无法提高模型精度

由 发布于

我正在建立一个通用的NN，它将图像（狗/无狗）和电影评论（好/坏）分类。我必须坚持非常具体的体系结构和损失函数，因此改变这两者似乎不可行。我的体系结构是一个两层网络，其中包含relu，其后是S型和交叉熵损失函数。通过1000个纪元和大约.001的学习率，我获得了100％的训练准确度和.72的测试准确度。我一直在寻找提高我的测试准确度的建议。这是我所拥有的布局：

'''
def train_net(epochs,batch_size,train_x,train_y,model_size,lr):
  n_x,n_h,n_y=model_size
  model = Net(n_x, n_h, n_y)
  optim = torch.optim.Adam(model.parameters(),lr=0.005)
  loss_function = nn.BCELoss() 
  train_losses = []
  accuracy = []
  for epoch in range(epochs):
    count=0
    model.train() 
    train_loss = []
    batch_accuracy = []
    for idx in range(0, train_x.shape[0], batch_size):

      batch_x = torch.from_numpy(train_x[idx : idx + batch_size]).float() 
      batch_y = torch.from_numpy(train_y[:,idx : idx + batch_size]).float()    
      model_output = model(batch_x) 
      batch_accuracy=[]  
      loss = loss_function(model_output, batch_y) 
      train_loss.append(loss.item())

      preds = model_output > 0.5
      nb_correct = (preds == batch_y).sum()
      count+=nb_correct.item()                            
      optim.zero_grad()
      loss.backward()
# Scheduler made it worse 
# scheduler.step(loss.item())  
  optim.step()

    if epoch % 100 == 1:
      train_losses.append(train_loss)
      print("Iteration : {}, Training loss: {} ,Accuracy %: {}".format(epoch,np.mean(train_loss),(count/train_x.shape[0])*100))              
  plt.plot(np.squeeze(train_losses))
  plt.ylabel('loss')
  plt.xlabel('iterations (per tens)')
  plt.title("Learning rate =" + str(lr))
  plt.show()
  return model

''' 我的模型参数：

batch_size = 32
lr = 0.0001
epochs = 1500

n_x = 12288     # num_px * num_px * 3
n_h = 7
n_y = 1
model_size=n_x,n_h,n_y
model=train_net(epochs,batch_size,train_x,train_y,model_size,or)

这是测试阶段。

model.eval()  #Setting the model to eval mode, hence making it deterministic.
test_loss = []
count=0;
loss_function = nn.BCELoss()

for idx in range(0, test_x.shape[0], batch_size):
  with torch.no_grad():   
    batch_x = torch.from_numpy(test_x[idx : idx + batch_size]).float() 
    batch_y = torch.from_numpy(test_y[:,idx : idx + batch_size]).float()
    model_output = model(batch_x)
    preds = model_output > 0.5
    loss = loss_function(model_output, batch_y)
    test_loss.append(loss.item())
    nb_correct = (preds == batch_y).sum()
    count+=nb_correct.item()  

print("test loss: {},test accuracy: {}".format(np.mean(test_loss),count/test_x.shape[0]))

我尝试过的事情： 顺应学习率，保持动力，使用调度程序和更改批处理大小，当然，这些主要是猜测，并非基于任何有效的假设。