Closed Shreeshrii closed 6 years ago
Thread 1 "lstmtraining" hit Breakpoint 2, tesseract::LSTMTrainer::EncodeString (str=..., unicharset=..., recoder=0x3fffffffe630, simple_text=false, null_char=26, labels=0x3fffffffdbd8)
at lstmtrainer.cpp:785
785 tprintf("Encoding of string failed! Failure bytes:");
(gdb) backtrace full
#0 tesseract::LSTMTrainer::EncodeString (str=..., unicharset=..., recoder=0x3fffffffe630, simple_text=false, null_char=26, labels=0x3fffffffdbd8) at lstmtrainer.cpp:785
err_index = 0
internal_labels = {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4, data_ = 0x10963360, clear_cb_ = 0x0, compare_cb_ = 0x0}
cleaned = "• arjuna uváca ---"
#1 0x00000000101e5c28 in tesseract::LSTMTrainer::EncodeString (this=0x3fffffffe408, str=..., labels=0x3fffffffdbd8) at lstmtrainer.h:248
No locals.
#2 0x00000000101e0d04 in tesseract::LSTMTrainer::PrepareForBackward (this=0x3fffffffe408, trainingdata=0x3fffac006e00, fwd_outputs=0x3fffffffdd28, targets=0x3fffffffddb8) at lstmtrainer.cpp:839
debug = false
truth_labels = {static kDefaultVectorSize = <optimized out>, size_used_ = 1, size_reserved_ = 4, data_ = 0x10963300, clear_cb_ = 0x0, compare_cb_ = 0x0}
upside_down = 63
w = -8800
image_scale = -nan(0x7fdbe0)
inputs = {f_ = {_vptr.GENERIC_2D_ARRAY = 0x3fffb7c00288 <__nptl_nthreads>, array_ = 0x3fffb6aaf100, empty_ = -nan(0x7fde30), dim1_ = 16383, dim2_ = -8864, size_allocated_ = 16383}, i_ = {
_vptr.GENERIC_2D_ARRAY = 0x3fffffffdc60, array_ = 0x3fffffffdca0 "\340\334\377\377\377?", empty_ = 0 '\000', dim1_ = 16383, dim2_ = 268528828, size_allocated_ = 0}, int_mode_ = false,
stride_map_ = {shape_ = {-9040, 16383, -8704}, t_increments_ = {16383, -1217303784, 16383}, heights_ = std::vector of length 16, capacity 4 = {-8992, 16383, -9040, 16383, 268529124, 0,
-1208027360, 16383, 271002932, 0, 459548672, -673080925, 0, 0, -8992, 16383}, widths_ = std::vector of length 17591816905295, capacity 618452 = {1610612736, 1610612736, 943652928,
-402587632, 2080900006, -337510408, 1317011488, 0, 16779520, 16777600, -69074952, -131989567, 2084506488, -125894616, 2089362296, -1858142172, -381747160, -2124480476, -1857486048,
1610612736, 943652928, -337510408, 1317011488, 0, 2304, 16777600, 1010831429, 943881728, 2080899750, -134152176, -75366432, -73269272, -71172112, -69074952, -131989583, 2084506488,
-125894616, -123797472, -381747160, -379650016, 2101629816, 2099465080, 1210506717, 1610612736, -381747168, -381091832, -381747160, -112656376, -381747168, -1991704560, -381747160,
-1723269104, -381747168, -1991704559, -381747160, -1723269103, -381747160, 961085464, 1002438679, -381747168, 1000931352, 2103202680, 958463999, 2143176704, 1100873764, 2141514616,
2139349880, 1207961273, 1610612736, 1000079392, 1002242080, 1004470271, 1275068376, -381747160, 2099465080, 943652944, -402587632, 2080900006, -343801888, -341704728, -339607568,
-337510408, 1317011488, 0, 16779520, 16778368, 1010831429, 943881728, 2080899750, -134152176, -69074952, -131989567, 2084506488, -125894616, -123797472, -381747160, 958990280,
-392232928, 2099465080, 1275068133, 1610612736, -394330072, 1209839929, 1610612736, 1610612736, 943652928, -402587632, 2080900006, -337510408, 1317011488, 0, 16779520, 16777600,
1010831429, 943881728, 2080899750, -134152176, -71172112, -69074952, -131989567, 2084506488, -125894616, 2089362296, -1858142172, -381747162, 958988344, 2032742052, -379650008,
2143963668, -381747160, 958988296, 2099465080, 1275026317, 1610612736, 2087263096, 1027608674, 1632259539, 2101956758, 2101884528, 2099969648, 2102018128, 491389928, 2099923024,
2099840948, 2099530616, 2143548280, 1207960793, 1610612736, 2087263096, -938934272, -65011568, 943652928, -402587632, 2080900006, -339607568, -337510408, 1317011488, 0, 16779520,
16777856, 1010831429, 943881728, 2080899750, -134152176, -69074952, -131989567, 2084506488, -125894616, -381747160, 958988360, 2099465080, 1275067537, 1610612736, -381747160,
