Questions tagged [fastai]

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

18 questions
4
votes
2 answers

Is it advisable to use a model which is underfit but gives very high accuracy?

I am training a model for a single-label classification task in Vision. In this training, I am using oversampling of all the classes, and MixUp augmentation, along with rotation and dihedral transformations to augment data. What happens is, the…
3
votes
1 answer

How to specify version for dependencies so that each one is compatible and stays within a size limit?

I am trying to deploy a web app to Heroku. The free tier is limited to 500 MB. I am using my resnet34 model as a .pkl file. I create model with it using the fastai library. This project requires torch and torchvision as dependencies. But not…
truth
  • 280
  • 1
  • 8
2
votes
2 answers

Face recognition - How to make an image classifier with large number of classes?

I am planning to make an image classifier that identifies the face of every player in the English Premier League. I have a couple of questions (since until now I have only worked with small or academic datasets). My questions: How do I download…
Shawn
  • 173
  • 1
  • 4
1
vote
2 answers

How imagenet mean and std derived?

To use pre-trained models it is a preferred practice to normalize the input images with imagenet standards. mean=[0.485, 0.456, 0.406] and std=[0.229, 0.224, 0.225]. How are these parameters derived?
Wickkiey
  • 299
  • 3
  • 10
1
vote
1 answer

fastai - using 'untar_data' function in kaggle kernel

I have recently started with fastai lesson 1 and I am using kaggle to run the course notebooks. While going through the ‘lesson1-pets’ notebook we use untar_data(URLs.PETS) to get the data. What I want to understand is where does this data get…
boredaf
  • 161
  • 1
  • 8
1
vote
2 answers

Classification with a lot of the classes

I’m trying to make model which will classify text into about 500 different classes. I think that I have to customize architecture of the Pooling Classifier which looks now like this: (1): PoolingLinearClassifier( (layers): Sequential( (0):…
1
vote
0 answers

Improve performance of my CNN model

I am working on an image classification problem. There are 876 images in the training and 600 in the test dataset. It is a multi class classification for plants. Since this is my first CNN problem, I started working with tensorflow and keras to…
1
vote
1 answer

Arguments in python fast.ai function that are not in the function definition?

I have been coming across function calls that use arguments that are not in the function definition. I would like to know how that works (i.e. how the compiler interprets this). For example, this function call: …
user637140
  • 201
  • 1
  • 5
0
votes
1 answer

How to handle imbalanced NLP text data set e.g. some classes only have 2 records

I am working on a dataset with around 2000 records. Around 80% records have their the categorical labels. There are around 200 categories, some categories got more than 20 records; whereas others only have TWO.... Considering this is a text dataset,…
Franva
  • 133
  • 6
0
votes
2 answers

Fast AI Lesson 4 - MNIST. Confused about multiplying weights by pixels?

I’m on lesson 4 of the Fast AI "Deep Learning for Coders" course, and have been back through the same lesson a few times now but I don’t think I’m quite getting a few things. I want to have an understanding of what’s going on before moving on. This…
Andrew
  • 101
  • 1
0
votes
0 answers

AttributeError: normalize using fastai

I'm trying to use fastai to train a model but I am getting this error when I try to normalize my data using imagenet stats. Can someone pls help me with it? #build fastai dataset loader np.random.seed(42) #fastai automatically factors the ./train…
Soumya
  • 1
0
votes
1 answer

Bad performance with CNN for basic image classification task

how are you doing? I'm playing around with CNN in FastAI. My model with 2 millions parameters only has around 80% accuracy. I also tried with Data normalization, Batch normalization, Label smoothing, Mixup but the results are still capped at 80-81%…
0
votes
0 answers

The best approach and library for time-series similarity

I have a time-series classification problem with IoT signals. The training dataset has seven target signals. I used tsai as a fastai/torch library, and I achieved satisfying results. However, in a production environment, there is a larger number of…
0
votes
0 answers

How to improve neural network for face classification?

I generated 700 1024x1024 images of female faces using an API. I labelled them either as attractive or unattractive. The neural net should learn which face I find attractive and which not. But the accuracy is worse than a random guess. To crop the…
0
votes
0 answers

How to use a Swin Transformer with metric learning?

Using timm's implementation of Swin Transformer, how does one generate an embedding vector? I would like to use timm's SwinTransformer class to generate an embedding vector for use with metric learning (sub-center ArcFace). What I've tried: To…
Larry OBrien
  • 111
  • 4
1
2