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
0 – training loss: 0.0837 | test loss: 0.0806
100 – training loss: 0.0433 | test loss: 0.0431
200 – training loss: 0.0426 | test loss: 0.0425
300 – training loss: 0.042 | test loss: 0.0419
400 – training loss: 0.0414 | test loss: 0.0414
500 – training loss: 0.0408 | test loss: 0.0408
600 – training loss: 0.0403 | test loss: 0.0403
700 – training loss: 0.0398 | test loss: 0.0398
800 – training loss: 0.0393 | test loss: 0.0394
900 – training loss: 0.0388 | test loss: 0.0389
Advertisement
Answer
First, as it was mentioned in the comments, you probably meant:
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). Using
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.