958988320, 2099465080, 1207960089, 1610612736, -381747160, 2099465080, 1207960429, 1610612736, 1610612736, 943652928, -402587632, 2080900006, -337510408, 1317011488, 0, 16779520,
16777600, 1010831429, 943881728, 2080899750, -134152176, -69074952, -131989567, 2084506488, -125894616, -381747160...}}, static multiplier_ = 0x0}
invert = false
loss_type = 16383
ocr_labels = {static kDefaultVectorSize = <optimized out>, size_used_ = -8808, size_reserved_ = 16383, data_ = 0x3fffb6aaf1c0, clear_cb_ = 0x3fffffffde30, compare_cb_ = 0x3fffffffdda0}
xcoords = {static kDefaultVectorSize = <optimized out>, size_used_ = -9184, size_reserved_ = 16383, data_ = 0x3fffffffdc60, clear_cb_ = 0x3fffffffdda0, compare_cb_ = 0x10017170
<std::vector<int, std::allocator<int> >::vector()+44>}
ocr_text = {data_ = 0x10017d5c <std::_Vector_base<int, std::allocator<int> >::_Vector_impl::_Vector_impl()+40>}
truth_text = {data_ = 0x3fffb6aaf100}
char_error = 3.4766779034661238e-310
word_error = 3.4766779034898389e-310
delta_error = 3.4766177611194795e-310
#3 0x00000000101e08d4 in tesseract::LSTMTrainer::TrainOnLine (this=0x3fffffffe408, trainingdata=0x3fffac006e00, batch=false) at lstmtrainer.cpp:799
fwd_outputs = {f_ = {_vptr.GENERIC_2D_ARRAY = 0x10322c80 <vtable for GENERIC_2D_ARRAY<float>+16>, array_ = 0x0, empty_ = 0, dim1_ = 0, dim2_ = 0, size_allocated_ = 0}, i_ = {
_vptr.GENERIC_2D_ARRAY = 0x10322cb0 <vtable for GENERIC_2D_ARRAY<signed char>+16>, array_ = 0x0, empty_ = 0 '\000', dim1_ = 0, dim2_ = 0, size_allocated_ = 0}, int_mode_ = false,
stride_map_ = {shape_ = {0, 0, 0}, t_increments_ = {0, 0, 0}, heights_ = std::vector of length 0, capacity 0, widths_ = std::vector of length 0, capacity 0}, static multiplier_ = 0x0}
targets = {f_ = {_vptr.GENERIC_2D_ARRAY = 0x10322c80 <vtable for GENERIC_2D_ARRAY<float>+16>, array_ = 0x0, empty_ = 0, dim1_ = 0, dim2_ = 0, size_allocated_ = 0}, i_ = {
_vptr.GENERIC_2D_ARRAY = 0x10322cb0 <vtable for GENERIC_2D_ARRAY<signed char>+16>, array_ = 0x0, empty_ = 0 '\000', dim1_ = 0, dim2_ = 0, size_allocated_ = 0}, int_mode_ = false,
stride_map_ = {shape_ = {0, 0, 0}, t_increments_ = {0, 0, 0}, heights_ = std::vector of length 0, capacity 0, widths_ = std::vector of length 0, capacity 0}, static multiplier_ = 0x0}
trainable = tesseract::TRAINABLE
debug = false
bp_deltas = {f_ = {_vptr.GENERIC_2D_ARRAY = 0x3fffffffde50, array_ = 0x3fffffffdeb0, empty_ = 0, dim1_ = 0, dim2_ = 270724720, size_allocated_ = 0}, i_ = {_vptr.GENERIC_2D_ARRAY = 0x0,
array_ = 0x92ffffffff <error: Cannot access memory at address 0x92ffffffff>, empty_ = 112 'p', dim1_ = 16383, dim2_ = 1, size_allocated_ = 0}, int_mode_ = 9, stride_map_ = {shape_ = {
0, 14, -1409257984}, t_increments_ = {16383, -8480, 16383}, heights_ = std::vector of length 16, capacity 140 = {-8464, 16383, -7968, 16383, 268487508, 0, -1208027360, 16383, 0,
---Type <return> to continue, or q <return> to quit---
146, 459548672, -673080925, 0, 0, -8464, 16383}, widths_ = std::vector of length 17591816915699, capacity 156699184427 = {1610612736, 2087263096, 2099465080, 943652928, -402587632,
2080900006, -337510408, 1317011488, 0, 16779520, 16777600, -69074952, -131989567, 2084506488, -125894616, -381747160, -383188194, 2099465080, 943652928, -337510408, 1317011488, 0,
2304, 16777600, -69074952, -131989567, 2084506488, -125894616, -381747160, -383188190, 2099465080, 943652928, -337510408, 1317011488, 0, 2304, 16777600, 1010831429, 943881728,
2080899750, -134152176, -69074952, -131989567, 2084506488, -125894616, -381747160, -383188198, 2032732128, 2099840948, 799604736, 1084096592, -381747160, -383188992, -383188992,
958988368, -381091840, -381747160, -383188992, 2099465080, -129957864, 2102154104, 2106131366, 1317012513, -398393320, -381747160, -383188198, 1630076929, 2099906484, -381747160,
