python - Images from NIST and iamDB into CNN: ValueError: total size of new array must be unchanged -


i working on handwritten text recognition application , train model on images both nist19 (handwritten character images+labels) , iamdb (handwritten word images+labels). model trains fine , works iamdb images, throws valueerror when include nist images. of images png files resized 128 x 128 b/w , turned numpy array (np.float32). full error is: 'valueerror: total size of new array must unchanged' on line: x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)

why iamdb arrays have no trouble reshape(), addition of nist arrays produces error? address problem appreciated.


Comments

Popular posts from this blog

javascript - Create a stacked percentage column -

Optimising Firebase database by automatically overwriting data -

javascript - Angular UI-Grid customTemplate directive causing rows to load slowly/? -