How to use your trained model - Deep Learning basics with Python, TensorFlow and Keras p.6

In this part, we're going to cover how to actually use your model. We will us our cats vs dogs neural network that we've been perfecting.

[jaewooko]

Thanks a lot.. I was trying recent tensorflowlite.. Your tut helped to start over from basic and detail. All sample files are working great!

[julianodbz]

That´s what I was talking about, you rock man, thank you so MUCH !

[oliverpolden]

The amount of random noises you make but yet I completely understand is very entertaining.

[elisabethdoyon]

thanks a lot for all those tutorials! Youre great! I'm always looking foward to discover the mug od the day! ;)

[Cristian-bgpr]

Really appreciate each video out of all. Thank you man!

[MuhammadUsman-whzi]

Discovered you right on time when I needed this kind of learning stuff. Great work Bro..

[Rushirajloke]

RNN would be great topic to cover next. And also if you could cover LSTM that would be awesome too.

[pdanielvazquez]

Thanks for all, you were great! You helped me to do my homework

[rezahosseini]

Do some finance staff with recurrent nets! Like a simple one

[lnqrmnr]

Wow! Tensorflow seems so simple now... Thanks for sharing.

[GAment_]

For anyone getting two dogs or getting two cats, or something that is not what you were expecting--I initially had the same issue. What I did was reprocess my images with a larger image size of 100 (He did 50 in his video and 70 in his text tutorials). After retraining the model with a larger image size of 100, I was able to classify images correctly. That said, as he pointed out, this is about 80% accurate, so if misclassified--it doesn't necessarily mean your CNN is wrong--it might just meant you have to tweak your model to increase validation accuracy. Thanks again for sentdex for such informative tutorials. Really helps with comprehension.

[rahuldass]

Hi! Thanks for this updated series. Super helpful! Would you please do a tutorial(s) of doing transfer learning and/or fine tuning learning by using "off-the shelf" models to run with custom data? Models such as AlexNet, Caffe, Inception v3, ResNet etc.

[hobbitthegobbit]

You are the life saver man and a great lecturer

[ahmedbenkhalifa]

Thank you sentdex for your awesome videos, we are waiting for new projects ;)

[smartaitechnologies]

awsome explanation, thanks for clearing my doubts

[camao]

hi, thank you so much for these videos, really help me out!

[satyajitdas]

Hey, Bro. U are really doing great. Thanks for sharing yr experience and knowledge.

[homealone]

Your vids are fun and easy to follow. Would love to see RNN and LSTM for stocks, and train for specific events such as intraday momentum to predict current momentum % move and confidence %.

[shipiboconibo]

Recently discovered you, and I'm addicted! Going to start this from pt 1 this afternoon and work through. I'm also excited about your recurrent net tutorial, mentioned at the end! Maybe I'm mistaken, but would that be appropriate for equity market data (stocks, in particular)? I've been experimenting a little, but am very very very much still in the learning phase with all of this. That said, I want my programming skills to be more current, and why not see if I can make a few bucks while learning! haha. Thanks for taking the time to share so much great knowledge!

[SalehAbod]

Thanks for the great tutorial.
I would suggest replacing '"int" with "round" in the last part:
>>>>
Since round will produce dog for prediction <0.5 and cat for >=0.5