Fitting the MNIST dataset to neural network giving “NotImplementedError”

(Harshit) #1

I’m new to PyTorch and I’m using the MNIST dataset for image classification as in Chapter 8.While fitting the model, I’m getting the error :

NotImplementedError: uint8

The code I’m using is as follows :

from keras.datasets import mnist
import matplotlib.pyplot as plt
from fastai.metrics import *
from fastai.model import *
from fastai.dataset import *
import torch.nn as nn

(x_train, y_train), (x_valid, y_valid) = mnist.load_data()

net = nn.Sequential(
  nn.Linear(784,10),
  nn.Softmax()).cuda()

md = ImageClassifierData.from_arrays('/data/mnist', 
(x_train,y_train), 
(x_valid, y_valid))   

loss = nn.NLLLoss()
metrics = [accuracy]
opt=optim.SGD(net.parameters(), 1e-1, momentum=0.9, weight_decay=1e-3)

fit(net, md, n_epochs=3, crit=loss, opt=opt, metrics=metrics)

I have spent awful amount of time figuring this out but sadly I couldn’t. Can someone tell what is this error about and it’s solution?

0 Likes