[英]why my model does not learn? Same on every epoch (Pytorch)
from sklearn import datasets
import pandas as pd
import numpy as np
import torch
from torch import nn
#loading the dataset
(data, target) = datasets.load_diabetes(as_frame=True,return_X_y=True) #with the as_frame=True data: pd.DataFrame
# converting data,target to tensors
data = torch.tensor(data.values,dtype=torch.float)
target = torch.tensor(target.values,dtype=torch.float)
#split the data 80% train 20% testing
a = 0.8
train_data , train_target = data[:int(a*len(data))] , data[:int(a*len(data))]
test_data , test_target = data[int(a*len(data)):] , data[int(a*len(data)):]
#constructing the model
# for this dataset dimentionality is 10 so the in_features will be 10
model = nn.Sequential(
nn.Linear(in_features=10, out_features=128),
nn.Linear(in_features=128, out_features=128),
nn.Linear(in_features=128, out_features=1)
)
#loss fn , optimizer
loss_fn = nn.L1Loss() #binary cross entropy
optimizer = torch.optim.SGD(params = model.parameters(),lr=0.001) #stochastic gradient descent
#training loop
epochs = 1000
for epoch in range(epochs):
#1. make prediction
model.train()
train_pred = model(train_data)
loss = loss_fn(train_pred, train_target)
optimizer.zero_grad()
loss.backward()
optimizer.step()
model.eval()
with torch.inference_mode():
test_pred = model(test_data)
loss_test = loss_fn(test_pred, test_target)
if epoch%(epochs//min(10,epochs))==0: print(f"{epoch} - training loss: {round(float(loss),4)} | test loss: {round(float(loss_test),4)}")- training loss: {loss} | test loss: {loss_test}")
Output Output
0 - training loss: 0.0837 | 0 - 训练损失:0.0837 | test loss: 0.0806
测试损失:0.0806
100 - training loss: 0.0433 | 100 - 训练损失:0.0433 | test loss: 0.0431
测试损失:0.0431
200 - training loss: 0.0426 | 200 - 训练损失:0.0426 | test loss: 0.0425
测试损失:0.0425
300 - training loss: 0.042 | 300 - 训练损失:0.042 | test loss: 0.0419
测试损失:0.0419
400 - training loss: 0.0414 | 400 - 训练损失:0.0414 | test loss: 0.0414
测试损失:0.0414
500 - training loss: 0.0408 | 500 - 训练损失:0.0408 | test loss: 0.0408
测试损失:0.0408
600 - training loss: 0.0403 | 600 - 训练损失:0.0403 | test loss: 0.0403
测试损失:0.0403
700 - training loss: 0.0398 | 700 - 训练损失:0.0398 | test loss: 0.0398
测试损失:0.0398
800 - training loss: 0.0393 | 800 - 训练损失:0.0393 | test loss: 0.0394
测试损失:0.0394
900 - training loss: 0.0388 | 900 - 训练损失:0.0388 | test loss: 0.0389
测试损失:0.0389
First, as it was mentioned in the comments, you probably meant:首先,正如评论中提到的那样,您可能的意思是:
train_data, train_target = data[:int(a*len(data))] , target[:int(a*len(data))]
test_data, test_target = data[int(a*len(data)):] , target[int(a*len(data)):]
Next, your target size is not consistent with the output size (this should give a warning).接下来,您的目标大小与 output 大小不一致(这应该会给出警告)。 Using
使用
loss = loss_fn(train_pred, train_target.unsqueeze(1))
and
loss_test = loss_fn(test_pred, test_target.unsqueeze(1))
should give you some traction.应该给你一些牵引力。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.