def next_fold(self):
'''
sets up and returns a batcher on the next validation fold
returns the (train, test) batchers on the next fold
'''
train_inds, test_inds = self.get_train_val_inds()
# return two Batcher
train_mean = 0
if self.new_batch:
print('calculating train mean')
train_fp = Batcher.Batcher(self.batch_sz,
self.metadata,
train_inds,
self.mass_headers,
self.calc_headers,
root_dir,
self.attr2onehot,
new_batch=self.new_batch)
train_mean = train_fp.get_train_mean()
print(train_mean)
train, test = Batcher.Batcher(self.batch_sz, self.metadata, train_inds, self.mass_headers, self.calc_headers, root_dir, self.attr2onehot, mean=train_mean, new_batch=self.new_batch), \
Batcher.Batcher(self.batch_sz, self.metadata, test_inds, self.mass_headers, self.calc_headers, root_dir, self.attr2onehot, mean=train_mean)
self.curr_fold += 1
return train, test
cost = map["cost"]
model = map["model"]
inputs = map["inputs"]
params = map["params"]
print "Computing cost..."
cost_func = theano.function(inputs=inputs, outputs=cost)
print "Computing update..."
updates = model.cmp_grad(alpha, cost)
print "Compution gradient step..."
sgd_step = theano.function(inputs=inputs, updates=updates)
print "Descent..."
batcher = Batcher(params)
batch = batcher.get_batch(batch_size)
last_cost = cost_func(batch[0], batch[1])
best_cost = last_cost
while batcher.epoch < max_epoch:
batch = batcher.get_batch(batch_size)
if batcher.epoch_percentage == 0:
last_cost = cost_func(batch[0], batch[1])
map["curve"] += [last_cost]
if best_cost > last_cost:
best_cost = last_cost
file = open(name + ".pkl", 'wb')
pickle.dump(map, file, -1)
sgd_step(batch[0], batch[1])
sys.stdout.write(
'\r%d%% of epoch %d completed. Best cost: %f, last cost %f' %
for i in range(10):
batch = batcher.get_batch(batch_size)
c, memory = cost_func(batch[0], memory, batch[1])
compilation += [c]
map["curve"] += [np.asarray(compilation)]
time = batcher.get_time()
sys.stdout.write('\r%d mins %d secs: valid cost = %s' %
(time[0], time[1], np.asarray(compilation)[:4].tolist()))
if np.mean(compilation) < best:
best = np.mean(compilation)
file = open(name + ".pkl", 'wb')
pickle.dump(map, file, -1)
file.close()
return best
print "Descent..."
batcher = Batcher()
valid = batcher.valid
best = 10000
for n in range(max_epoch):
best = valid_cost(best)
batcher.reset()
memory = np.zeros((model.depth, batch_size, params[0]),
dtype=config.floatX)
for i in range(10):
batch = batcher.get_batch(batch_size)
memory = sgd_step(batch[0], memory, batch[1])
print ""
