Lesson 1 In-Class Discussion ✅

I guess this is what you are looking for http://course-v3.fast.ai/#using-a-gpu

anyone running the lesson on a old gpu?

Or did you meant this

1 Like

yes we are using own gpu (nvidia geforce 1080ti) and we are facing some issue with nvidia drivers. will post shortly in another place

The batch size indicates the number of images the computer is processing at once. So if greater it runs out of memory. It is always better to start out with these numbers depending on your GPU Ram. Nothing to do with divisibility.

1 Like

If anyone is using Jupyterlab and find that the progress bars don’t show up you need to ensure jupyter widgets are installed properly using jupyter labextension install @jupyter-widgets/jupyterlab-manager. You need to have node.js installed for this to work.


Nice, thanks. Never knew the forum software outside the text box had keyboard shortcuts.

1 Like

Yes - your validation set can help you choose or compare certain hyperparameters or tune certain “values”. Your test set is used after you’ve chosen these “values”.

1 Like

nice one! thanks!
more info on 1 cycle policy: https://sgugger.github.io/the-1cycle-policy.html


No, for inference GPU is not needed. CPU’s is good for most of inference on most of trained models.

nor me, I’m pleased to know this

This may also be helpful : https://forums.fast.ai/t/platform-gcp/27375

FYI I’ve removed the various questions about setup, since they should go in to the dedicated topics listed in the FAQ. I’ve also removed a lot of the “thanks” etc posts. Hopefully the thread is a little easier to read now.


There are quite a few forum posts on collecting your own images



Validation set


I’m having the same issue with the padding_mode needs to be ‘zeros’ or ‘border’ but got reflection… I’ll try the update of the pytorch as the next posts indicates, see if that works better

I got this error:

ImportError                               Traceback (most recent call last)
<ipython-input-4-67a75a9cc9b3> in <module>()
      1 # Import necessary libraries
----> 2 from fastai import *
      3 from fastai.vision import *
      4 import matplotlib.pyplot as plt

~/anaconda3/lib/python3.6/site-packages/fastai/__init__.py in <module>()
----> 1 from .basic_train import *
      2 from .callback import *
      3 from .callbacks import *
      4 from .core import *
      5 from .basic_data import *

~/anaconda3/lib/python3.6/site-packages/fastai/basic_train.py in <module>()
      1 "Provides basic training and validation with `Learner`"
----> 2 from .torch_core import *
      3 from .basic_data import *
      4 from .callback import *

~/anaconda3/lib/python3.6/site-packages/fastai/torch_core.py in <module>()
      1 "Utility functions to help deal with tensors"
----> 2 from .imports.torch import *
      3 from .core import *
      5 AffineMatrix = Tensor

~/anaconda3/lib/python3.6/site-packages/fastai/imports/__init__.py in <module>()
      1 from .core import *
----> 2 from .torch import *

~/anaconda3/lib/python3.6/site-packages/fastai/imports/torch.py in <module>()
      1 import torch, torch.nn.functional as F
      2 from torch import ByteTensor, DoubleTensor, FloatTensor, HalfTensor, LongTensor, ShortTensor, Tensor
----> 3 from torch import nn, optim, as_tensor
      4 from torch.utils.data import BatchSampler, DataLoader, Dataset, Sampler, TensorDataset

ImportError: cannot import name 'as_tensor'

I have ubuntu local machine. I tested pip install fastai==0.7.0 which worked for some people (ImportError: cannot import name 'as_tensor'?) but not for me.

Open a terminal and try this

python3 -c "import torch;from torch import nn, optim, as_tensor"
1 Like

File “”, line 1
SyntaxError: invalid character in identifier
from: can’t read /var/mail/torch

The forum changed the character… its double or single quotes

1 Like