so i'm trying to import mnist to use it in a simple CNN example, but it's not being recognized, here is the code that i'm using:
from keras.models import Model
from keras.layers import Input, merge
from keras.layers.core import Flatten, Dense, Dropout, Activation
from keras.layers.convolutional import Convolution2D, MaxPooling2D, AveragePooling2D
from keras.layers.normalization import BatchNormalization
import keras.utils.np_utils as kutils
from keras.utils.vis_utils import plot_model, model_to_dot
import MNIST as dc
import numpy as np
batch_size = 128 # 128
nb_epoch = 100 # 12
img_rows, img_cols = 28, 28
trainData = dc.convertPandasDataFrameToNumpyArray(dc.loadTrainData(describe=False))
trainX = trainData[:, 1:].reshape(trainData.shape[0], 1, img_rows, img_cols)
trainX = trainX.astype(float)
trainX /= 255.0
the error that i get:
ModuleNotFoundError: No module named 'MNIST'
i've already installed the MNIST using pip but didn't help at all
I've never seen the MNIST being imported this way. Why don't you just use this since you're already using Keras?
from keras.datasets import mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()