Designing a neural network | Text Classification Tutorial Pt. 2 (Coding TensorFlow)

No video

Designing a neural network | Text Classification Tutorial Pt. 2 (Coding TensorFlow)

Рет қаралды 52,672

5 жыл бұрын

In Part 2, we continue our tutorial on Text Classification, which assigns categories to text documents. In the last episode, we pre-processed the data so it would be ready to train a neural network. But, how do we design the neural network so it can learn from the data we prepared? Find out in this episode of Coding TensorFlow with @lmoroney. Stay tuned for our next video, which will feature how to do regression in TensorFlow.
Text classification with movie reviews → bit.ly/2CNVMbi
Subscribe to TensorFlow → bit.ly/TensorFlow1
Watch more Coding TensorFlow, including Part 1 → bit.ly/2zoZfvt

Пікірлер: 25

@DavidMartin-gr7ji 5 жыл бұрын

Laurence, these videos are great! Thank you for making them! Some feedback: the text titles of the videos aren't easy to read and that makes it difficult to know the order to watch related videos. Consider changing the sequence of the items in the title from: "Title, Subject, Part" to "Subject, Part, Title". For example, this video would be:" Text Classification, Pt.2 | Designing a neural network".

@gusthema 5 жыл бұрын

This was very good! The embedding example was great!

@laurencemoroney655 5 жыл бұрын

THanks! :)

@oumski7529 Жыл бұрын

تحياتي الخالصة من الجزائر thank you very mutch

@TheDavidlloydjones 5 жыл бұрын

Thanks for giving Part 1 a title beginning with P and Part 2 a title beginning with D. This means they will alphabetise themselves in a list about as far apart as possible, and maximise the amount of searching the human has to do "manually," by eye-ball. Thank goodness the machines are coming!

@laurencemoroney655 5 жыл бұрын

Heheh. Nice point. I should make playlists with them ordered to make it easier to figure out which comes after which. I'll speak with the social folks. :)

@darrengovoni6184 5 жыл бұрын

Had a question about this code. In cell 22 you separate out a subset of the original training data and call this validation set. And you fit only this data. Yet in cell 23 you evaluate the test_data which is already returned separately. So why the need for this extra validation set? If you train on the entire train_data and validate on the test_data, are not the two datasets already distinct?

@PeterMancini 5 жыл бұрын

Why 16 dimensions? Why not 3 or 160?

@segev1824 4 жыл бұрын

Hi! Have you found out that answer to this? I'd greatly appreciate any insight into this!

@pandarzzz 5 жыл бұрын

Thank you for sharing this informative video! 😺🖐

@laurencemoroney655 5 жыл бұрын

My pleasure! :)

@iwantandjaya3028 4 жыл бұрын

Hi, I have a question, Is lemmatization and stemming applied to the dataset? If not, is there built-in tf/keras feature that can pre-process the data? Thanks.

@AbhishekKumar-mq1tt 5 жыл бұрын

Thank u for this awesome video and series

@laurencemoroney655 5 жыл бұрын

Thanks, Abishek! :)

@jdbrrocks 4 жыл бұрын

How can we use model.predict() in this case??

@mohansaisingamsetti7456 5 жыл бұрын

Nice

@intelligenttrends8935 5 жыл бұрын

AWESOME

@laurencemoroney655 5 жыл бұрын

Thanks!

@rosaria3932 3 жыл бұрын

Thank you so much for the video! The link to the workbook is not working, could you please upload it again?

@randomaccessvemuri5788 3 жыл бұрын

www.tensorflow.org/tutorials/keras/text_classification

@ProfessorElectronic 5 жыл бұрын

Hi, how do I export the trained model from Codelab to my computer?

@suraj-ram7488 5 жыл бұрын

I am not fully sure, but you can use the saveModel feature of TF to create files that contain your trained model. You can then download these files and run them on your computer. BTW this same youtube channel has more information regarding this feature.

@EvenYan-home 5 жыл бұрын

oh, no. The 14th video can't be show, could yo tell me why?

@farhadshadmand5785 5 жыл бұрын

I tried to do that this programming with my data from tweets, but I get error below, Someone can help me?? nvalidArgumentError: indices[0,39] = -1 is not in [0, 2000) [[Node: embedding_23/embedding_lookup = ResourceGather[Tindices=DT_INT32, _class=["loc:@training_12/Adam/gradients/embedding_23/embedding_lookup_grad/Reshape"], dtype=DT_FLOAT, validate_indices=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](embedding_23/embeddings, embedding_23/Cast)]]