Stack Overflow
Stack Overflow

Questions tagged [fast-ai]

Fastai is a deep learning library for Python. It is built on top of PyTorch, and provides high level API to various common deep learning applications and data types.

Fastai is a deep learning library for Python. It is built on top of PyTorch, and provides high level API to various common deep learning applications and data types. For more information see: https://docs.fast.ai or https://github.com/fastai

433 questions
0
votes
1 answer

How can I use this dataset to train a fast.ai model to recognize the pupil-limbus ratio?

UPDATE: I have created the dataset and run the model here: https://github.com/woodytwoshoes/Eyetrain.git I'm a medical student trying to produce a machine learning model which recognizes a particular feature of the eye: the Pupil-Limbus…
Woodsworthy Wordsworth
  • 1
  • 4
0
votes
1 answer

Saving then reusing CNN models - preserving initializations

I wish to repeat a series of image classification experiments by reusing a CNN with the same CNN with identical hyperparameters especially initializations. So, if I save a model after I have instantiated it and before I train it, does that also save…
Winston Dodson
  • 31
  • 4
0
votes
1 answer

How the VM instance set up on gcloud contains the fast.ai tutorials already?

I am just about to start the fast.ai course and have followed the instruction to set up the VM instance on Google Compute Cloud. Surprisingly I found that when I started the instance and opened localhost:8080/tree, there is already a folder called…
user10661584
0
votes
1 answer

untar_data from fast.ai fails to download dataset

This piece of code: from fastai.vision import * path = untar_data(URLs.CAMVID) logs this to console: Downloading https://s3.amazonaws.com/fast-ai-imagelocal/camvid but download never really finishes. If you open this url, you get: How can I fix…
Stepan Yakovenko
  • 8,670
  • 28
  • 113
  • 206
0
votes
1 answer

How to get penultimate layer output of fastai text model?

learn = text_classifier_learner(data_clas, AWD_LSTM, drop_mult=0.7) learn.fit_one_cycle(1, 1e-2) I have trained fastai model as above. I can get prediction as below preds, targets = learn.get_preds() But instead I want penultimate layer embeddings…
Ravikrn
  • 387
  • 1
  • 3
  • 19
0
votes
1 answer

FastAI v1 PyTorch Custom Model

i have been trying to use fastai with a custom torch model. My code is as follow: X_train = np.load(dirpath + 'X_train.npy') X_valid = np.load(dirpath + 'X_valid.npy') Y_train = np.load(dirpath + 'Y_train.npy') Y_valid = np.load(dirpath +…
Tolga Oguz
  • 142
  • 1
  • 14
0
votes
1 answer

TextLMDataBunch Memory issue Language Model Fastai

I have a dataset with 45 million rows of data. I have three 6gb ram gpu. I am trying to train a language model on the data. For that, I am trying to load the data as the fastai data bunch. But this part always fails because of the memory issue.…
Jerry George
  • 71
  • 7
0
votes
2 answers

Fastai issue with TextLMDataBunch and language_model_learner

Tried to replicate this code using fastai lib, but I'm running in two major issues. This par of code: data_lm = TextLMDataBunch.from_df('data', train_df, valid_df, text_cols='idea') Gives this kind of…
Stanyko
  • 95
  • 3
  • 15
0
votes
1 answer

i can't use pretrained_model=URLs.WT103 from fastai.text

I'm trying to create a model that predicts a word as input and output as paragraph. I get an error when trying to implement the same example given on fastai|text to my own data set. It gives an error in the following step. When you reviewed the…
Ali.Turkkan
  • 266
  • 2
  • 11
0
votes
1 answer

Set higher shared memory to avoid RuntimeError with PyTorch on Google Colab

Using pytorch 1.0 Preview with fastai v1.0 in Colab. I often get RuntimeError: DataLoader worker (pid 13) is killed by signal: Bus error. for more memory intensive tasks (nothing huge). Looks like a shared memory…
jeffhale
  • 3,759
  • 7
  • 40
  • 56
0
votes
1 answer

Running out of memory when building a language model in Fast.ai 1.0

I'm dealing with a rather large text dataset (5.4 million short texts) and I'm trying to perform sentiment analysis con them on 16GB of ram. I keep running out of memory whenever I try to build the language model: data_lm =…
Salva Marti
  • 1
  • 1
0
votes
1 answer

Keep Getting Permission denied when using fastai library on AWS setting

I'm learning deep learning by taking a lecture that uses fastai. I'm running fastai library on AWS p2.xlarge. When I ran some function on fastai library I get this error.: Traceback (most recent call last) in…
joseya7
  • 53
  • 8
0
votes
1 answer

Pytorch installation issue under Anaconda

I followed the link here to install fastai library using pip install git+https://github.com/fastai/fastai.git It gave me the following error message. These messages keep the same even I installed Pytorch successfully using conda install…
user288609
  • 12,465
  • 26
  • 85
  • 127
0
votes
3 answers

Cannot run fastai library on Jupyter Notebook

I hope this question is not redundant, but I couldn’t find a solution on the internet so far. I’ve followed the github guide (https://github.com/fastai/fastai) to install the fastai library on my Anaconda environment. I want to use this library to…
calicationoflife
  • 281
  • 2
  • 8
  • 17
-1
votes
0 answers

'NoneType' object is not iterable in colab

import numpy as np np.random.seed(42) path_data = Path(base_dir+'faces/images/images') data = ImageDataLoaders.from_folder(path_data, train="train", valid="validation", ds_tfms=aug_transforms(), size=224,…
卢明达
  • 1
1 2 3
…
28
29