我使用的是旧的源代码,使用的是Scipy的L-BFGS-B算法。不过,我有一些不准确的地方
我得到了以下指示: 一般来说,如果您在使用L-BFGS-B时遇到问题,您可能还需要尝试使用投影Adam或其他类似算法。对于解决这个问题,L-BFGS-B并没有什么特别之处,只是当时对我来说很方便。您可以从optim.Adam代码开始,在每一步之后,将x钳制在您的范围内
我想知道如何更改以下代码以使用ADAM而不是L-BFGS-B。我不熟悉Scipy。请帮忙,因为我是初学者
def get_sharpness(data_loader, model, criterion, epsilon, manifolds=0):
# extract current x0
x0 = None
for p in model.parameters():
if x0 is None:
x0 = p.data.view(-1)
else:
x0 = torch.cat((x0, p.data.view(-1)))
x0 = x0.cpu().numpy()
# get current f_x
f_x0, _ = get_minus_cross_entropy(x0, data_loader, model, criterion)
f_x0 = -f_x0
logging.info('min loss f_x0 = {loss:.4f}'.format(loss=f_x0))
# find the minimum
if 0==manifolds:
x_min = np.reshape(x0 - epsilon * (np.abs(x0) + 1), (x0.shape[0], 1))
x_max = np.reshape(x0 + epsilon * (np.abs(x0) + 1), (x0.shape[0], 1))
bounds = np.concatenate([x_min, x_max], 1)
func = lambda x: get_minus_cross_entropy(x, data_loader, model, criterion, training=True)
init_guess = x0
else:
warnings.warn("Small manifolds may not be able to explore the space.")
assert(manifolds<=x0.shape[0])
#transformer = rp.GaussianRandomProjection(n_components=manifolds)
#transformer.fit(np.random.rand(manifolds, x0.shape[0]))
#A_plus = transformer.components_
#A = np.linalg.pinv(A_plus)
A_plus = np.random.rand(manifolds, x0.shape[0])*2.-1.
# normalize each column to unit length
A_plus_norm = np.linalg.norm(A_plus, axis=1)
A_plus = A_plus / np.reshape(A_plus_norm, (manifolds,1))
A = np.linalg.pinv(A_plus)
abs_bound = epsilon * (np.abs(np.dot(A_plus, x0))+1)
abs_bound = np.reshape(abs_bound, (abs_bound.shape[0], 1))
bounds = np.concatenate([-abs_bound, abs_bound], 1)
def func(y):
floss, fg = get_minus_cross_entropy(x0 + np.dot(A, y), data_loader, model, criterion, training=True)
return floss, np.dot(np.transpose(A), fg)
#func = lambda y: get_minus_cross_entropy(x0+np.dot(A, y), data_loader, model, criterion, training=True)
init_guess = np.zeros(manifolds)
#rand_selections = (np.random.rand(bounds.shape[0])+1e-6)*0.99
#init_guess = np.multiply(1.-rand_selections, bounds[:,0])+np.multiply(rand_selections, bounds[:,1])
minimum_x, f_x, d = sciopt.fmin_l_bfgs_b(func, init_guess, maxiter=10, bounds=list(bounds), disp=1, iprint=101)
得到负交叉熵的定义是
def get_minus_cross_entropy(x, data_loader, model, criterion, training=False):
if type(x).__module__ == np.__name__:
x = torch.from_numpy(x).float()
x = x.cuda()
# switch to evaluate mode
model.eval()
# fill vector x of parameters to model
x_start = 0
for p in model.parameters():
psize = p.data.size()
peltnum = 1
for s in psize:
peltnum *= s
x_part = x[x_start:x_start+peltnum]
p.data = x_part.view(psize)
x_start += peltnum
result, grads = forward(data_loader, model, criterion, 0,
training=training, optimizer=None)
#print ('get_minus_cross_entropy {}!'.format(-result['loss']))
return (-result['loss'], None if grads is None else grads.cpu().numpy().astype(np.float64))
目前没有回答
相关问题 更多 >
编程相关推荐