TensorFlow Tutorial 11 - Text Classification - NLP Tutorial

Поделиться
HTML-код
  • Опубликовано: 22 дек 2024

Комментарии • 35

  • @kccchiu
    @kccchiu 3 года назад +2

    I feel much more confident going into the TF cert exam after finishing your playlist. Danke Patrick!

  • @bosszz1282
    @bosszz1282 2 года назад +1

    omg,your tensorflow series is very good for bigginers to understand how to begin train their models,i hope you can make some develop tutorials.Thank you so much

  • @Waterlmelon
    @Waterlmelon 3 года назад +1

    Many thanks! very clear explanation i like it

  • @binyaminramati3010
    @binyaminramati3010 4 года назад +4

    Thanks for your awesome videos, some GAN's videos would be helpful.

    • @patloeber
      @patloeber  4 года назад +1

      Will try to do this in the future

  • @manuelcerezo5869
    @manuelcerezo5869 2 года назад

    thanks for this video, that i can learn NLP and english

  • @juancamilodiazmesa1472
    @juancamilodiazmesa1472 2 года назад

    Hii thanks for the video. I just have one questions. What is your recommendation to fix the overfitting in the model?

  • @brauliovasquez8421
    @brauliovasquez8421 Год назад

    how can I export your model to use in another application?

  • @hardianhidayat3195
    @hardianhidayat3195 3 года назад

    How can you get the prediction and validation to those numbers? what is the formula to get those numbers?

  • @risnandianggara
    @risnandianggara 2 года назад

    how about cactegories on a document or tittle of a paragraph
    what method we use
    edit:
    what i saw its only 2 categories this whole time how about 3 or more categories

  • @pandaski6690
    @pandaski6690 2 года назад

    I recognize different lengths in train_sentences and train_sequences (at 12:xx). The length of sentence 3 and sentence 5 do not match with their sequence length. Can you please explain this?

  • @MOHAMMADAUSAF
    @MOHAMMADAUSAF 2 года назад

    at 7:09 this would no longer work, one of the functions maybe
    from collections import Counter
    def counter_word(text_col):
    count = Counter()
    df['text'].str.lower().str.split().apply(count.update)
    return count
    counter = counter_word(df.text)

  • @ayencoscolfield3312
    @ayencoscolfield3312 4 года назад +1

    Please can you do a video on tweet sentiment analysis to determine suicidal classification using NLP

    • @patloeber
      @patloeber  4 года назад +1

      I'll add it to my list :)

  • @aadhavanalakan97
    @aadhavanalakan97 2 года назад

    Hey man, I am getting this error (NotImplementedError: Cannot convert a symbolic Tensor (lstm_11/strided_slice:0) to a numpy array. This error may indicate that you're trying to pass a Tensor to a NumPy call, which is not supported). Can anyone help me out or do you mind sharing which versions of tensor and numpy you used while coding this exercise?

  • @HazemAzim
    @HazemAzim 4 года назад

    question : why did we use Padding to fix the sequence length ? LSTM/RNNs can deal with variable sequence lengths .. am I missing something ?

    • @HazemAzim
      @HazemAzim 4 года назад

      aka : unless the reason is in the embeddings layer input expecting a matrix with batch size and max input length ?!! ====>>> model.add(layers.Embedding(num_unique_words, 32, input_length=max_length))
      # The layer will take as input an integer matrix of size (batch, input_length),
      # and the largest integer (i.e. word index) in the input should be no larger than num_words (vocabulary size).

    • @patloeber
      @patloeber  4 года назад

      We should use masking or padding for RNN. In this case I used padding explicitely. And yes if input_length is used then it must be of same size

  • @teetanrobotics5363
    @teetanrobotics5363 4 года назад

    just amazing

  • @kaiye4954
    @kaiye4954 4 года назад

    Another great video. Just a question. In the real world, when processing natural language, is that always converting training words into numbers first before applying to model? Like in this example, you convert "flood bago myanmar arrived bago" into [99, 3742, 612, 1451, 3742]. Basically, we can't use real words in the model?

    • @patloeber
      @patloeber  4 года назад

      No, you always somehow have to map the words to numbers so that the model can understand it. There are different ways of doing this...

  • @nikolayandcards
    @nikolayandcards 4 года назад

    Notification Gang 🔥🔥🔥

  • @venkatesanr9455
    @venkatesanr9455 4 года назад +4

    Thanks for your valuable content.Kindly do some nlp tasks like NER, BERT implementation that will be highly useful.

    • @patloeber
      @patloeber  4 года назад +1

      Yes very interesting topics

  • @samanesharify
    @samanesharify 3 года назад +1

    Hi thank you for your nice work, can I ask for the code?

    • @samanesharify
      @samanesharify 3 года назад +1

      Thank you I had found it on the link to github

    • @patloeber
      @patloeber  3 года назад +1

      yep almost all the code to my videos is on github

  • @gowthamkrishna6283
    @gowthamkrishna6283 3 года назад

    Why didn't we use test sentences in the tutorial to check the prediction?

    • @patloeber
      @patloeber  3 года назад +1

      my mistake. I should have used the test data in the end...

    • @gowthamkrishna6283
      @gowthamkrishna6283 3 года назад

      @@patloeber that's okay. Just wanted to check if my understanding was correct. And thanks for your videos. They are amazing brother

  • @manojkumarcr9417
    @manojkumarcr9417 3 года назад +1

    When you say helper functions, next time do explain it also how it works please!!

  • @MachineLearningAcademySriLanka

    Text classification using tensorflow
    ruclips.net/p/PL-N0_7SF7nTqOQdTzLRIRvyGJW-msR3Q4&feature=shared