Share your work here ✅


(Rick N) #781

Thanks Jeremy, that makes sense, so I went back and read more text samples, since I recalled seeing some where the source was mentioned. There’s no field for the article source, and the model only sees the article text, so I looked for the news source (or something related) showing up in the text. Turns out there aren’t many of those - maybe 5%. Most are “clean” in not having any markers that I could see.

But I looked deeper into the dataset heritage and it was (in my opinion) a bit flawed, partly because it was labelled based on the article source (website) and not on the actual content. McIntire used a Kaggle fake news dataset (https://www.kaggle.com/mrisdal/fake-news) from 2016 for his ‘fake’ records and AllSides (https://www.allsides.com/unbiased-balanced-news) to scrape articles for ‘real’ records. The Kaggle ds was in turn based on a Chrome add-in, BS Detector (https://bsdetector.tech/) which in turn was based on classification of online sources by OpenSources (http://www.opensources.co/) which actually has 12 classes. The Kaggle ds used the most ‘fake’ websites to collect articles with 8 classes, and McIntire simplified the labelling into just FAKE, which I think is a bit misleading (e.g., that includes the ones labeled ‘satire’).

I think it’s misleading to judge that an article is fake strictly because of its source, and reading some ds samples bears that out: there are quite a few records where the article content seemed fine to me (and I’m pretty skeptical in general) but it was classified as fake.

But all that said, it still looks to me like the model works amazingly well at classifying McIntire’s dataset. Because I consider the labeling to be biased and too simplistic, I don’t think this should be used for a real-world application, but it was a good learning experience, and I’m planning to move on to trying the full Kaggle ds. But I would appreciate any other feedback or suggestions!


NLP for fake news
(Jithin James) #782

Hi,
I have started writing a small blog after reading couple of deep learning related papers.(More on its way :grinning:)

https://jithinjk.github.io/blog

I have only tried to summarize important points from relevant papers. Just like a bookmark, if you want to refer a certain paper in the future, but instead of reading it through its entirety, you could come here and go over the summarized version.

Please do let me know what you think and also mention other relevant papers that you would like to see here.


(Karl) #783

Update on this. I made some modifications to the model and deployed it to AWS. The main thing I changed about the model was the dataset used. It turns out when you train an image generation model on images of pets, it starts to make everything look a little furry. Instead I used a subset of the Open Images dataset.

I got the model up and running on AWS. @pankymathur’s code was helpful in figuring out returning an image. Although I still manage the process by saving the model output as an image and serving it with html, which I am not sure is optimal. I’m planning on doing a write up of the whole process at some point.

Anyway you can check out the web app here:

http://www.deepenhance.im/


#785

I made a couple of text generators following the model of lesson 3 IMDB – one is trained on the complete works of Jane Austen and the other on Trump’s tweets from 2009-2018. :stuck_out_tongue: They are both online, the first at https://deepjane.now.sh/ and the second at https://deepdonald.appspot.com/. The second is powered by Google App Engine. In case it helps anyone in the future, I had a lot of trouble getting the app working on GAE (I ran into errors even with the starter code) but ended up able to deploy successfully after building the Docker image locally (and trying over and over a bunch of times).

They are also on twitter! Jane is @AutoAusten and Donald is @RNN_DonaldTrump. They tweet periodically by themselves, but you can also @ message them a few words and they’ll (hopefully) respond with a tweet beginning with your message. If you try them and don’t get a response, please let me know! I’ve been working out the bugs but fear there are still some lurking around.

Currently working on a Medium post about the experience. :slight_smile:


(Pierre Guillou) #786

Create an infinity of images to train your Neural Networks :slight_smile:
My article on “Data Augmentation by fastai v1”. All comments welcome! Thanks.


(Pankaj Mathur) #787

Good one Karl, just tried uploading few thumbnails and output resolution images were great, IMHO App and website look great :slight_smile: . you can surely enhance and optimize it in future, depending upon traffic and heavy production loads, so keep up the good work


(Aayush Agrawal) #788

I trained a facial attribute multi-label classification model which finds 40 attributes using CelebA dataset. I have also used OpenCV to combine it with the webcam for live detection. The code is on Github. Check the output -


(Wayde Gilliam) #789

I did an object detection problem that finds the center of a phone in an image using Fastai v1 and the Datablock api. The link to it on my github is here.

