search

chshin10 / epinet

EPINET: A Fully-Convolutional Neural Network using Epipolar Geometry for Depth from Light Field Images
MIT License
90 stars 39 forks source link

questions about AttributeError: 'threadsafe_iter' object has no attribute 'shape' #16

Open Yuanzhisheng opened 4 years ago

Yuanzhisheng commented 4 years ago

I have a problem when I try to run the code: Traceback (most recent call last): File "EPINET_train.py", line 278, in initial_epoch=iter00, verbose=1,workers=1) File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/keras/engine/training.py", line 1426, in fit_generator initial_epoch=initial_epoch) File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/keras/engine/training_generator.py", line 115, in model_iteration shuffle=shuffle) File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/keras/engine/training_generator.py", line 377, in convert_to_generator_like num_samples = int(nest.flatten(data)[0].shape[0]) AttributeError: 'threadsafe_iter' object has no attribute 'shape'

Anyone may give me some suggestions about it? Thanks a lot !!

Cimino023 commented 4 years ago

I have the same problem, did someone fix this already?

Cimino023 commented 4 years ago

This worked for me: update tensorflow, then change in func_epinetmodel.py

from tensorflow.contrib.keras.api.keras.optimizers import RMSprop from tensorflow.python.keras.utils.data_utils import Sequence from tensorflow.contrib.keras.api.keras.models import Model, Sequential from tensorflow.contrib.keras.api.keras.layers import Input , Activation from tensorflow.contrib.keras.api.keras.layers import Conv2D, Reshape from tensorflow.contrib.keras.api.keras.layers import Dropout,BatchNormalization from tensorflow.contrib.keras.api.keras.layers import concatenate

into

from keras.optimizers import RMSprop from keras.utils.data_utils import Sequence from keras.models import Model, Sequential from keras.layers import Input , Activation from keras.layers import Conv2D, Reshape from keras.layers import Dropout,BatchNormalization from keras.layers import concatenate

Vishwanathts01 commented 3 years ago

This worked for me: update TensorFlow, then change in func_epinetmodel.py

from tensorflow.contrib.keras.api.keras.optimizers import RMSprop from tensorflow.python.keras.utils.data_utils import Sequence from tensorflow.contrib.keras.api.keras.models import Model, Sequential from tensorflow.contrib.keras.api.keras.layers import Input , Activation from tensorflow.contrib.keras.api.keras.layers import Conv2D, Reshape from tensorflow.contrib.keras.api.keras.layers import Dropout,BatchNormalization from tensorflow.contrib.keras.api.keras.layers import concatenate

into

from keras.optimizers import RMSprop from keras.utils.data_utils import Sequence from keras.models import Model, Sequential from keras.layers import Input , Activation from keras.layers import Conv2D, Reshape from keras.layers import Dropout,BatchNormalization from keras.layers import concatenate

Yes, I've tried changing it. But, I am still facing the same problem. Could you please help me in fixing this problem?

chaowentao commented 2 years ago

I fixed the problem. downgrade the tensorflow-gpu=1.10. You can try it.

conda install tensorflow-gpu=1.10
Liaowan commented 2 years ago

I installed tensorflow-gpu=1.10 to run this code,but apendented a error showing that 'version_info' object has no attribute 'version' when i install matplotlib,another problem is my memory is not enough. can you help me solve both question,thinks very much.