-1857486056, 1610612736, 943652928, -402587632, 2080900006, -337510408, 1317011488, 0, 16779520, 16777600, 1010831429, 943881728, 2080899750, -134152176, -71172112, -69074952,
-131989631, 2084506488, -125894552, -123797408, -381747096, 1003030472, -394330016, 1275048189, -398393320, 2087263096, 2099530616, 2143548280, 1210551757, 1610612736, 2087263096,
1764294657, 1428751934, 799604736, 1100873780, 956301422, 1021509613, 954696552, 1019412461, 952533896, 950009858, 1015218157, 948208544, 1610612736, 945984008, 1210520253,
1610612736, -394330008, 1209881485, 1610612736, 1610612736, 943652992, -402587632, 2080900006, -339607568, -337510408, 1317011488, 0, 16779520, 16777856, -69074952, -131989567,
2084506488, -125894616, -381747160, -938932792, -65011568, 943652928, -337510408, 1317011488, 0, 2304, 16777600, -69074952, -131989567, 2084506488, -125894616, 2089362296,
-1858142172, -381747160, -2124480476, -1857485068, 1610612736, 943652928, -337510408, 1317011488, 0, 2304, 16777600, 1010831429, 943881728, 2080899750, -134152176, -69074952,
-131989599, 2084506488, -125894600, -123797456, 2091461496, -1723924433, -381747144, 958988296, 2099465080, 1275067825, 1610612736, 2087263096, -1858142144, -381747152, 958989672,
-379649982, 2101629816, 2099465080, 1275067601, 1610612736, 2087263096, -113311672, -381747128, 799604736, 1100873796, -1992359889, 2099596152, -392232888, -394330056, 1209874961,
1610612736, 2087263096, -1858142140, -2126577596, 797507586, 1100873744, -2126577596...}}, static multiplier_ = 0x0}
#4 0x000000001000ce58 in tesseract::LSTMTrainer::TrainOnLine (this=0x3fffffffe408, samples_trainer=0x3fffffffe408, batch=false) at ../../src/lstm/lstmtrainer.h:264
trainable = tesseract::PERFECT
sample_index = 146
image = 0x3fffac006e00
#5 0x000000001000b27c in main (argc=1, argv=0x3ffffffff3c8) at lstmtraining.cpp:201
target_iteration = 200
iteration = 100
log_str = {data_ = 0x3fffb7fefc60 <__libc_enable_secure>}
model_output = {data_ = 0x107233b0}
checkpoint_file = {data_ = 0x107233e0}
checkpoint_bak = {data_ = 0x10724000}
trainer = {<tesseract::LSTMRecognizer> = {network_ = 0x10941e80, ccutil_ = {_vptr.CCUtil = 0x103221f8 <vtable for tesseract::CCUtil+16>, datadir = {data_ = 0x10723390}, imagebasename = {
data_ = 0x10711dd0}, lang = {data_ = 0x10711e10}, language_data_path_prefix = {data_ = 0x10711f30}, unicharset = {static kCustomLigatures =
0x10450e78 <UNICHARSET::kCustomLigatures>, static kSpecialUnicharCodes = {0x10367f78 " ", 0x1037ed80 "Joined", 0x1037ed88 "|Broken|0|1"},
static kCleanupMaps = <same as static member of an already seen type>, static null_script = 0x1037ebb8 "NULL", unichars = 0x10961768, ids = {nodes = 0x10941f28}, size_used = 28,
size_reserved = 28, script_table = 0x10962890, script_table_size_used = 3, script_table_size_reserved = 8, top_bottom_set_ = true, script_has_upper_lower_ = true,
script_has_xheight_ = true, old_style_included_ = false, null_sid_ = 0, common_sid_ = 1, latin_sid_ = 2, cyrillic_sid_ = 0, greek_sid_ = 0, han_sid_ = 0, hiragana_sid_ = 0,
katakana_sid_ = 0, thai_sid_ = 0, hangul_sid_ = 0, default_sid_ = 2}, unichar_ambigs = {dang_ambigs_ = {static kDefaultVectorSize = <optimized out>, size_used_ = 0,
size_reserved_ = 4, data_ = 0x10924930, clear_cb_ = 0x0, compare_cb_ = 0x0}, replace_ambigs_ = {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4,
data_ = 0x109248a0, clear_cb_ = 0x0, compare_cb_ = 0x0}, one_to_one_definite_ambigs_ = {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4,
data_ = 0x109248d0, clear_cb_ = 0x0, compare_cb_ = 0x0}, ambigs_for_adaption_ = {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4,
data_ = 0x10936330, clear_cb_ = 0x0, compare_cb_ = 0x0}, reverse_ambigs_for_adaption_ = {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4,
data_ = 0x10936360, clear_cb_ = 0x0, compare_cb_ = 0x0}}, imagefile = {data_ = 0x10724090}, directory = {data_ = 0x10936390}, params_ = {int_params = {
