Model.save('./model_weights/model_' + str(i) + '.h5') Error

#1

my fit_generator function is not working pls fix it as soon as possible

https://colab.research.google.com/drive/1tsYsUFFxAcgpDlNeoZlpYFJ88rmesQ6s?authuser=1#scrollTo=HYBeyBGV_92s

#2

hey @amanbh_123 ,
dont do save.
change it save weights,

#3

I am still getting error

#4

Hi prashant can you run my generator code part your end

#5

hey @amanbh_123 ,
did you used load_weights ??

yeah , will check running in it quite a bit time.

#6

still not working can we talk in call

#7

/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:1844: UserWarning: Model.fit_generator is deprecated and will be removed in a future version. Please use Model.fit, which supports generators. warnings.warn(’Model.fit_generator is deprecated and ’ --------------------------------------------------------------------------- KeyError Traceback (most recent call last) in () ----> 1 train() 6 frames in data_generator(train_description, encoding_train, word_to_idx, max_len, num_photos_per_batch) 11 n +=1 12 —> 13 photo = encoding_train[key+".jpg"] 14 15 for desc in desc_list: KeyError: ‘2513260012_03d33305cf.jpg’

#8

hey @amanbh_123 ,
its a key error.

means while creating data , you might haven’t provided keys along with extension.
but at the time of extraction , you are doing it in another way.

#9

I have done all things that tell in the video you can see my notebook. ab bs mara model aap run krva do bhut dakh liya maine prashant

#10

hey @amanbh_123 ,
have a look at this link
https://colab.research.google.com/drive/1HOCQCyGQcQCae_2iOLzzUfCr51WXa6fA?usp=sharing

for dataset , mount your google drive and add the data.

#11

Thank you prashant it’s done

#12

I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.

On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.

#13

hey, I have same issue in this!..it will be great if it can be resolve :slight_smile:

#14

did you tried to solve it using the above method