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
-1
votes
1 answer

Image size (324768098 pixels) exceeds limit of 178956970 pixels, could be decompression bomb DOS attack

Was facing an issue in classification model trained on fastai. Running images in batches on a classification model. But due to 1 image, entire batch is failing. The classification model when trained was trained on preprocessed images, by applying…
Arastu Mudgal
  • 1
  • 1
-1
votes
1 answer

Training the AI model taking so long

I am solving a multi-class classification problem.The data set looks like below : |---------------------|------------------|----------------------|------------------| | feature 1 | feature 3 | feature 4 | feature 2 …
Ricky
  • 2,662
  • 5
  • 25
  • 57
-1
votes
1 answer

SyntaxError when passing async=True to function

from fastai.conv_learner import * from fastai.dataset import * import pandas as pd import numpy as np import os from PIL import Image from sklearn.model_selection import train_test_split I got following error during import cuda 10.1 tensorflow =…
user11173832
-1
votes
1 answer

fastai tabular model trained but can not find categorical mapping

After training my dataset which has a number of categorical data using fastai's tabular model, I wish to read out the entity embedding and use it to map to my original data values. I can see the embedding weights. The number of input don't seem to…
bhomass
  • 3,414
  • 8
  • 45
  • 75
-1
votes
1 answer

Colab running out RAM

I've been working on kaggle's dataset Favorita Grocery sales. I'm trying to use the function add_datepart from fast.ai but when I invoke add_datepart, Colab runs out of RAM. Is there any remedy for this? Any way around this?
Husun
  • 29
  • 1
  • 7
-1
votes
1 answer

My fast.ai install wasn't working in Windows 7. Hope things are fixed these days

[from 2018] I created a new Windows 7 admin account for development so there's no spaces in directory names. I installed Anaconda for Windows and ran a git copy for fast.ai. I ran a conda activate environment for the CPU version of fast.ai, and at…
Kevin Crosby
  • 29
  • 6
-2
votes
0 answers

Fastai appears to be slower than PyTorch Lightning

I noticed that Fastai appears to be slower than PyTorch Lightning on my machine. For instance, the code below is used to classify the CIFAR-10 dataset. It utilizes a ResNet32 model implemented by Timm and was trained for a total of 20 epochs. The…
lllIlllllIll
  • 19
  • 4
-2
votes
1 answer

How to load best model in fastai tsai

I am using below code in tsai library to train my timeseries binary classification model. But I am unable to get the same accuracy on validation set when I try to load the best model and then test validation data on it. Perhaps my method of loading…
Granth
  • 325
  • 4
  • 17
-2
votes
2 answers

Is FastAI performing transfer learning when calling a vision learner?

learn = vision_learner(dls, models.resnet18) In the above code snippet, I am calling a Vision Learner Resnet 18 model using FastAI and passing in a Dataloader containing my data. I wonder if this process is performing any transfer learning within…
M5RKED
  • 73
  • 1
  • 16
-2
votes
1 answer

Prediction on image with different size

Is is possible to run prediction on images with different sizes than the training data? I have trained a unet_learner on pictures of a certain size (1000*1000) and exported it for later use. I then load it with the following: learn =…
Morten
  • 3,778
  • 2
  • 25
  • 45
-3
votes
1 answer

When to use learning rate finder

Reading the paper ' Cyclical Learning Rates for Training Neural Networks' https://arxiv.org/abs/1506.01186 Does it make sense to use the learning rate finder if the model is over-fitting ? Other than reduce the number of iterations before the model…
blue-sky
  • 51,962
  • 152
  • 427
  • 752
-4
votes
1 answer

Python Calling Current Directrory

I am using fasitai library and when ı tried the loading model ı want to take model from current directory. learn = load_learner('This arg. have to my current directory','model.pkl') I tried os.get_cwd() and ' ./ ' but they aren't worked. Thanks
Hamdi KAPTAN
  • 58
  • 7
-4
votes
1 answer

Python - importing fastai results in SyntaxError

I am trying to setup an ML model using fastai and have to do the following imports: import fastai.models import fastai.nlp import fastai.dataset However, it gives me the following error by the fastai imports. Python 2.7.15rc1 (default, Apr 15…
Fan
  • 217
  • 3
  • 14
1 2 3
…
28
29