PyTorch Beginner Tutorial - Training an Image Classification Model and putting it online!
Вставка
- Опубліковано 7 гру 2020
- In this tutorial we'll be training a Deep Learning Model with PyTorch 1.7 and FastAI in a beginner-friendly way. I will explain how to use Machine Learning and the basics about how it works. At the end you will have a public website up and running where your Model is deployed using Flask, Python and Docker.
Sorry for some of the audio issues!
*Links related to Tutorial*:
Github Link: github.com/Sebastian-Schuchma...
My example site: churros-or-samosa.site/
Distill Link (Visualizations): distill.pub/2017/feature-visu...
Docker Link: www.docker.com/products/docke...
Render Link: render.com
How to Git: support.gitkraken.com/start-h...
Book recommendation: www.oreilly.com/library/view/...
*Other Links*:
Support me on Patreon: www.patreon.com/user?u=25285137
ML-Agents Discord Channel: / discord
Keep in touch: / sebastianschuc7
*Timestamps*:
00:00: Intro
00:30: Downloading Dataset
02:44: How Neural Networks work
05:57: Training the Model
11:17: Inside a Neural Network
13:41: Exporting the Model
15:50: Building the Website
18:04 Deploying the Website - Наука та технологія
![Build Your First Pytorch Model In Minutes! [Tutorial + Code]](http://i.ytimg.com/vi/tHL5STNJKag/mqdefault.jpg)
Awesome channel, consistent information and extraordinary performance. Great to be a part of this great community. I am very happy you Sebastian has created something specials. Thanks. Have a nice day!
I've been desperately looking for a legitimately beginner-friendly channel on machine learning, so glad I found yours!!
Great beginners tutorial . Thank you so much!
Thank you for this video, You make learning fun. Keep making such videos pls
Wow owow......u have implemented ur training model using the fastai framework. I just bunked in this video out of sheer luck. There is hardly any videos on cnn that trains a model using fastai framework. Please please upload more videos of this kind. Looking forward to it. Cheers!!!
Thank you so much for this video!!!
Amazing🔥
When we upload the image of Churros, does the dimension has to be 224 x 224? Coz I just uploaded churros image of different dimension and it is giving me Samosa answer even though it is churro pic.
Man you are awesome!
I've tried to use my own datasets but the error kept on coming up
What could possibly go wrong here?
#I only change the path
dls = ImageDataLoaders.from_name_func(
mixed_path, get_image_files(mixed_path), valid_pct=0.05, seed=420,
label_func=GetLabel, item_tfms=Resize(256))
dls.train.show_batch()
#That's the error
TypeError Traceback (most recent call last)
in ()
1 dls = ImageDataLoaders.from_name_func(
2 mixed_path, get_image_files(mixed_path), valid_pct=0.05, seed=420,
----> 3 label_func=GetLabel, item_tfms=Resize(256))
4
5 dls.train.show_batch()
9 frames
/usr/local/lib/python3.6/dist-packages/fastai/data/core.py in setup(self, train_setup)
258 x = f(x)
259 self.types.append(type(x))
--> 260 types = L(t if is_listy(t) else [t] for t in self.types).concat().unique()
261 self.pretty_types = '
'.join([f' - {t}' for t in types])
262
TypeError: 'NoneType' object is not iterable
Thank you!
We want more ML Agents :)
can we do this multiple like 9-10 classes?
Hi Sebastian. On my live server, Upload returns same image when classify button is pressed but no actual result. Is this an error in the code or have i missed a step?
How many rtx3090s do you need to train your own AlphaZero in a , week, two weeks or a month?
@@sps014 Yes I already know that but you are not answering my question
@@sps014 can you show calculation that it is not possible or are you just guessing?
@@sps014 You are still not answering the question... If you don't know the answer why are you bothering answering and adding lot of noise to the simple question...
Let me rephrase my question...
Assuming you have a perfect model of Alpha Zero, the one David Silver built. How many gtx3090s do you need train the model in a week? How many do you need to train in two weeks? a month?
I fully understand computer science so I do mind details. Thank you
This ain't good place to ask , get some brain.
Lol people still ask questions in comment section, lot of stupidity on display.