static kDefaultVectorSize = <optimized out>, size_used_ = 1, size_reserved_ = 4, data_ = 0x109363b0, clear_cb_ = 0x0, compare_cb_ = 0x0}, bool_params = {
static kDefaultVectorSize = <optimized out>, size_used_ = 2, size_reserved_ = 4, data_ = 0x109363e0, clear_cb_ = 0x0, compare_cb_ = 0x0}, string_params = {
static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4, data_ = 0x10936410, clear_cb_ = 0x0, compare_cb_ = 0x0}, double_params = {
static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4, data_ = 0x10936440, clear_cb_ = 0x0, compare_cb_ = 0x0}},
ambigs_debug_level = {<tesseract::Param> = {name_ = 0x1037cc48 "ambigs_debug_level", info_ = 0x1037cc60 "Debug level for unichar ambiguities", init_ = true, debug_ = true},
value_ = 0, default_ = 0, params_vec_ = 0x3fffffffe548}, use_definite_ambigs_for_classifier = {<tesseract::Param> = {name_ = 0x1037cc88 "use_definite_ambigs_for_classifier",
info_ = 0x1037ccb0 "Use definite ambiguities when running character classifier", init_ = false, debug_ = false}, value_ = 0 '\000', default_ = 0 '\000',
params_vec_ = 0x3fffffffe568}, use_ambigs_for_adaption = {<tesseract::Param> = {name_ = 0x1037ccf0 "use_ambigs_for_adaption",
info_ = 0x1037cd08 "Use ambigs for deciding whether to adapt to a character", init_ = false, debug_ = false}, value_ = 0 '\000', default_ = 0 '\000',
params_vec_ = 0x3fffffffe568}}, recoder_ = {static kFirstHangul = 44032, static kNumHangul = 11172, static kLCount = 19, static kVCount = 21, static kTCount = 28, encoder_ = {
static kDefaultVectorSize = <optimized out>, size_used_ = 28, size_reserved_ = 28, data_ = 0x10946f70, clear_cb_ = 0x0, compare_cb_ = 0x0},
decoder_ = std::unordered_map with 27 elements = {[{static kMaxCodeLen = 9, self_normalized_ = 1 '\001', length_ = 1, code_ = {25, 0, 0, 0, 0, 0, 0, 0, 0}}] = 27, [{
static kMaxCodeLen = 9, self_normalized_ = 1 '\001', length_ = 1, code_ = {24, 0, 0, 0, 0, 0, 0, 0, 0}}] = 26, [{static kMaxCodeLen = 9, self_normalized_ = 1 '\001',
length_ = 1, code_ = {23, 0, 0, 0, 0, 0, 0, 0, 0}}] = 25, [{static kMaxCodeLen = 9, self_normalized_ = 1 '\001', length_ = 1, code_ = {22, 0, 0, 0, 0, 0, 0, 0, 0}}] = 24, [{
---Type <return> to continue, or q <return> to quit---
static kMaxCodeLen = 9, self_normalized_ = 1 '\001', length_ = 1, code_ = {21, 0, 0, 0, 0, 0, 0, 0, 0}}] = 23, [{static kMaxCodeLen = 9, self_normalized_ = 1 '\001',
length_ = 1, code_ = {20, 0, 0, 0, 0, 0, 0, 0, 0}}] = 22, [{static kMaxCodeLen = 9, self_normalized_ = 1 '\001', length_ = 1, code_ = {19, 0, 0, 0, 0, 0, 0, 0, 0}}] = 21, [{
static kMaxCodeLen = 9, self_normalized_ = 1 '\001', length_ = 1, code_ = {18, 0, 0, 0, 0, 0, 0, 0, 0}}] = 20, [{static kMaxCodeLen = 9, self_normalized_ = 1 '\001',
length_ = 1, code_ = {17, 0, 0, 0, 0, 0, 0, 0, 0}}] = 19, [{static kMaxCodeLen = 9, self_normalized_ = 1 '\001', length_ = 1, code_ = {16, 0, 0, 0, 0, 0, 0, 0, 0}}] = 18, [{
static kMaxCodeLen = 9, self_normalized_ = 1 '\001', length_ = 1, code_ = {15, 0, 0, 0, 0, 0, 0, 0, 0}}] = 17, [{static kMaxCodeLen = 9, self_normalized_ = 1 '\001',
length_ = 1, code_ = {14, 0, 0, 0, 0, 0, 0, 0, 0}}] = 16, [{static kMaxCodeLen = 9, self_normalized_ = 1 '\001', length_ = 1, code_ = {13, 0, 0, 0, 0, 0, 0, 0, 0}}] = 15, [{
static kMaxCodeLen = 9, self_normalized_ = 1 '\001', length_ = 1, code_ = {12, 0, 0, 0, 0, 0, 0, 0, 0}}] = 14, [{static kMaxCodeLen = 9, self_normalized_ = 1 '\001',
length_ = 1, code_ = {11, 0, 0, 0, 0, 0, 0, 0, 0}}] = 13, [{static kMaxCodeLen = 9, self_normalized_ = 1 '\001', length_ = 1, code_ = {10, 0, 0, 0, 0, 0, 0, 0, 0}}] = 12, [{
static kMaxCodeLen = 9, self_normalized_ = 1 '\001', length_ = 1, code_ = {9, 0, 0, 0, 0, 0, 0, 0, 0}}] = 11, [{static kMaxCodeLen = 9, self_normalized_ = 1 '\001', length_ = 1,
code_ = {8, 0, 0, 0, 0, 0, 0, 0, 0}}] = 10, [{static kMaxCodeLen = 9, self_normalized_ = 1 '\001', length_ = 1, code_ = {7, 0, 0, 0, 0, 0, 0, 0, 0}}] = 9, [{
