The nascaps from ehw-fit

Hardware accelerator configuration

Could you please provide some info on how to feed this framework a new generic Hardware accelerator? (have read your paper, great job by the way)

Training of generated model (from the generated gene) gives tensorflow.python.framework.errors_impl.InternalError: Blas GEMM launch failed

I have been going over the implementation of the NASCaps repo, and to understand how the algorithm searches the architecture I am following the README.md there to run the "main.py" with its args as mentioned in the file. and I have encountered an issue explained down below:
Once a gene is created and the corresponding CapsNet model is created, upon training the model for evaluating the population (method evaluate_population > wrap_train_test > train) I get the following error:

File "/home/ak11263/miniconda3/envs/tf-1.13-gpu/lib/python3.7/site-packages/tensorflow/python/framework/errors_impl.py", line 528, in __exit__
    c_api.TF_GetCode(self.status.status))
  File "/home/ak11263/miniconda3/envs/tf-1.13-gpu/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1439, in __call__
    run_metadata_ptr)
  File "/home/ak11263/miniconda3/envs/tf-1.13-gpu/lib/python3.7/site-packages/keras/backend/tensorflow_backend.py", line 2675, in _call
    fetched = self._callable_fn(*array_vals)
  File "/home/ak11263/miniconda3/envs/tf-1.13-gpu/lib/python3.7/site-packages/keras/backend/tensorflow_backend.py", line 2715, in __call__
    return self._call(inputs)
  File "/home/ak11263/miniconda3/envs/tf-1.13-gpu/lib/python3.7/site-packages/keras/engine/training.py", line 1217, in train_on_batch
    outputs = self.train_function(ins)
  File "/home/ak11263/miniconda3/envs/tf-1.13-gpu/lib/python3.7/site-packages/keras/engine/training_generator.py", line 217, in fit_generator
    class_weight=class_weight)
  File "/home/ak11263/miniconda3/envs/tf-1.13-gpu/lib/python3.7/site-packages/keras/engine/training.py", line 1418, in fit_generator
    initial_epoch=initial_epoch)
  File "/home/ak11263/miniconda3/envs/tf-1.13-gpu/lib/python3.7/site-packages/keras/legacy/interfaces.py", line 91, in wrapper
    return func(*args, **kwargs)
  File "/home/ak11263/nascaps/nsga/main.py", line 893, in train
    callbacks=[timeout_call, log, checkpoint, lr_decay])
  File "/home/ak11263/nascaps/nsga/main.py", line 652, in wrap_train_test
    runid, _ = train(model=model, data=((x_train_current, y_train), (x_test_current, y_test)), args=args)
  File "/home/ak11263/nascaps/nsga/main.py", line 525, in evaluate_population
    p["runid"], train_acc = wrap_train_test(p["gene"])
  File "/home/ak11263/nascaps/nsga/main.py", line 711, in run_NSGA2
    evaluate_population(parent)
  File "/home/ak11263/nascaps/nsga/main.py", line 1065, in <module>
    rets = run_NSGA2(metrics=["accuracy_drop", "energy", "memory", "latency"], inshape=inshape, p_size=args.population, q_size=args.offsprings, generations=args.generations)
  File "/home/ak11263/miniconda3/envs/tf-1.13-gpu/lib/python3.7/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/home/ak11263/miniconda3/envs/tf-1.13-gpu/lib/python3.7/runpy.py", line 193, in _run_module_as_main (Current frame)
    "__main__", mod_spec)
tensorflow.python.framework.errors_impl.InternalError: Blas GEMM launch failed : a.shape=(100, 160), b.shape=(160, 784), m=100, n=784, k=160
	 [[{{node decoder/dense_1/MatMul}}]]
	 [[{{node loss/decoder_loss/Mean_3}}]]

After disabling (commenting out) the training and testing of the generated model and replacing it with a dummy model to generate a random test_acc I have seen that the program runs successfully.

I have been looking around the net and have some suggestions that the use of tensorflow v1 is causing the issue (I also have seen that it has been showing me plenty of warnings of deprecations).

I also have started migrating the project into tensorflow 2, although not very successfully.

It would have been delightful if I could have been given any suggestions.

How to run this on Windows?

Hi,
How can I run this on a windows system. I have installed conda and tried to set the environment but it failed. Any tips please? It looks like a really nice software by the way.

Best regards,
MA

Mapping Weights to Structure

Hi,
I have run this code many times. A problem that I have is that sometimes when I try to load a trained network with weights, the weights don't map on to the network. Here is an example of the error that I get.

ValueError: You are trying to load a weight file containing 1 layers into a model with 4 layers.

I wonder if there is a cure for this?

Best regards,

ehw-fit / nascaps Goto Github PK

nascaps's People

Contributors

Stargazers

Watchers

Forkers

nascaps's Issues

Hardware accelerator configuration

Training of generated model (from the generated gene) gives tensorflow.python.framework.errors_impl.InternalError: Blas GEMM launch failed

How to run this on Windows?

Mapping Weights to Structure

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent