Image Captioning using Tensorflow || Developers Hutt

[@Nature_Traveller-PR]

Sir., is it possible to use yolo. For image captioning

[@DevelopersHutt]

You can take features of an image from the middle layer of the yolo model and then use the features to get the captions as we did in the video

[@Nature_Traveller-PR]

@@DevelopersHutt thank you sir., Sir can you suggest me from where we can download medical image dataset along with reports.., PEIR dataset right now I have but very few .., suggest me any other please

[@DevelopersHutt]

Which kind of dataset do you want?

[@priyavrat2044]

got error at cell no. 57. AttributeError: in user code:
:9 train_step *
dec_input = tf.expand_dims([tokenizer.word_to_index("")] * target.shape[0], 1)
AttributeError: 'Tokenizer' object has no attribute 'word_to_index'

[@fubukisophicha8831]

please upadate more

[@DevelopersHutt]

What kind of update do you want?

[@lomash_irl]

This is a helpful video lecture especially because of using attention practically... if possible do videos on fine grained detailed objects like fingerprint recognition or self supervised methods to create embeddings and stuff​@@DevelopersHutt