static kMaxCodeLen = 9, self_normalized_ = 1 '\001', length_ = 1, code_ = {6, 0, 0, 0, 0, 0, 0, 0, 0}}] = 8, [{static kMaxCodeLen = 9, self_normalized_ = 1 '\001', length_ = 1,
code_ = {5, 0, 0, 0, 0, 0, 0, 0, 0}}] = 7, [{static kMaxCodeLen = 9, self_normalized_ = 1 '\001', length_ = 1, code_ = {4, 0, 0, 0, 0, 0, 0, 0, 0}}] = 6, [{
static kMaxCodeLen = 9, self_normalized_ = 1 '\001', length_ = 1, code_ = {3, 0, 0, 0, 0, 0, 0, 0, 0}}] = 5, [{static kMaxCodeLen = 9, self_normalized_ = 1 '\001', length_ = 1,
code_ = {2, 0, 0, 0, 0, 0, 0, 0, 0}}] = 4, [{static kMaxCodeLen = 9, self_normalized_ = 1 '\001', length_ = 1, code_ = {1, 0, 0, 0, 0, 0, 0, 0, 0}}] = 3, [{
static kMaxCodeLen = 9, self_normalized_ = 1 '\001', length_ = 1, code_ = {26, 0, 0, 0, 0, 0, 0, 0, 0}}] = 2, [{static kMaxCodeLen = 9, self_normalized_ = 1 '\001', length_ = 1,
code_ = {0, 0, 0, 0, 0, 0, 0, 0, 0}}] = 0}, is_valid_start_ = {static kDefaultVectorSize = <optimized out>, size_used_ = 27, size_reserved_ = 27, data_ = 0x1092d0d0,
clear_cb_ = 0x0, compare_cb_ = 0x0}, next_codes_ = std::unordered_map with 0 elements, final_codes_ = std::unordered_map with 1 elements = {[{static kMaxCodeLen = 9,
self_normalized_ = 1 '\001', length_ = 0, code_ = {0, 0, 0, 0, 0, 0, 0, 0, 0}}] = 0x109368e0}, code_range_ = 27}, network_str_ = {data_ = 0x10960f60}, training_flags_ = 64,
training_iteration_ = 100, sample_iteration_ = 146, null_char_ = 26, learning_rate_ = 0.00100000005, momentum_ = 0.5, adam_beta_ = 0.999000013, randomizer_ = {seed_ = 1},
scratch_space_ = {int_mode_ = false, int_stack_ = {stack_ = {<GenericVector<tesseract::NetworkIO*>> = {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4,
data_ = 0x10936570, clear_cb_ = 0x0, compare_cb_ = 0x0}, <No data fields>}, flags_ = {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4,
data_ = 0x109365a0, clear_cb_ = 0x0, compare_cb_ = 0x0}, stack_top_ = 0, mutex_ = {mutex_ = {__data = {__lock = 0, __count = 0, __owner = 0, __nusers = 0, __kind = 0,
__spins = 0, __elision = 0, __list = {__prev = 0x0, __next = 0x0}}, __size = '\000' <repeats 39 times>, __align = 0}}}, float_stack_ = {
stack_ = {<GenericVector<tesseract::NetworkIO*>> = {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4, data_ = 0x109365c0, clear_cb_ = 0x0,
compare_cb_ = 0x0}, <No data fields>}, flags_ = {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4, data_ = 0x109365f0, clear_cb_ = 0x0,
compare_cb_ = 0x0}, stack_top_ = 0, mutex_ = {mutex_ = {__data = {__lock = 0, __count = 0, __owner = 0, __nusers = 0, __kind = 0, __spins = 0, __elision = 0, __list = {
__prev = 0x0, __next = 0x0}}, __size = '\000' <repeats 39 times>, __align = 0}}}, vec_stack_ = {stack_ = {<GenericVector<GenericVector<double>*>> = {
static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4, data_ = 0x10936610, clear_cb_ = 0x0, compare_cb_ = 0x0}, <No data fields>}, flags_ = {
static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4, data_ = 0x10936640, clear_cb_ = 0x0, compare_cb_ = 0x0}, stack_top_ = 0, mutex_ = {mutex_ = {
__data = {__lock = 0, __count = 0, __owner = 0, __nusers = 0, __kind = 0, __spins = 0, __elision = 0, __list = {__prev = 0x0, __next = 0x0}},
__size = '\000' <repeats 39 times>, __align = 0}}}, array_stack_ = {stack_ = {<GenericVector<tesseract::TransposedArray*>> = {static kDefaultVectorSize = <optimized out>,
size_used_ = 0, size_reserved_ = 4, data_ = 0x10936660, clear_cb_ = 0x0, compare_cb_ = 0x0}, <No data fields>}, flags_ = {static kDefaultVectorSize = <optimized out>,
size_used_ = 0, size_reserved_ = 4, data_ = 0x10936690, clear_cb_ = 0x0, compare_cb_ = 0x0}, stack_top_ = 0, mutex_ = {mutex_ = {__data = {__lock = 0, __count = 0, __owner = 0,
