RuntimeError: The size of tensor a (115) must match the size of tensor b (64) at non-singleton dimension 1

kushaj · July 21, 2019, 5:40pm

The problem has something to do with batch size. Can you try explicitly setting batch size=64 in the databunch and see if there is any difference.

seanoconnor · July 21, 2019, 5:52pm

Hi Kushajveer,

I changed it to 64 but am still receiving the same error…

kushaj · July 21, 2019, 5:54pm

Try the same code for MNIST sample data and see if the error persists. I tried with your code and I got no error.

seanoconnor · July 21, 2019, 6:01pm

Just tried with MNIST sample data and I am still receiving a similar error

RuntimeError: The size of tensor a (3) must match the size of tensor b (64) at non-singleton dimension 1

kushaj · July 21, 2019, 6:06pm

It is probably a version issue. Update fastai. Mine version is 1.0.55 and your code is working on my machine.

seanoconnor · July 21, 2019, 6:08pm

Strange, mine is the same. Do you mind if you copy and paste your MNIST code so I could compare where i am going wrong please?

kushaj · July 21, 2019, 6:11pm

path = untar_data(URLs.MNIST)

np.random.seed(42)
data = (ImageList.from_folder(path) 
                 .split_by_rand_pct(0.2)             
                 .label_from_folder()            
                 .transform(get_transforms(), size=128)
                 .databunch().normalize(imagenet_stats))

architecture = models.resnet34
acc_02 = partial(accuracy_thresh, thresh=0.2)
f_score = partial(fbeta, thresh=0.2)
learn = cnn_learner(data, architecture, metrics=[acc_02, f_score])

lr = 0.01
learn.fit_one_cycle(5, slice(lr))

I ran for 1 epoch and it is working.

kushaj · July 21, 2019, 6:16pm

I came to the conclusion early. This is giving an error but after the epoch is run. Wait few minutes, I will try to resolve it .

seanoconnor · July 21, 2019, 6:21pm

Yeah I am still getting errors. I will wait.

kushaj · July 21, 2019, 6:28pm

Oh I forgot we are doing single label classification. These metrics are meant for multi-label problems.

seanoconnor · July 21, 2019, 6:29pm

Excuse my ignorance bu why does that matter? Surely there should be a accuracy score and f_score anyway?

kushaj · July 21, 2019, 6:30pm

To use these metrics you have to give one-hot encoded inputs but in fastai by default for single label problems the labels the labels are not one-hot encoded.

kushaj · July 21, 2019, 6:31pm

You can create a custom callback where you convert your labels to one-hot encoded format and then use the metric there.

seanoconnor · July 21, 2019, 6:32pm

Ah okay, so what is a better metric to use?

kushaj · July 21, 2019, 6:35pm

They are for different purposes. If you have multi label problem, then with accuracy_thresh you are calculating how much error is there is I select all the classes greater than this thresh.

In F-score you are measuring how much precision and recalll you are able to get after setting a thresh.

kushaj · July 21, 2019, 6:36pm

This article can help link.

seanoconnor · July 21, 2019, 6:38pm

Great, I changed it to error rate and the pochs are running successfully, thank you so much for your help kushaj!!!

YoungProgrammer · September 29, 2019, 7:58pm

Hey I’m doing a project similar to this but for myself and I’m also running into this error.
More like this tho:
RuntimeError: The size of tensor a (128) must match the size of tensor b (4096) at non-singleton dimension 1
I can’t do large batch sizes because my computer is really weak.
I was wondering if you could help

nofreewill · January 20, 2020, 5:20pm

Thanks. I had this error with batch size of 1, 2, 4, and 6. Now with 8 I don’t get the error somehow. Feels a bit magic.

panggraduate · January 25, 2021, 12:30pm

hello I also met this question :RuntimeError: The size of tensor a (4096) must match the size of tensor b (65536) at non-singleton dimension 1 .I tried to change batch_size and checked the version of torch ,both failed , can you give me some advice? I am appreciate if you could help.