自动编码器
可以用于特征的转换（mxnet实现的代码模板）
def get_manifold(X): from mxnet import nd from mxnet import ndarray as F from mxnet.gluon import Block, nn from mxnet.initializer import Uniform class Model(Block): def __init__(self, num_dim, **kwargs): super(Model, self).__init__(**kwargs) #Unifrom产生随机数 wi1 = Uniform(0.25) wi2 = Uniform(0.1) with self.name_scope(): self.encoder1 = nn.Dense(num_dim//2, in_units=num_dim, weight_initializer=wi1) self.encoder2 = nn.Dense(num_dim//4, in_units=num_dim//2, weight_initializer=wi1) self.encoder3 = nn.Dense(num_dim//8, in_units=num_dim//4, weight_initializer=wi2) self.encoder4 = nn.Dense(num_dim//16, in_units=num_dim//8, weight_initializer=wi2) self.encoder5 = nn.Dense(num_dim//32, in_units=num_dim//16, weight_initializer=wi2) self.decoder5 = nn.Dense(num_dim//16, in_units=num_dim//32, weight_initializer=wi2) self.decoder4 = nn.Dense(num_dim//8, in_units=num_dim//16, weight_initializer=wi2) self.decoder3 = nn.Dense(num_dim//4, in_units=num_dim//8, weight_initializer=wi2) self.decoder2 = nn.Dense(num_dim//2, in_units=num_dim//4, weight_initializer=wi1) self.decoder1 = nn.Dense(num_dim, in_units=num_dim//2, weight_initializer=wi1) self.layers = [(self.encoder1,self.decoder1), (self.encoder2,self.decoder2), (self.encoder3,self.decoder3), (self.encoder4,self.decoder4), (self.encoder5,self.decoder5)] def onelayer(self, x, layer): xx = F.tanh(layer[0](x)) return layer[1](xx) def oneforward(self, x, layer): return F.tanh(layer[0](x)) def forward(self, x): n_layer = len(self.layers) for i in range(n_layer): x = F.tanh(self.layers[i][0](x)) for i in range(n_layer-1): x = F.tanh(self.layers[n_layer-i-1][1](x)) return self.layers[0][1](x) def manifold(self, x): n_layer = len(self.layers) for i in range(n_layer-1): x = F.tanh(self.layers[i][0](x)) return self.layers[n_layer-1][0](x) from mxnet import autograd from mxnet import cpu from mxnet.gluon import Trainer from mxnet.gluon.loss import L2Loss # Stacked AutoEncoder model = Model(X.shape[1]) model.initialize(ctx=[cpu(0),cpu(1),cpu(2),cpu(3)]) # Select Trainign Algorism trainer = Trainer(model.collect_params(),'adam') loss_func = L2Loss() # Start Pretraining print('start pretraining of StackedAE...') loss_n = [] # for log buffer = nd.array(X.values) for layer_id, layer in enumerate(model.layers): print('layer %d of %d...'%(layer_id+1,len(model.layers))) trainer.set_learning_rate(0.02) for epoch in range(1, epochs[layer_id] + 1): # random indexs for all datas indexs = np.random.permutation(buffer.shape[0]) for bs in range(0,buffer.shape[0],batch_size): be = min(buffer.shape[0],bs+batch_size) data = buffer[indexs[bs:be]] # forward with autograd.record(): output = model.onelayer(data, layer) # make loss loss = loss_func(output, data) # for log loss_n.append(np.mean(loss.asnumpy())) del output # backward loss.backward() # step training to one batch trainer.step(batch_size, ignore_stale_grad=True) del data, loss # show log print('%d/%d epoch loss=%f...'%(epoch,epochs[layer_id],np.mean(loss_n))) loss_n = [] del bs, be, indexs buffer = model.oneforward(buffer, layer) del layer, loss_n, buffer print('start training of StackedAE...') loss_n = [] buffer = nd.array(X.values) trainer.set_learning_rate(0.02) for epoch in range(1, epochs[-1] + 1): # random indexs for all datas indexs = np.random.permutation(buffer.shape[0]) for bs in range(0,buffer.shape[0],batch_size): be = min(buffer.shape[0],bs+batch_size) data = buffer[indexs[bs:be]] # forward with autograd.record(): output = model(data) # make loss loss = loss_func(output, data) # for log loss_n.append(np.mean(loss.asnumpy())) del output # backward loss.backward() # step training to one batch trainer.step(batch_size, ignore_stale_grad=True) del data, loss # show log print('%d/%d epoch loss=%f...'%(epoch,epochs[-1],np.mean(loss_n))) loss_n = [] del bs, be, indexs del trainer, loss_func, loss_n, buffer print('making manifold...') manifold_X = pd.DataFrame() for bs in range(0,X.shape[0],batch_size): be = min(X.shape[0],bs + batch_size) nx = nd.array(X.iloc[bs:be].values) df = pd.DataFrame(model.manifold(nx).asnumpy()) manifold_X = manifold_X.append(df, ignore_index=True, sort=False) del be, df, nx del model, bs return manifold_X