__nusers = 0, __kind = 0, __spins = 0, __elision = 0, __list = {__prev = 0x0, __next = 0x0}}, __size = '\000' <repeats 39 times>, __align = 0}}}}, dict_ = 0x0,
search_ = 0x0, debug_win_ = 0x0}, _vptr.LSTMTrainer = 0x1036fff0 <vtable for tesseract::LSTMTrainer+16>, align_win_ = 0x0, target_win_ = 0x0, ctc_win_ = 0x0, recon_win_ = 0x0,
debug_interval_ = -1, checkpoint_iteration_ = 0, model_base_ = {data_ = 0x109367f0}, checkpoint_name_ = {data_ = 0x10936820}, randomly_rotate_ = false, training_data_ = {
documents_ = {<GenericVector<tesseract::DocumentData*>> = {static kDefaultVectorSize = <optimized out>, size_used_ = 11, size_reserved_ = 16, data_ = 0x109629f0, clear_cb_ = 0x0,
compare_cb_ = 0x0}, <No data fields>}, cache_strategy_ = tesseract::CS_ROUND_ROBIN, num_pages_per_doc_ = 0, max_memory_ = 6291456000}, best_model_name_ = {data_ = 0x10936720},
num_training_stages_ = 2, file_reader_ = 0x101e4afc <tesseract::LoadDataFromFile(STRING const&, GenericVector<char>*)>,
file_writer_ = 0x101e4b68 <tesseract::SaveDataToFile(GenericVector<char> const&, STRING const&)>, checkpoint_reader_ = 0x109368b0, checkpoint_writer_ = 0x10936be0,
best_error_rate_ = 95.632999999999996, best_error_rates_ = {12.999000000000001, 49.640999999999998, 99.667000000000002, 95.632999999999996, 46}, best_iteration_ = 100,
worst_error_rate_ = 95.632999999999996, worst_error_rates_ = {12.999000000000001, 49.640999999999998, 99.667000000000002, 95.632999999999996, 46}, worst_iteration_ = 100,
stall_iteration_ = 10100, best_model_data_ = {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4, data_ = 0x10936740 "", clear_cb_ = 0x0,
compare_cb_ = 0x0}, worst_model_data_ = {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4, data_ = 0x10936760 "", clear_cb_ = 0x0, compare_cb_ = 0x0},
best_trainer_ = {static kDefaultVectorSize = <optimized out>, size_used_ = 9257707, size_reserved_ = 9257707, data_ = 0x3fffb39f0010 "", clear_cb_ = 0x0, compare_cb_ = 0x0},
sub_trainer_ = 0x0, error_rate_of_last_saved_best_ = 75, training_stage_ = 0, best_error_history_ = {static kDefaultVectorSize = <optimized out>, size_used_ = 1, size_reserved_ = 4,
data_ = 0x109367a0, clear_cb_ = 0x0, compare_cb_ = 0x0}, best_error_iterations_ = {static kDefaultVectorSize = <optimized out>, size_used_ = 1, size_reserved_ = 4, data_ = 0x109367d0,
clear_cb_ = 0x0, compare_cb_ = 0x0}, improvement_steps_ = 100, learning_iteration_ = 100, prev_sample_iteration_ = 146, perfect_delay_ = 0, last_perfect_training_iteration_ = 0,
static kRollingBufferSize_ = 1000, error_buffers_ = {{static kDefaultVectorSize = <optimized out>, size_used_ = 1000, size_reserved_ = 1000, data_ = 0x10936c40, clear_cb_ = 0x0,
compare_cb_ = 0x0}, {static kDefaultVectorSize = <optimized out>, size_used_ = 1000, size_reserved_ = 1000, data_ = 0x10938b90, clear_cb_ = 0x0, compare_cb_ = 0x0}, {
static kDefaultVectorSize = <optimized out>, size_used_ = 1000, size_reserved_ = 1000, data_ = 0x1093aae0, clear_cb_ = 0x0, compare_cb_ = 0x0}, {
---Type <return> to continue, or q <return> to quit---
static kDefaultVectorSize = <optimized out>, size_used_ = 1000, size_reserved_ = 1000, data_ = 0x1093ca30, clear_cb_ = 0x0, compare_cb_ = 0x0}, {
static kDefaultVectorSize = <optimized out>, size_used_ = 1000, size_reserved_ = 1000, data_ = 0x1093e980, clear_cb_ = 0x0, compare_cb_ = 0x0}}, error_rates_ = {12.999000000000001,
49.640999999999998, 99.667000000000002, 95.632999999999996, 46}, mgr_ = {data_file_name_ = {data_ = 0x109408d0}, reader_ = 0x0, is_loaded_ = true, swap_ = false, entries_ = {{
static kDefaultVectorSize = <optimized out>, size_used_ = 863, size_reserved_ = 863,
data_ = 0x10940940 "# IAST=International Alphabet of Sanskrit Transliteration\n# http://en.wikipedia.org/wiki/International_Alphabet_of_Sanskrit_Transliteration\n# http://en.wikipedia.org/wiki/ISO_15919\n\n# config variables"..., clear_cb_ = 0x0, compare_cb_ = 0x0}, {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 0, data_ = 0x0,