One of the challenges I had was making a custom collate function for single image points, as Fastai only has one function for bboxes in the vision library. Having it work though made a huge difference in my accuracy as I only had ~115 images to work with.


(Less ) #790

I made a basic snake classifier as a small project. The first and only goal of the initial part was to prove if it could readily distinguish between a very common confusion of copperhead (venomous) and corn snake (harmless). Result was it could do so rather easily and got to 100% quickly with all three models (resnet, vgg, etc). I wrote an article on it to help promote FastAI here:

Now I’m working on adding a number of other snakes (garter, rattlesnake, etc) to try and expand it into a fuller snake classifier where people could just easily upload a photo and get a classification for most snakes in the US and ideally other countries over time.


(Jeremy Howard (Admin)) #791

Did you check the image regression (keypoints) lesson notebook? IIRC I had something there that was doing single image points and worked OK…


(Wayde Gilliam) #792

I was using the lesson3-head-pose notebook on the BIWI data set as a reference; I don’t think I’ve seen the notebook you’re referencing. Is from the old Part 2 course? I didn’t see anything in the docs either about a collate function for Image Points so I just assumed it hadn’t been done before in any of the lessons.


(Robin) #793

I worked through lesson one using my own dataset of images captured at my birdfeeder. I previously created a binary classifier using a commercial product Classificationbox and achieved 92% accuracy, but by following the lesson plan and using resnet34 I am getting almost 98% accuracy, so a great result :slight_smile: Notebook on kyso -> https://kyso.io/robmarkcole/birds-vs-not-birds-image-classification-using-fastai


(Dhyey Pankaj Mehta) #794

Hey, to create a new image classifier after lesson 1, do I need to create a completely new notebook? Also, I am using colab, so can someone tell me how to upload the new dataset. Basically, I would really appreciate a complete step by step guide on how to create a classifier from scratch.


(Lucas) #795

My weekend’s excitement on a kaggle dataset I can no longer find: I used the Lesson 1 code to categorize pieces of art to the following categories: painting, engraving, iconography, sculpture, and drawings.

Using the ImageDataBunch.from_folder took forever because I didn’t know how to use the path parameter, and their were corrupt images.

PIL has a nifty verify() function that helped.


(Hafidz Zulkifli) #796

Finally found some time to write something about entity embeddings. The course really sparked my interest in diving deeper into the subject. Hope the post could be off some use to everyone.

“Understanding Entity Embeddings and It’s Application” by Hafidz Zulkifli https://link.medium.com/sIBqXgqAPT


(Sanyam Bhutani) #797

Hi all,

Jeremy had mentioned about FP16 training during one of the lectures. For this week, I chose to dig deeper into that.
Thanks to @Ekami I was able to do a 2080Ti Vs 1080Ti comparision for training times.

I think this deserves a mention that even though FP 16 is supported by many libraries now, none make it as easy as wrapping your code with a .to_fp16() like fastai does.

Here is a gentle introduction to Mixed Precision Training & a few benchmark comparision:

Regards,
Sanyam


#798

Having similar issue. I’m trying to use exponential mae similarly to what Jeremy did in Rossman, but also getting score around 0.33. Before using fastai v1 I made the same notebook but for fastai v0.7 and got the error 10x smaller. The way you create custom metrics has changed in v1, it’s not as simple as it used to be and it’s quite confusing for me.


(Konstantin Dorichev) #799

I’ve built a binary image classifier, using resnet34 and resnet50 on a dataset of blood cells images to distinguish whether a cell is infected with malaria or not. Here is

Thanks for any constructive critique and suggestions.


(Yogita) #800

I tried another fine-grain classification problem after watching lesson 1.
Dataset - 10 Monkey species
Here’s the blog post explaining my approch.

Feedback and Suggestions are appreciated.


(Lesly) #801

I created a Plants and Fruits Image classifier. Here is an article about the same: