RuntimeError: tried to construct a tensor from a int sequence, but found an item of type float at index (0)

hafidz_zulkifli · February 5, 2018, 7:45pm

I’m currently getting the above error when trying to fit a model on pytorch, and I have no idea how to fix it. Am hoping that any of you might have an idea to share or provide guidance on how to solve this.

The error dump is as below.

gist.github.com

https://gist.github.com/ikanez/ea4224f46102270aaf40e77396179a72

found an item of type float at index (0)

---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
<ipython-input-37-16682764c468> in <module>()
----> 1 fit(m, md, 1, lo.opt, F.binary_cross_entropy)
      2 # use F.binary_cross_entropy for multi-label problems

~\Dropbox\3.SelfStudy\fastai_pytorch\fastai\courses\dl1\fastai\model.py in fit(model, data, epochs, opt, crit, metrics, callbacks, **kwargs)
    104             i += 1
    105 
--> 106         vals = validate(stepper, data.val_dl, metrics)

This file has been truncated. show original

Actual code can be referred to here:

github.com

ikanez/kaggle/blob/master/kaggle-toxic-comments.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import spacy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import torchtext"
   ]
  },

This file has been truncated. show original

I’m currently using pytorch with fast,ai library in Windows 10 environment.