nudles commented on issue #651: [WIP ]Simply example APIs URL: https://github.com/apache/singa/pull/651#issuecomment-609045570 I suggest to merge the examples under `examples/autograd` into the following scheme ``` autograd train.py train_mpi.py train_multiprocess.py data # define the data loading and preprocessing cifar10.py mnist.py model # define the model cnn.py resnet.py xception.py ``` ```python # train.py def run(max_epoch, rank, num_workers, model, data, sgd): if model == 'resnet': from model import resnet model = resnet.create_model() elif model == 'cnn': model = cnn.create_model() .... if data == 'cifar10': from data import cifar10: train_x, train_y, val_x, val_y = cifar10.load() elif data == 'mnist': .... train_x, train_y, val_x, val_y = partition(rank, num_workers, train_x, train_y, val_x, val_y) # bp and sgd if __name__ == '__main__': # use argparse to get command config: max_epoch, model, data, etc. for single gpu training sgd = # create sgd run(0, 1, ..., sgd) # train_mpi.py if __name__ == '__main__': # use argparse to get command args: max_epoch, model, data, etc. for multi-gpu training sgd = # create sgd dist_sgd = DistOpt(sgd...) run(dist_sgd.rank, dist_sgd.world_size, ... dist_sgd) # train_multiprocess.py def run(rank, num_gpu, ...): sgd = ... dist_sgd = DistOpt(sgd) train.run(rank, num_gpu, ... dist_sgd) if __name__ == '__main__': # use argparse to get command args: max_epoch, model, data, etc. for multi-gpu training nccl_id = ... process = [] for gpu_num in range(0, gpu_per_node): process.append(multiprocessing.Process(target=run, args=(gpu_num, ... nccl_id))) for p in process: p.start() ```
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
