img = np.expand_dims(img, axis=0) print("image %s shape" % (i), img.shape) if i == 1: X_extra = img else: X_extra = np.append(X_extra, img, axis=0) # grayscale c_map = 'viridis' row_count = 2 plot_images(X_extra, row_count, c_map) if USE_GRAYSCALE: X_extra = rgb_to_gray(X_extra) c_map = plt.cm.gray # normalize X_extra = np.subtract(X_extra, 128.0) extra_mean = np.mean(X_extra, axis=(0,1,2)) X_extra = np.subtract(X_extra, extra_mean) row_count = 2 plot_images(X_extra, row_count, c_map) #printing out some stats and plotting print('The extra data shape is:', X_extra.shape) # labels y_extra = [14, 28, 13, 27, 17, 26, 2, 33, 5, 5]
img = np.expand_dims(img, axis=0) print("image %s shape" % (i), img.shape) if i == 1: X_EXTRA = img else: X_EXTRA = np.append(X_EXTRA, img, axis=0) # grayscale C_MAP = 'viridis' ROW_COUNT = 2 plot_images(X_EXTRA, ROW_COUNT, C_MAP) if USE_GRAYSCALE: X_EXTRA = rgb_to_gray(X_EXTRA) C_MAP = 'gray' # normalize X_EXTRA = np.subtract(X_EXTRA, 128.0) EXTRA_MEAN = np.mean(X_EXTRA, axis=(0, 1, 2)) X_EXTRA = np.subtract(X_EXTRA, EXTRA_MEAN) plot_images(X_EXTRA, ROW_COUNT, C_MAP) #printing out some stats and plotting print('The extra data shape is:', X_EXTRA.shape) # labels Y_EXTRA = [14, 28, 13, 27, 17, 26, 2, 33, 5, 5]