forked from githubharald/SimpleHTR
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
4119ac8
commit 3968a52
Showing
6 changed files
with
138 additions
and
2 deletions.
There are no files selected for viewing
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file not shown.
Binary file not shown.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
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
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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,136 @@ | ||
from __future__ import division | ||
from __future__ import print_function | ||
|
||
import sys | ||
import math | ||
import copy | ||
import numpy as np | ||
import cv2 | ||
import matplotlib.pyplot as plt | ||
from DataLoader import Batch | ||
from Model import Model, DecoderType | ||
from SamplePreprocessor import preprocess | ||
|
||
|
||
class FilePaths: | ||
"filenames and paths to data" | ||
fnCharList = '../model/charList.txt' | ||
fnAnalyze = '../data/analyze.png' | ||
fnPixelRelevance = '../data/pixelRelevance.npy' | ||
fnTranslationInvariance = '../data/translationInvariance.npy' | ||
|
||
|
||
def odds(val): | ||
return val / (1 - val) | ||
|
||
|
||
def weightOfEvidence(origProb, margProb): | ||
return math.log2(odds(origProb)) - math.log2(odds(margProb)) | ||
|
||
|
||
def analyzePixelRelevance(): | ||
"simplified implementation of paper: Zintgraf et al - Visualizing Deep Neural Network Decisions: Prediction Difference Analysis" | ||
|
||
# setup model | ||
model = Model(open(FilePaths.fnCharList).read(), DecoderType.BestPath, mustRestore=True) | ||
|
||
# read image and specify ground-truth text | ||
img = cv2.imread(FilePaths.fnAnalyze, cv2.IMREAD_GRAYSCALE) | ||
(w, h) = img.shape | ||
assert Model.imgSize[1] == w | ||
gt = 'are' | ||
|
||
# compute probability of gt text in original image | ||
batch = Batch([gt], [preprocess(img, Model.imgSize)]) | ||
(_, probs) = model.inferBatch(batch, calcProbability=True, probabilityOfGT=True) | ||
origProb = probs[0] | ||
|
||
# iterate over all pixels in image | ||
pixelRelevance = np.zeros(img.shape, np.float32) | ||
for x in range(w): | ||
for y in range(h): | ||
|
||
# try a subset of possible grayvalues of pixel (x,y) | ||
imgsMarginalized = [] | ||
for g in [0, 63, 127, 191, 255]: | ||
imgChanged = copy.deepcopy(img) | ||
imgChanged[x, y] = g | ||
imgsMarginalized.append(preprocess(imgChanged, Model.imgSize)) | ||
|
||
# put them all into one batch | ||
batch = Batch([gt]*len(imgsMarginalized), imgsMarginalized) | ||
|
||
# compute probabilities | ||
(_, probs) = model.inferBatch(batch, calcProbability=True, probabilityOfGT=True) | ||
|
||
# marginalize over pixel value (assume uniform distribution) | ||
margProb = sum(probs)/len(probs) | ||
|
||
pixelRelevance[x, y] = weightOfEvidence(origProb, margProb) | ||
|
||
print(x, y, pixelRelevance[x, y], origProb, margProb) | ||
|
||
np.save(FilePaths.fnPixelRelevance, pixelRelevance) | ||
|
||
|
||
|
||
def analyzeTranslationInvariance(): | ||
# setup model | ||
model = Model(open(FilePaths.fnCharList).read(), DecoderType.BestPath, mustRestore=True) | ||
|
||
# read image and specify ground-truth text | ||
img = cv2.imread(FilePaths.fnAnalyze, cv2.IMREAD_GRAYSCALE) | ||
(w, h) = img.shape | ||
assert Model.imgSize[1] == w | ||
gt = 'are' | ||
|
||
imgList = [] | ||
for dy in range(Model.imgSize[0]-h+1): | ||
targetImg = np.ones((Model.imgSize[1], Model.imgSize[0])) * 255 | ||
targetImg[:,dy:h+dy] = img | ||
imgList.append(preprocess(targetImg, Model.imgSize)) | ||
|
||
# put images and gt texts into batch | ||
batch = Batch([gt]*len(imgList), imgList) | ||
|
||
# compute probabilities | ||
(_, probs) = model.inferBatch(batch, calcProbability=True, probabilityOfGT=True) | ||
np.save(FilePaths.fnTranslationInvariance, probs) | ||
|
||
|
||
def showResults(): | ||
# 1. pixel relevance | ||
pixelRelevance = np.load(FilePaths.fnPixelRelevance) | ||
plt.figure('Pixel relevance') | ||
|
||
plt.imshow(pixelRelevance, cmap=plt.cm.jet, vmin=-0.5, vmax=0.5) | ||
plt.colorbar() | ||
|
||
img = cv2.imread(FilePaths.fnAnalyze, cv2.IMREAD_GRAYSCALE) | ||
plt.imshow(img, cmap=plt.cm.gray, alpha=.4) | ||
|
||
|
||
# 2. translation invariance | ||
probs = np.load(FilePaths.fnTranslationInvariance) | ||
plt.figure('Translation invariance') | ||
|
||
plt.plot(probs, 'o-') | ||
plt.xlabel('horizontal translation') | ||
plt.ylabel('text probability') | ||
|
||
# show both plots | ||
plt.show() | ||
|
||
|
||
if __name__ == '__main__': | ||
if len(sys.argv)>1: | ||
if sys.argv[1]=='--relevance': | ||
print('Analyze pixel relevance') | ||
analyzePixelRelevance() | ||
elif sys.argv[1]=='--invariance': | ||
print('Analyze translation invariance') | ||
analyzeTranslationInvariance() | ||
else: | ||
print('Show results') | ||
showResults() | ||
|