def plot_images(images, img_shape,cls_true, cls_pred=None):
assert len(images) == len(cls_true) == 42
# Create figure with 7x6 sub-plots.
fig, axes = plt.subplots(7, 6)
fig.subplots_adjust(hspace=0.3, wspace=0.3)
for i, ax in enumerate(axes.flat):
# Plot image.
# import cv2
# cv2.imshow('image',images[0][0])
# cv2.waitKey()
ax.imshow(images[i][0], cmap='binary')
# Show true and predicted classes.
if cls_pred is None:
xlabel = "True: {0}".format(cls_true[i])
else:
#to find corrrect class index
cls = np.where(cls_true[i] == 1)[0][0]
xlabel = "True: {0}, Pred: {1}".format(getAllCharacterFromIndex(cls), getAllCharacterFromIndex(cls_pred[i]))
# Show the classes as the label on the x-axis.
ax.set_xlabel(xlabel)
# Remove ticks from the plot.
ax.set_xticks([])
ax.set_yticks([])
# Ensure the plot is shown correctly with multiple plots
# in a single Notebook cell.
plt.show()
def get_class_name(index):
return int(getAllCharacterFromIndex(index))