Just did looks to be good, only bit I read was about mobile streaming Iād need over 1k subscribers or more
Very exciting! Iām particularly interested in the tabular part.
You never know. I never dream of my local study group grows over 2.3K members and is still growing.
Youāll certainly be more intrigued by the fourth lesson (in the tabular block)! I revised it to try to let us experiment with the new architectures that have come out over the last year or so (NODE, TabNet, etc).
@muellerzr excited to watch this. Do you happen to have a step by step for fastai v2 for GCP? I followed the steps outlined here:https://course.fast.ai/start_gcp.html and successfully setup the server with v1 but canāt seem to wrap my head around getting v2 running.
much appreciated and looking forward to class.
I donāt use GCP, so Iām unsure about that. What have you tried so far?
I tried conda install -c fastai -c pytorch fastai
but couldnāt find where fastai v2 would be in the vm terminal.
and am confused about the other suggestion of this. because I donāt see where fastai2 would be in the terminal
cd fastai2
conda env create -f environment.yml
source activate fastai2
Youād need to either git clone the fastai2 repo (to get fastai2) or do a pip install fastai2. Try the install directions here:
I guess my confusion with this, is where I am supposed to be changing the directory into fastai2, or am I supposed to create it first?
Thanks for the help.
From what I can read (@sgugger correct me if Iām wrong here):
Clone the repo into some base directory to run out of
cd and Conda activate
The conda install of fastai2 is not super well tested, I would strongly encourage using a developer install using pip for now.
cool that did the trick! thanks @sgugger and @muellerzr for the help.
For anyone other newbies out there, I followed this:
pip install packaging
git clone https://github.com/fastai/fastai2
cd fastai2
pip install -e .[dev]
Iāll also add that in the Wiki as GCP instructions
Edit: done. Thanks for trying that out @jankelowitz!
no problem, going through dev pets tutorial to make sure I actually did it right
@muellerzr Thanks for the initiative! Iām in, although Iāll be watching the recordings since 5 pm CST is midnight CET. But I already blocked my Thursday nights for that.
That is supercool. Looks like Iām living under the rock and still under the impression that no architectures except fully-connected layers is applicable here.
That do you recommend to try at first NODE, TabNet or maybe something else? I donāt think I will be able to overcome all of them
What worked best in your cases, if you was already able to try it (or what is your intuition on what will play better/have more potential)
@Pak NODE looks to be the āeasiestā (Iām reworking my implementation to solve some headaches). Thereās some cost benefit with both (that I plan on going over). TabNet Iām yet to play with but itās one that I saw that looked interesting. I have my own intuition about a paper that came out in which the data was embedded in a 2d space (aka they wrote the variables on a picture) and I think we can push that further, Iāll be testing that out this week or so (and if it works youāll see it here, if not you wonāt!)
Am I right that you mean these notebooks https://github.com/muellerzr/Practical-Deep-Learning-for-Coders-2.0 (tabular in this repository)?
Awesome I will definitely watch your github on that.
As well as will watch your stream.
Not yet, Iām working on them now. Iāll announce the course repo once itās closer (so thereās little questions on them beforehand and cause Iām in the middle of making a few of them right now). I donāt have have the Tabular implementations done yet (Iām finishing vision block this week). I believe thereās an old NODE thread where I posted an example (very very messy example) with fastai v1
@muellerzr I was trying the second notebook 02_Custom_Image_Classification.ipynb via colab and had the following error.
The file is not being read as a file but as a string. I tried with the following
file = open(path/files[i])
download_images(file, path/folders[i], max_pics=50)
This time it downloads the files but none of them are proper images and therefore the verify_images deletes all of them. I can attach the url_text files here if you want. Wanted your help to know if it is an issue with the code or the way I am doing things here.