Skip to content

Commit ad7f45d

Browse files
authored
Update README.md
1 parent 34fb3b9 commit ad7f45d

1 file changed

Lines changed: 12 additions & 0 deletions

File tree

README.md

Lines changed: 12 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -9,6 +9,18 @@ Thank you very much to the original author of ConvNetJS (Andrej Karpathy) and to
99

1010
## What's new ?
1111

12+
01/07/2017
13+
14+
- ConvNetSharp.Flow: A new way to create neural networks by defining a computation graph. There are now 3 ways of creating neural networks:
15+
16+
| Core.Layers | Flow.Layers | Pure Flow |
17+
| ------------- | ------------- | ------------- |
18+
| No computation graph | Layers that create a computation graph behind the scene | Computation graph |
19+
| Network organised by stacking layers | Network organised by stacking layers | 'Ops' connected to each others. Can implement more complex networks |
20+
| ![Layers](https://github.com/cbovar/ConvNetSharp/blob/master/img/structure.png) | ![Layers](https://github.com/cbovar/ConvNetSharp/blob/master/img/structure.png) | ![Layers](https://github.com/cbovar/ConvNetSharp/blob/master/img/graph.png) |
21+
| E.g. [MnistDemo](https://github.com/cbovar/ConvNetSharp/tree/master/Examples/MnistFlowGPUDemo) | E.g. [MnistFlowGPUDemo](https://github.com/cbovar/ConvNetSharp/tree/master/Examples/MnistDemo.Flow.GPU) or [Flow version of Classify2DDemo ](https://github.com/cbovar/ConvNetSharp/blob/master/Examples/FlowDemo/Classify2DDemo.cs) | E.g. [ExampleCpuSingle](https://github.com/cbovar/ConvNetSharp/blob/master/Examples/FlowDemo/ExampleCPUSingle.cs) |
22+
23+
1224
30/05/2017
1325

1426
- Available on [Nuget](https://www.nuget.org/packages/Cognitio.ConvNetSharp.Volume/) in pre-release (i.e. not stable)

0 commit comments

Comments
 (0)