clear_cb_ = 0x0, compare_cb_ = 0x0} <repeats 17 times>, {static kDefaultVectorSize = <optimized out>, size_used_ = 42, size_reserved_ = 42, data_ = 0x109366b0 "*",
clear_cb_ = 0x0, compare_cb_ = 0x0}, {static kDefaultVectorSize = <optimized out>, size_used_ = 64938, size_reserved_ = 64938, data_ = 0x10963730 "*", clear_cb_ = 0x0,
compare_cb_ = 0x0}, {static kDefaultVectorSize = <optimized out>, size_used_ = 954, size_reserved_ = 954, data_ = 0x10940cb0 "*", clear_cb_ = 0x0, compare_cb_ = 0x0}, {
static kDefaultVectorSize = <optimized out>, size_used_ = 1856, size_reserved_ = 1856,
data_ = 0x10941080 "28\nNULL 0 Common 0\nJoined 7 0,255,0,255,0,0,0,0,0,0 Latin 1 0 1 Joined\t# Joined [4a 6f 69 6e 65 64 ]a\n|Broken|0|1 f 0,255,0,255,0,0,0,0,0,0 Common 2 10 2 |Broken|0|1\t# Broken\na 3 58,65,186,200,85,164,"..., clear_cb_ = 0x0, compare_cb_ = 0x0}, {static kDefaultVectorSize = <optimized out>, size_used_ = 256, size_reserved_ = 256,
data_ = 0x109369d0 "\034", clear_cb_ = 0x0, compare_cb_ = 0x0}, {static kDefaultVectorSize = <optimized out>, size_used_ = 22, size_reserved_ = 22,
data_ = 0x10936890 "4.0.0-beta.3-105-g909a", clear_cb_ = 0x0, compare_cb_ = 0x0}}}}
filenames = {static kDefaultVectorSize = <optimized out>, size_used_ = 11, size_reserved_ = 16, data_ = 0x10947dc8, clear_cb_ = 0x0, compare_cb_ = 0x0}
tester = {test_data_ = {documents_ = {<GenericVector<tesseract::DocumentData*>> = {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4, data_ = 0x109616d0,
clear_cb_ = 0x0, compare_cb_ = 0x0}, <No data fields>}, cache_strategy_ = (unknown: 4294961440), num_pages_per_doc_ = 0, max_memory_ = 6291456000}, total_pages_ = 0,
async_running_ = false, running_mutex_ = {mutex_ = {__data = {__lock = 0, __count = 0, __owner = 0, __nusers = 0, __kind = 0, __spins = 0, __elision = 0, __list = {__prev = 0x0,
__next = 0x0}}, __size = '\000' <repeats 39 times>, __align = 0}}, test_iteration_ = -1208020688, test_training_errors_ = 0x0, test_model_mgr_ = {data_file_name_ = {
data_ = 0x10936780}, reader_ = 0x0, is_loaded_ = false, swap_ = false, entries_ = {{static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4,
data_ = 0x10936490 "@\r\204\267\377?", clear_cb_ = 0x0, compare_cb_ = 0x0}, {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4,
data_ = 0x109629a0 "@\r\204\267\377?", clear_cb_ = 0x0, compare_cb_ = 0x0}, {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4,
data_ = 0x10963060 "0\r\204\267\377?", clear_cb_ = 0x0, compare_cb_ = 0x0}, {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4,
data_ = 0x10963080 "0\r\204\267\377?", clear_cb_ = 0x0, compare_cb_ = 0x0}, {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4,
data_ = 0x109630a0 "0\r\204\267\377?", clear_cb_ = 0x0, compare_cb_ = 0x0}, {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4,
data_ = 0x109630c0 "0\r\204\267\377?", clear_cb_ = 0x0, compare_cb_ = 0x0}, {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4,
data_ = 0x109630e0 "0\r\204\267\377?", clear_cb_ = 0x0, compare_cb_ = 0x0}, {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4,
data_ = 0x10963100 "0\r\204\267\377?", clear_cb_ = 0x0, compare_cb_ = 0x0}, {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4,
data_ = 0x10963120 "0\r\204\267\377?", clear_cb_ = 0x0, compare_cb_ = 0x0}, {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4,
data_ = 0x10963140 "0\r\204\267\377?", clear_cb_ = 0x0, compare_cb_ = 0x0}, {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4,
data_ = 0x10963160 "0\r\204\267\377?", clear_cb_ = 0x0, compare_cb_ = 0x0}, {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4,
data_ = 0x10963180 "0\r\204\267\377?", clear_cb_ = 0x0, compare_cb_ = 0x0}, {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4,
data_ = 0x109631a0 "0\r\204\267\377?", clear_cb_ = 0x0, compare_cb_ = 0x0}, {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4,
