Menu
I run from keras.datasets import mnist and mnist.load_data() to downloaded the MNIST data. But I want to know where they are stored. I am using Windows 10 and Anaconda, and I looked into here:-
C:\Users\My_User_Name\Anaconda3\Lib\site-packages\keras\datasets
I can find the text file mnist.py, but I can't find the downloaded data. Where should I find them? Many thanks!
286
The format of the test set is identical to that of the training set. The primary repository for the MNIST files is currently located at yann.lecun.com/exdb/mnist. The training pixel data is stored in file train-images-idx3-ubyte. gz and the training label data is stored in file train-labels-idx1-ubyte.
To load images from a local directory, use image_dataset_from_directory() method to convert the directory to a valid dataset to be used by a deep learning model. image_size and batch_size parameters specify the size of an image and the number of dataset batches respectively.
keras. datasets module provide a few toy datasets (already-vectorized, in Numpy format) that can be used for debugging a model or creating simple code examples. If you are looking for larger & more useful ready-to-use datasets, take a look at TensorFlow Datasets.
Looking at the source for that function, we see it uses get_file(), which says:
By default the file at the url
originis downloaded to the cache_dir~/.keras, placed in the cache_subdirdatasets, and given the filenamefname. The final location of a fileexample.txtwould therefore be~/.keras/datasets/example.txt.
So look in C:\Users\My_User_Name\.keras\datasets.
109
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With
