'm_label_one_hot', 'image', 'italic', 'aspect_ratio', 'upper_case'
]
ds = ocr_utils.read_data(input_filters_dict=input_filters_dict,
output_feature_list=output_feature_list,
test_size=.1,
engine_type='tensorflow',
dtype=dtype)
nn = nnetwork.network(ds.train)
nn.fit(ds.train, nEpochs=5000)
nn.test(ds.test)
else:
# loop through all the fonts and train individually
# pick up the entire list of fonts and font variants. Train each one.
df1 = ocr_utils.get_list(input_filters_dict={'font': ()})
import pprint as pprint
pp = pprint.PrettyPrinter(indent=4)
pp.pprint(df1)
output_feature_list = [
'm_label_one_hot', 'image', 'italic', 'aspect_ratio', 'upper_case',
'font_one_hot'
]
# Change nEpochs to 5000 for better results
for l in df1:
#input_filters_dict= {'font': (l[0],)}
input_filters_dict = {
'm_label':
'''
dumps out some statistics for the fonts.zip database and
makes plots, saved in files, of characters for each fontVariant found in
the database
Created on Jul 25, 2016
@author: richard
'''
import ocr_utils
import numpy as np
df1 = ocr_utils.get_list(input_filters_dict = {'font':()})
unique_fonts=[]
unique_fontVariants=[]
unique_m_labels=[]
unique_strengths=[]
unique_italics=[]
unique_orientations=[]
#############################################################################
# read and show the character images for each font variant
# output only the character label and the image
for font in df1:
df2 = ocr_utils.get_list(input_filters_dict = {'font':font,'fontVariant':(), 'm_label':(),'strength':(),'italic':(),'orientation':()})
unique_fonts = np.unique( np.append(unique_fonts, df2['font']))
u1= np.unique(df2['fontVariant'])
unique_fontVariants = np.unique(np.append(unique_fontVariants, u1))
u2 = np.unique(df2['m_label'])
unique_m_labels = np.unique(np.append(unique_m_labels,u2))
input_filters_dict = {'m_label': list(range(48,58))+list(range(65,91))+list(range(97,123)),'fontVariant':'scanned'}
#input_filters_dict = {}
output_feature_list = ['m_label_one_hot','image','italic','aspect_ratio','upper_case']
ds = ocr_utils.read_data(input_filters_dict = input_filters_dict,
output_feature_list=output_feature_list,
test_size = .1,
engine_type='tensorflow',dtype=dtype)
nn = nnetwork.network( ds.train)
nn.fit( ds.train, nEpochs=5000)
nn.test(ds.test)
else:
# loop through all the fonts and train individually
# pick up the entire list of fonts and font variants. Train each one.
df1 = ocr_utils.get_list(input_filters_dict={'font': ()})
import pprint as pprint
pp = pprint.PrettyPrinter(indent=4)
pp.pprint(df1)
output_feature_list = ['m_label_one_hot','image','italic','aspect_ratio','upper_case','font_one_hot']
# Change nEpochs to 5000 for better results
for l in df1:
#input_filters_dict= {'font': (l[0],)}
input_filters_dict = {'m_label': list(range(48,58))+list(range(65,91))+list(range(97,123)),'font': (l[0],)}
#train_a_font(input_filters_dict,output_feature_list, nEpochs = 500)
ds = ocr_utils.read_data(input_filters_dict = input_filters_dict,
output_feature_list=output_feature_list,
'''
dumps out some statistics for the fonts.zip database and
makes plots, saved in files, of characters for each fontVariant found in
the database
Created on Jul 25, 2016
@author: richard
'''
import ocr_utils
import numpy as np
df1 = ocr_utils.get_list(input_filters_dict={'font': ()})
unique_fonts = []
unique_fontVariants = []
unique_m_labels = []
unique_strengths = []
unique_italics = []
unique_orientations = []
#############################################################################
# read and show the character images for each font variant
# output only the character label and the image
for font in df1:
df2 = ocr_utils.get_list(
input_filters_dict={
'font': font,
'fontVariant': (),
'm_label': (),
'strength': (),