Last active
July 27, 2016 20:50
-
-
Save vgenty/54b39c05e2a533f95cb495f668072335 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from ROOT import larcv | |
from matplotlib import colors | |
import numpy as np | |
import matplotlib | |
import matplotlib.pyplot as plt | |
matplotlib.rcParams['font.size'] = 20 | |
matplotlib.rcParams['font.family'] = 'serif' | |
larcv.load_pyutil | |
cmap = colors.ListedColormap(['blue','red','green','yellow','pink','orange']) | |
bounds=[0,1,2,3,4,5,6] | |
norm = colors.BoundaryNorm(bounds, cmap.N) | |
iom = larcv.IOManager() | |
iom.add_in_file("/data/vgentyvalid_hires_100.root") | |
iom.add_in_file("/data/vgenty/UBFCN/retraining/alex/fcn16/weights/ana/alex_fcn16_weights_21696_writeana.root.root") | |
iom.initialize() | |
iom.read_entry(397) | |
imgs=iom.get_data(larcv.kProductImage2D,"tpc_hires_crop").Image2DArray() | |
gts=iom.get_data(larcv.kProductImage2D,"segment_hires_crop").Image2DArray() | |
segs=iom.get_data(larcv.kProductImage2D,"fcn").Image2DArray() | |
# create 6 channel score tensor | |
ss = np.zeros([6,576,576]) | |
for s in xrange(6): | |
seg = larcv.as_ndarray(segs[s]) | |
ss[s,:,:] = seg | |
# argmax to get the scoremap | |
scoremap=ss.argmax(axis=0) | |
#Get plane 2 image and ground truth labels | |
p2img = larcv.as_ndarray(imgs[2]) | |
p2seg = larcv.as_ndarray(gts[2]) | |
# Threshold low pixel values | |
picut = p2img < 10.0 | |
# Make them background in scoremap | |
scoremap[picut] = 0.0 | |
# Order classes 1 to 5 (0 is background) | |
for ix,c in enumerate([3.0,4.0,6.0,8.0,9.0]): | |
p2seg[p2seg == c] = ix+1 | |
fig,_=plt.subplots(figsize=(30,20)) | |
#Ground Truth | |
ax = plt.subplot(2,1,1) | |
img = plt.imshow(p2seg,cmap=cmap,norm=norm,interpolation='none') | |
ax.set_title("Ground Truth",fontweight='bold') | |
cbar = plt.colorbar(img, cmap=cmap, norm=norm, boundaries=bounds, ticks=[0,1,2,3,4,5,6],fraction=0.046, pad=0.04) | |
plt.axis("off") | |
#Segmentation | |
ax = plt.subplot(2,1,2) | |
img = plt.imshow(scoremap,cmap=cmap,norm=norm,interpolation='none') | |
ax.set_title("Inference",fontweight='bold') | |
cbar = plt.colorbar(img, cmap=cmap, norm=norm, boundaries=bounds, ticks=[0,1,2,3,4,5,6],fraction=0.046, pad=0.04) | |
plt.axis("off") | |
plt.show() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment