Pytorch - Problem with fine tune training from custom features and classes-CodePudding

The core of my problem is the fact that my features come from NumPy files (.npy).

Therefore I need the following class in my code

import torch
import torchvision
import torchvision.transforms as transforms
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import numpy as np
from torch.utils.data import Dataset, DataLoader
from torchvision.models import resnet50
import time
import copy

class MyDataSet(torch.utils.data.Dataset):
    def __init__(self, x, y, transform=None):
        super(MyDataSet, self).__init__()
        # store the raw tensors
        self._x = np.load(x)
        self._y = np.load(y)
        self.transform = transform
    
    def __len__(self):
        # a DataSet must know it size
        return self._x.shape[0]

    def __getitem__(self, index):
        x = self._x[index, :]
        y = self._y[index, :]
        return x, y

To convert my NumPy files to DataLoaders I do the following. The code below seems to work (at least, no errors are returned)

#Transform dataset 
transform = transforms.Compose([transforms.ToTensor()])
dataset = MyDataSet("train1-features.npy","train1-classes.npy",transform=transform)
dataloader = DataLoader(dataset, batch_size=32)

I am trying to fine-tune a RESNET-50 network in these data with 12 classes. Here is what I do

def set_parameter_requires_grad(model, feature_extracting):
    if feature_extracting:
        for param in model.parameters():
            param.requires_grad = False

feature_extract = True
batch_size = 8
num_epochs = 15
num_classes=12

model_ft = resnet50(pretrained=True)
set_parameter_requires_grad(model_ft, feature_extract)
num_ftrs = model_ft.fc.in_features
model_ft.fc = nn.Linear(num_ftrs, num_classes)
input_size = 224

if torch.cuda.is_available():
    model_ft.cuda()

params_to_update = model_ft.parameters()

print("Params to learn:")
if feature_extract:
    params_to_update = []
    for name,param in model_ft.named_parameters():
        if param.requires_grad == True:
            params_to_update.append(param)
            print("\t",name)
else:
    for name,param in model_ft.named_parameters():
        if param.requires_grad == True:
            print("\t",name)

# Observe that all parameters are being optimized
optimizer_ft = optim.SGD(params_to_update, lr=0.001, momentum=0.9)

# Setup the loss fxn
criterion = nn.CrossEntropyLoss()

Finally, here is the problematic training function

for epoch in range(num_epochs):  # loop over the dataset multiple times

    running_loss = 0.0
    for i, data in enumerate(dataloader, 0):
          
        # get the inputs; data is a list of [inputs, labels]
        inputs, labels = data
            
        #transfer labels and inputs to cuda()
        inputs,labels=inputs.cuda(), labels.cuda()
    
        # zero the parameter gradients
        optimizer.zero_grad()

        # forward   backward   optimize
        outputs = model_ft(inputs)
        loss = loss_func(outputs, labels)
        loss.backward()
        optimizer.step()

        # print statistics
        running_loss  = loss.item()
        if i % 2000 == 1999:    # print every 2000 mini-batches
            print(f'[{epoch   1}, {i   1:5d}] loss: {running_loss / 2000:.3f}')
            running_loss = 0.0

This returns me the following error once I execute the code:

Traceback (most recent call last):
  File "train_my_data_example.py", line 89, in <module>
    for i, data in enumerate(dataloader, 0):
  File "/usr/local/lib/python3.8/dist-packages/torch/utils/data/dataloader.py", line 517, in __next__
    data = self._next_data()
  File "/usr/local/lib/python3.8/dist-packages/torch/utils/data/dataloader.py", line 557, in _next_data
    data = self._dataset_fetcher.fetch(index)  # may raise StopIteration
  File "/usr/local/lib/python3.8/dist-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/usr/local/lib/python3.8/dist-packages/torch/utils/data/_utils/fetch.py", line 44, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "train_my_data_example.py", line 29, in __getitem__
    y = self._y[index, :]
IndexError: too many indices for array: array is 1-dimensional, but 2 were indexed

The error is clearly the dataloader variable, so is this creation ok? I mean, I am loading NumPy data and transforming it to a data loader as below:

transform = transforms.Compose([transforms.ToTensor()])
dataset = MyDataSet("train1-features.npy","train1-classes.npy",transform=transform)
dataloader = DataLoader(dataset, batch_size=32)

Is there any error in my data loader or is the problem the training loop of Pytorch?

P.s: you can reproduce my code by downloading the classes and features here

CodePudding user response：

You are trying to index the second axis of an array which only has a single dimension. Simply replace y = self._y[index, :] with y = self._y[index].

Actually when positioned last, : is not required as all dimensions are selected by default.