Comments (8)
@ahmetakman your network, as you defined in self.blocks
, has two hidden layers and one output layer of dimensions 512, 512, and 10 respectively. So it does make sense to get the dimension of the network as 512, 512, and 10 when you load the network, isn't it?
from lava-dl.
I thought the dimension should be
Dense : Process_1 , shape : (34342,512)
Dense : Process_4 , shape : (512,512)
Dense : Process_7 , shape : (512,10)
As were in the NetX examples.
from lava-dl.
Look at the dense block definition in PilotNet SDNN training
and the shapes in PilotNet SDNN inference with NetX
from lava-dl.
I have mistaken the error about the dimensions I got when was connecting the processes. I will try again soon ,and write back. Thanks for the reply.
from lava-dl.
Let me come back to here,
First of all, I am not sure my environment is fully utilized but at some point I have a system with barely passing unit tests with hanging code block issue #55 .
Here my interpretation about NetX dimensions is still because of the current error I am getting. Let me summarize my goal then give the error.
I would like to run trained NMNIST model with lava core by using NetX network exchange. The result of the conversion is given above.
When I try to connect processes with the code block:
gt_logger = io.sink.RingBuffer(shape=(1,), buffer=num_steps)
output_logger = io.sink.RingBuffer(shape=net.out_layer.shape, buffer=num_steps)
dataloader.ground_truth.connect(gt_logger.a_in)
dataloader.s_out.connect(net.in_layer.neuron.a_in) ***** issue line ********
net.out_layer.out.connect(output_logger.a_in)
I get the error
AssertionError: Shapes torch.Size([2312]) and (512,) are incompatible.]()
First, my interpretation was the dimension was lost since it is 512 not 2312
from lava-dl.
Aren't you supposed to connect the dataloader.s_out
to net.in_layer.synapse.s_in
? It seems you are bypassing the syanpse of the first layer!
dataloader.s_out.connect(net.in_layer.syanpse.s_in)
from lava-dl.
Yeah that was it, now I have connected processes the run config is running right now.
Thank you very much for the explanation. I sincerely thank for your patience.
I am actively learning the lava-ecosystem, SNNs ,and the new computers I am running them on.
Until I completely got the structure, I think it is natural to misunderstand some concepts.
I am closing the issue,
All the best,
Ahmet.
from lava-dl.
No problem @ahmetakman, happy to clarify any confusion.
from lava-dl.
Related Issues (20)
- Support verification and optimization of YoloKP on Loihi2 HOT 2
- Compiled netx hdf5 models cannot be serialized. HOT 1
- YOLO SDNN GPU inference notebook is too big to render on github
- Unable to reproduce Slayer NMNIST Test Accuracy HOT 1
- lava.lib.dl.netx.hdf5 imports Convolutional Layers incorrectly HOT 3
- YOLO SDNN inference
- SDNNs and SNNs
- error while using Recurrent block in lava-dl
- TypeError when using adrf neurons HOT 1
- Regression Tutorial using slayer HOT 2
- RuntimeError when using Recurrent blocks HOT 2
- When using slayer.block.cuba.Pool, input-output dimensions are not as expected. HOT 1
- next input block does not connect input port to neuron input. HOT 2
- Allow slayer norms to use parameters HOT 2
- Making the decay parameters(dv,du) learnable and separate du, dv for different layers? HOT 2
- optimize_weight_bits is increasing the weight matrix scale? HOT 1
- Netx DelaySynapse Bug: Weight_exp is None
- Neuron Parameters remain unchanged after setting them and also after training them. HOT 1
- Save recurrent network in lava-dl to hdf5 file, and load hdf5 file into lava with NetX
- Accelerate BDD100K dataset
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from lava-dl.