Thanks fast.ai (@sgugger, @rachel, @jeremy) for your work on these lectures (and the library of course). Just wrapped up Part 1 of the course and my notes are here: https://sites.google.com/view/raybellwaves/courses/fast-ai
Heya I’m an enterprise sales rep interested in ML. I’ve never done any coding, and I’m wondering: what is the best way to get the 1 year required experience for Fast.ai?
Thanks!
Hi Jeremy/all,
I would like to what’s the average training time for the course projects and whether it would be necessary to use TPUs?
I am working to collect a list of projects that suffer from long training times and technique toward accelerating them.
Best,
Mahdi
Hi WeWalk hope you are well!
The above link has many free tutorials. If I were in your position I would complete two of the tutorials/courses typing in the code by hand absolutely no cutting and pasting. I would especially choose a course that has a web part where you deploy an app online.
Once I have competed the above I would create my own app and deploy it using GitHub and Docker.
When all the above was complete I would start the fastai course.
Jeremy recommends typing all the notebooks by hand when you start and checking how much you can remember especially the main stages.
One of the many people who inspire me on this site is the person who wrote this post. How do you... learn? (and study)
His output is prolific.
If you do most of the above I am sure you will find the whole course/journey inspiring.
Cheers mrfabulous1 
Hi Everyone,
I just needed a clarification on how we should run our jupyter notebook when we have a bigproject, for example currently I have to run my code again from the beginning each time I start the notebook.
I am currently at the lesson 2 and trying with my own dataset, I have been working on it for a few days, but everytime I need to start from beginning like downloading the urls. Is there any thing that I can do about this?
I am new in deep learning, hope I come out better from this course!
Happy new year everyone!
I am so pumped up right now after listening to first lecture. I have couple projects in my mind. Wish me good luck to make it happen.
love u
be consistent man. sure you will do
Hi pratikw hope all is well!
I am sure that if you follow Jeremie’s advice and type in everything by hand, experiment and get to lesson 8 you will come out better.
Cheers mrfabulous1
Hi ,
Is there any difference in topics covered in v2 and v3. I initially took Andrew Ng Deep Learning course now looking to take the course in Fast ai and confused between v2 and v3. Digging deep I found topics like Darknet covered in v2 which I am more interested in, I am planning to do a project which requires YOLO algorithm for realime detection.
Everyone seems to advice to take Practical Deep Learning for Coders 2019 first.
Does v3 covers topics related to realtime object detection??
1 Like
I couldn’t find the option to create topic so,i am publishing my doubt here,folks
While implementing a Neural Network on a tabular data,i m facing this error in learn.predict function
KeyError Traceback (most recent call last)
/usr/local/lib/python3.6/dist-packages/pandas/core/indexes/base.py in get_loc(self, key, method, tolerance)
2896 try:
-> 2897 return self._engine.get_loc(key)
2898 except KeyError:
pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()
pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()
pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item()
pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item()
KeyError: ‘Review’
During handling of the above exception, another exception occurred:
KeyError Traceback (most recent call last)
10 frames
/usr/local/lib/python3.6/dist-packages/pandas/core/indexes/base.py in get_loc(self, key, method, tolerance)
2897 return self._engine.get_loc(key)
2898 except KeyError:
-> 2899 return self._engine.get_loc(self._maybe_cast_indexer(key))
2900 indexer = self.get_indexer([key], method=method, tolerance=tolerance)
2901 if indexer.ndim > 1 or indexer.size > 1:
pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()
pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()
pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item()
pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item()
KeyError: ‘Review’
Can somebody help me out?
what is callback? why are there so many different callbacks ? how to use them?
Hi am.sharan hope all is well!
The callback system in the fastai library allows you to execute any code at specific times in the training. This can be extremely useful if you want to
record some parameters (for instance metrics, gradients) use a condition to change a parameter (for instance change the learning rate if the validation loss hasn't improved) make a schedule of parameters (for instance changing the probabilities of the dropout layers as the training goes)
The above quote is from a notebook in this link Using the callback system in fastai
I also found these posts useful to. https://medium.com/@edwardeasling/implementing-callbacks-in-fast-ai-1c23de25b6eb
https://medium.com/ai³-theory-practice-business/callback-fastai-09-436615d07186
Cheers mrfabulous1
Hello everyone. I competed in my first ever Kaggle competition (MNIST), and now i’m looking for a similar Kaggle beginner friendly competition in image classification. any suggestions ?
1 Like
@Miske
If you want to try out another MNIST kind of dataset try-
MNIST like datatset for Kannada handwritten digits ( https://www.kaggle.com/c/Kannada-MNIST )
Else you want to graduate to more ‘real-image’ kind of competitions, here is a list from the archives ( this is a little dated - there are newer ones though )
| About | Link |
|---|---|
| State Farm Distracted Driver Detection ( Can computer vision spot distracted drivers?) | https://www.kaggle.com/c/state-farm-distracted-driver-detection |
| Airbus Ship Detection Challenge - Find ships on satellite images as quickly as possible | https://www.kaggle.com/c/airbus-ship-detection |
| Cdiscount’s Image Classification Challenge (Categorize e-commerce photos) | https://www.kaggle.com/c/cdiscount-image-classification-challenge |
| Aerial Cactus Identification (Determine whether an image contains a columnar cactus) | https://www.kaggle.com/c/aerial-cactus-identification |
| Dog Breed Identification (Determine the breed of a dog in an image) | https://www.kaggle.com/c/dog-breed-identification |
| iMaterialist Challenge (Furniture) at FGVC5(Image Classification of Furniture & Home Goods.) | https://www.kaggle.com/c/imaterialist-challenge-furniture-2018 |
| Plant Seedlings Classification(Determine the species of a seedling from an image) | https://www.kaggle.com/c/plant-seedlings-classification |
5 Likes
Thank you very much . This reply helped.
Hi guys,
I am not sure if this is the right place to ask, I will give it a shot.
This course talked a lot about “progressive resizing” the input image size, when solving a image classification task. I want to implement this in my thesis I am writing, Jeremey once mentioned a paper regarding this topic, but I can’t find any literature about this method. Could you help me out?
Thanks!
Hi,
Is there an issue with the files.fast.ai servers ?
path = untar_data(URLs.MNIST_SAMPLE); is failing with a connection timeout error – while the ones hitting s3 work just fine.
http://files.fast.ai/data/examples/mnist_sample – doesn’t work.
https://s3.amazonaws.com/fast-ai-imageclas/mnist_png – works
ConnectTimeout: HTTPConnectionPool(host=‘files.fast.ai’, port=80): Max retries exceeded with url: /data/examples/mnist_sample.tgz (Caused by ConnectTimeoutError(<urllib3.connection.HTTPConnection object at 0x7f67705483c8>, ‘Connection to files.fast.ai timed out. (connect timeout=4)’))
hi guys seems like your SSL certs expired ?
the file still exists – just the ssl certs are bad ?
hey so I’m getting through the fastai deep learning courses and I was wondering if there was any one that talked about choosing the right metrics for the types of data you may encounter?