'Error when downloading datasets in tensorflow_dataset: GCS inacssibile
I have a problem to load data using tfds. When I try to load the data I got the following error.
ValueError: GCS bucket inaccessible
To solve the problem I upgraded TensorFlow to version 1.15.0, then I installed tensorflow-datasets using the following code:
conda install -c anaconda TensorFlow-datasets
But unfortunately, it didn't work out. I use the following code to load data.
import tensorflow.compat.v2 as tf
import tensorflow_datasets as tfds
data, info = tfds.load(name='tf_flowers',as_supervised=True, with_info =True)
Solution 1:[1]
Its working fine please see this colab notebook.
I think there is something wrong in your setup try to uninstall tensorflow
and tensorflow_datasets
and create a seprate enviroment
and then install both using pip install tesnorflow==2.0.0
and pip install tesnorflow_datasets==2.1.0
Solution 2:[2]
GCS Server refuses the connection. Change your country's IP and try again.
Sources
This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.
Source: Stack Overflow
Solution | Source |
---|---|
Solution 1 | Eshan Agarwal |
Solution 2 | Roozi |