tf native 1.15 | tf native 2.3 | +| -------------------------- | ------------- | -------------- | ------------- | +| tf.net 0.3x, tf.keras 0.2x | | | x | +| tf.net 0.2x | | x | x | +| tf.net 0.1x | x | x | | +| tf.net 0.1x | x | | | Troubleshooting of running example or installation, please refer [here](tensorflowlib/README.md). +There are many examples reside at [TensorFlow.NET Examples](https://github.com/SciSharp/TensorFlow.NET-Examples) written in C# and F#. + #### C# Example Install TF.NET and TensorFlow binary through NuGet. @@ -67,18 +65,16 @@ Linear Regression in `Eager` mode: ```c# // Parameters -int training_steps = 1000; -float learning_rate = 0.01f; -int display_step = 100; +var training_steps = 1000; +var learning_rate = 0.01f; +var display_step = 100; // Sample data -NDArray train_X, train_Y; -int n_samples; -train_X = np.array(3.3f, 4.4f, 5.5f, 6.71f, 6.93f, 4.168f, 9.779f, 6.182f, 7.59f, 2.167f, +var train_X = np.array(3.3f, 4.4f, 5.5f, 6.71f, 6.93f, 4.168f, 9.779f, 6.182f, 7.59f, 2.167f, 7.042f, 10.791f, 5.313f, 7.997f, 5.654f, 9.27f, 3.1f); -train_Y = np.array(1.7f, 2.76f, 2.09f, 3.19f, 1.694f, 1.573f, 3.366f, 2.596f, 2.53f, 1.221f, +var train_Y = np.array(1.7f, 2.76f, 2.09f, 3.19f, 1.694f, 1.573f, 3.366f, 2.596f, 2.53f, 1.221f, 2.827f, 3.465f, 1.65f, 2.904f, 2.42f, 2.94f, 1.3f); -n_samples = train_X.shape[0]; +var n_samples = train_X.shape[0]; // We can set a fixed init value in order to demo var W = tf.Variable(-0.06f, name: "weight"); @@ -218,6 +214,7 @@ for step = 1 to (training_steps + 1) do printfn $"step: {step}, loss: {loss.numpy()}, W: {W.numpy()}, b: {b.numpy()}" ``` +Read the docs & book [The Definitive Guide to Tensorflow.NET](https://tensorflownet.readthedocs.io/en/latest/FrontCover.html) if you want to know more about TensorFlow for .NET under the hood. ### Contribute: @@ -249,9 +246,7 @@ git pull upstream master ### Contact -Feel free to star or raise issue on [Github](https://github.com/SciSharp/TensorFlow.NET). - -Follow us on [Medium](https://medium.com/scisharp). +Follow us on [Twitter](https://twitter.com/ScisharpStack), [Facebook](https://www.facebook.com/scisharp.stack.9), [Medium](https://medium.com/scisharp), [LinkedIn](https://www.linkedin.com/company/scisharp-stack/). Join our chat on [Gitter](https://gitter.im/sci-sharp/community). diff --git a/src/TensorFlowNET.Keras/Open.snk b/src/TensorFlowNET.Keras/Open.snk new file mode 100644 index 0000000000000000000000000000000000000000..22a3cbd253a7f1091078ac81eb16eb2ffd32880c GIT binary patch literal 596 zcmV-a0;~N80ssI2Bme+XQ$aES1ONa50096?hQ!NwRGT!qwi-Ja0OC9TwX^Iw0CWTu zHmBpu*?(UI&ku!hRj87VswwOJ5zo7=JEso*r@f;hY-)`+3QW@j_Y_ELZoDE{g{C-1 z9&Yt<%#x&GJOH@*W!4%#X z>O=LYCI9oV9(*3OvX<8KOfn^kauKMK)Q40Ck2iNzf(#`9!BGFmecB2~ccY%9L3QBBe zG%-a6fU%je)>Y8T3}#BFs84D=?*xidlht=JZr@^(#S^o(LP3+g}r|MD4BH`p~&~6 zt~;;|=bt(1I3jtmbU;6+`22n#0nqha;uK51JVJW88+KQpHUsg+5ZCZ{4D~-qSw{)8 ixNldK-pEwZArM>aiB7nKifAJOwbkQ2Qk0=;PvjC{`6;si literal 0 HcmV?d00001 diff --git a/src/TensorFlowNET.Keras/Tensorflow.Keras.csproj b/src/TensorFlowNET.Keras/Tensorflow.Keras.csproj index b99d9be4..616467ff 100644 --- a/src/TensorFlowNET.Keras/Tensorflow.Keras.csproj +++ b/src/TensorFlowNET.Keras/Tensorflow.Keras.csproj @@ -17,7 +17,8 @@ Keras for .NET is a C# version of Keras ported from the python version. * Support CIFAR-10 dataset in keras.datasets. -* Support Conv2D functional API. +* Support Conv2D functional API. +* Support BatchNormalization layer. Keras for .NET Keras is an API designed for human beings, not machines. Keras follows best practices for reducing cognitive load: it offers consistent & simple APIs, it minimizes the number of user actions required for common use cases, and it provides clear & actionable error messages. @@ -26,6 +27,8 @@ Keras is an API designed for human beings, not machines. Keras follows best prac tensorflow, keras, deep learning, machine learning false Git + true + Open.snk