Class imagej_tiff to read multilayer tiff files and parse tags

• layers are stacked along depth (think RGB)
• parse imagej generated tags (50838 and 50839)

• Presentation for CVPR2018: Elphel_TP-CNN_slides.pdf
• TIFF Image stacks for Machine Learning

• models/all/state_street/1527256815_150165/v01/ml/ or
• go to 3d+biquad, open individual models and hit the light green button to ‘Download source files for ml’

• Python 3.5.2 (not strict)
• Pillow 5.1.0+ (strict)
• Numpy 1.14.2 (not strict)
• Matplotlib 2.2.2 (not strict)

~$ python3 infer_qcds_01.py qcstereo_conf.xml data_sets

where:

• qcstereo_conf.xml - config file
• data_sets - root dir for trained models/data/checkpoints

#!/usr/bin/env python3
from PIL import Image
import xml.etree.ElementTree as ET
import numpy as np
import matplotlib.pyplot as plt
import imagej_tiff as ijt

tiff = ijt.imagej_tiff('test.tiff')
print(tiff.nimages)
print(tiff.labels)
print(tiff.infos)
tiff.show_images(['X-corr','Y-corr',0,2])
plt.show()