data_ = 0x109631c0 "0\r\204\267\377?", clear_cb_ = 0x0, compare_cb_ = 0x0}, {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4,
data_ = 0x109631e0 "0\r\204\267\377?", clear_cb_ = 0x0, compare_cb_ = 0x0}, {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4,
data_ = 0x10963200 "0\r\204\267\377?", clear_cb_ = 0x0, compare_cb_ = 0x0}, {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4,
data_ = 0x10963220 "0\r\204\267\377?", clear_cb_ = 0x0, compare_cb_ = 0x0}, {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4,
data_ = 0x10963240 "0\r\204\267\377?", clear_cb_ = 0x0, compare_cb_ = 0x0}, {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4,
data_ = 0x10963260 "0\r\204\267\377?", clear_cb_ = 0x0, compare_cb_ = 0x0}, {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4,
data_ = 0x10963280 "0\r\204\267\377?", clear_cb_ = 0x0, compare_cb_ = 0x0}, {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4,
data_ = 0x109632a0 "0\r\204\267\377?", clear_cb_ = 0x0, compare_cb_ = 0x0}, {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4,
data_ = 0x109632c0 "0\r\204\267\377?", clear_cb_ = 0x0, compare_cb_ = 0x0}, {static kDefaultVectorSize = <optimized out>, size_used_ = 0, size_reserved_ = 4,
data_ = 0x109632e0 "0\r\204\267\377?", clear_cb_ = 0x0, compare_cb_ = 0x0}, {static kDefaultVectorSize = <optimized out>, size_used_ = 23, size_reserved_ = 23,
data_ = 0x10963340 "4.0.0-beta.3-130-gc9efe0!", clear_cb_ = 0x0, compare_cb_ = 0x0}}}, test_training_stage_ = -5752, test_result_ = {data_ = 0x10963320}}
tester_callback = 0x0
@stweil I built using
./configure --enable-debug --disable-shared --disable-static CXXFLAGS="-Wall -Wextra -g -O0"
Still some variables show up as optimized out
.
Also, is this missing file to be expected on error while running gdb?
./configure --disable-shared --disable-static
Using both options does not make sense. One of these options will be ignored. Use just one of them.
This is a general advice, unrelated to your issue.
I think it makes sense. That's my default configuration because it compiles fast and is optimized for debugging.
It's strange that some variables where optimized out. Maybe that code parts where compiled with optimization enabled?
The missing files could be part of the standard C library. In addition to the debug information (provided by Debian package libc6-dbg
) you'll also need the source code for libc
if you want full debugging.
Thank you! So, looks like this is unrelated to tesseract. CLosing the issue.
Hint: instead of stepping into library functions for which there is no source code, you can use next
which steps over the next line of code.
Thank you for the hint. I will try it next time.
I think it makes sense.
Think again :-)
./configure --disable-shared --disable-static
configure will just ignore the second option.
configure's output:
checking whether to build shared libraries... no checking whether to build static libraries... yes
So it's equivalent to:
./configure --disable-shared
Thank you. It's always good to have someone who carefully reviews things.
You are perfectly right, and I can simplify my build scripts by removing -disable-static
.
I wrongly thought that I could avoid building the static libraries because I did not want to build
external applications based on them. But of course Tesseract's own applications also are linked
against those libraries, so they are always needed (either static or shared).
I'm glad this tip helped you!
A reminder from the past: https://github.com/tesseract-ocr/tesseract/issues/943#issuecomment-305408592
This time, I was able to get your attention :-)
@amitdo Thank You.
But of course Tesseract's own applications also are linked against those libraries, so they are always needed (either static or shared).
Shouldn't then there be an error thrown if both static and shared libraries are disabled?
While running gdb for 'Encoding of string failed!`