search

Ning-Ding / Implementation-CVPR2015-CNN-for-ReID

Implementation for CVPR 2015 Paper: "An Improved Deep Learning Architecture for Person Re-Identification".
MIT License
147 stars 71 forks source link

fit_generator throws error on validation data being float data type #37

Open adityak6798 opened 6 years ago

adityak6798 commented 6 years ago

I'm trying to run CUHK03 Person Re-ID script. Error text reads as follows:

TypeError Traceback (most recent call last) in () ----> 1 main("E:\DL\cuhk-03.h5")

in main(dataset_path) 17 model = generate_model() 18 model = compile_model(model) ---> 19 train(model, dataset_path) 20 21 def train(model,

in train(model, h5_path, weights_name, train_num, one_epoch, epoch_num, flag_random, random_pattern, flag_train, flag_val, which_val_data, nb_val_samples) 39 rand_x = np.random.rand() 40 flag_train = random_pattern(rand_x) ---> 41 model.fit_generator(Data_Generator.flow(f,flag = flag_train),one_epoch,epoch_num,validation_data=Data_Generator.flow(f,train_or_validation=which_val_data,flag=flag_val),nb_val_samples=nb_val_samples) 42 Rank1s.append(round(cmc(model)[0],2)) 43 print (Rank1s)

~\Anaconda3\lib\site-packages\keras\legacy\interfaces.py in wrapper(*args, *kwargs) 89 warnings.warn('Update your ' + object_name + 90 ' call to the Keras 2 API: ' + signature, stacklevel=2) ---> 91 return func(args, **kwargs) 92 wrapper._original_function = func 93 return wrapper

~\Anaconda3\lib\site-packages\keras\engine\training.py in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch) 2023 epoch = initial_epoch 2024 -> 2025 do_validation = bool(validation_data) 2026 self._make_train_function() 2027 if do_validation:

TypeError: 'float' object cannot be interpreted as an integer

I am using Jupyter Notebook in Anaconda on Windows 10(x86). Keras version 2.1.3 Python version 3.6.3 Tensorflow backend (1.4.0)

bmiftah commented 6 years ago

I am not gonna give targeted solution but I guess keras version may be giving you some of the problems .. my bugs were different from your but i was having keras 2.1 > ... I downgrade it to 2.0.0 and issues with keras version were solved... Also , I see your Tensorflow version is also different version to the one on which the model was developed ... you may consider checking the development environment the contributor tested the code on as given here https://github.com/Ning-Ding/Implementation-CVPR2015-CNN-for-ReID

abhigoku10 commented 6 years ago

@adityak6798 you need to use the keras version 2.0.0