def initialize_everything(self):
### initialize matrices for cuda ###
self.r_ =np.zeros(self.cfg.chains).astype('float32').copy('F')
self.w = cp.dev_tensor_float_cm(self.w_.copy("F"))
### generate basemodel
softened = (self.data.mean(axis=1) + 0.1)
self.baserate_bias_= (np.log(softened) - np.log(1-softened)).astype('float32').copy('F')
self.baserate_bias_.shape=(self.w.shape[0],1)
## start chains
self.v_ = np.tile(sigm(self.baserate_bias_),(1,self.cfg.chains))
self.v_ = sample(self.v_,self.cfg['utype']).astype('float32').copy('F')
self.v = cp.dev_tensor_float_cm(self.v_.copy("F"))
self.h = cp.dev_tensor_float_cm([self.num_hids,self.cfg.chains])
self.baserate_bias = cp.dev_tensor_float_cm(self.baserate_bias_.copy("F"))
self.r = cp.dev_tensor_float_cm(np.vstack(self.r_).copy("F"))
cp.initialize_mersenne_twister_seeds(int(time.time()*1000) % 100000)
def initialize(cfg):
cp.initCUDA(cfg.device)
cp.initialize_mersenne_twister_seeds(cfg.seed)
import cuv_python as cp
if __name__ == "__main__":
try:
if sys.argv[2] == "--host":
switchtohost()
except:
pass
try:
mnist = MNIST_data(sys.argv[1])
except:
print('Usage: %s {path of MNIST dataset} [--host]' % sys.argv[0])
sys.exit(1)
cp.initialize_mersenne_twister_seeds(0)
# obtain training/test data
train_data, train_labels = mnist.get_train_data()
test_data, test_labels = mnist.get_test_data()
# set layer sizes
sizes = [train_data.shape[0], 128, train_labels.shape[0]]
print('Initializing MLP...')
mlp = MLP(sizes, 100)
print('Training MLP...')
try:
mlp.fit(train_data, train_labels, 200)
except KeyboardInterrupt:
def initialize(cfg):
cp.initCUDA(cfg.device)
cp.initialize_mersenne_twister_seeds(cfg.seed)
import numpy as np
import cuv_python as cp
if __name__ == "__main__":
try:
if sys.argv[2] == "--host":
switchtohost()
except: pass
try:
mnist = MNIST_data(sys.argv[1]);
except:
print('Usage: %s {path of MNIST dataset} [--host]' % sys.argv[0])
sys.exit(1)
cp.initialize_mersenne_twister_seeds(0)
# obtain training/test data
train_data, train_labels = mnist.get_train_data()
test_data, test_labels = mnist.get_test_data()
# set layer sizes
sizes = [train_data.shape[0], 128, train_labels.shape[0]]
print('Initializing MLP...')
mlp = MLP(sizes, 100)
print('Training MLP...')
try:
mlp.fit(train_data, train_labels, 200)
except KeyboardInterrupt:
