nn_ds_inmem5.py 26.7 KB
Newer Older
Andrey Filippov's avatar
Andrey Filippov committed
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115
#!/usr/bin/env python3
from numpy import float64

__copyright__ = "Copyright 2018, Elphel, Inc."
__license__   = "GPL-3.0+"
__email__     = "andrey@elphel.com"


from PIL import Image

import os
import sys
import glob

import numpy as np
import itertools

import time

import matplotlib.pyplot as plt

import shutil

TIME_START = time.time()
TIME_LAST  = TIME_START
DEBUG_LEVEL= 1
DISP_BATCH_BINS =   20 # Number of batch disparity bins
STR_BATCH_BINS =    10 # Number of batch strength bins
FILES_PER_SCENE =    5 # number of random offset files for the scene to select from (0 - use all available)
#MIN_BATCH_CHOICES = 10 # minimal number of tiles in a file for each bin to select from 
#MAX_BATCH_FILES =   10 #maximal number of files to use in a batch
MAX_EPOCH =        500
LR =               1e-4 # learning rate
USE_CONFIDENCE =     False
ABSOLUTE_DISPARITY = False # True # False
DEBUG_PLT_LOSS =     True
FEATURES_PER_TILE =  324
EPOCHS_TO_RUN =     10000 #0
EPOCHS_SAME_FILE =   20
RUN_TOT_AVG =       100 # last batches to average. Epoch is 307 training  batches  
BATCH_SIZE =       1080 # Each batch of tiles has balanced D/S tiles, shuffled batches but not inside batches
SHUFFLE_EPOCH =    True
NET_ARCH =           3 # overwrite with argv?
#DEBUG_PACK_TILES = True
SUFFIX=str(NET_ARCH)+ (["R","A"][ABSOLUTE_DISPARITY])
#http://stackoverflow.com/questions/287871/print-in-terminal-with-colors-using-python
class bcolors:
    HEADER = '\033[95m'
    OKBLUE = '\033[94m'
    OKGREEN = '\033[92m'
    WARNING = '\033[38;5;214m'
    FAIL = '\033[91m'
    ENDC = '\033[0m'
    BOLD = '\033[1m'
    BOLDWHITE = '\033[1;37m'
    UNDERLINE = '\033[4m'
def print_time(txt="",end="\n"):
    global TIME_LAST
    t = time.time()
    if txt:
        txt +=" "
    print(("%s"+bcolors.BOLDWHITE+"at %.4fs (+%.4fs)"+bcolors.ENDC)%(txt,t-TIME_START,t-TIME_LAST), end = end, flush=True)
    TIME_LAST = t
#reading to memory (testing)
def readTFRewcordsEpoch(train_filename):
#    filenames = [train_filename]
#    dataset = tf.data.TFRecordDataset(filenames)
    if not  '.tfrecords' in train_filename:
        train_filename += '.tfrecords'
    record_iterator = tf.python_io.tf_record_iterator(path=train_filename)
    corr2d_list=[]
    target_disparity_list=[]
    gt_ds_list = []
    for string_record in record_iterator:
        example = tf.train.Example()
        example.ParseFromString(string_record)
        corr2d_list.append           (np.array(example.features.feature['corr2d'].float_list.value, dtype=np.float32))
#        target_disparity_list.append(np.array(example.features.feature['target_disparity'].float_list.value[0], dtype=np.float32))
        target_disparity_list.append (np.array(example.features.feature['target_disparity'].float_list.value, dtype=np.float32))
        gt_ds_list.append            (np.array(example.features.feature['gt_ds'].float_list.value, dtype= np.float32))
    corr2d=            np.array(corr2d_list)
    target_disparity = np.array(target_disparity_list)
    gt_ds =            np.array(gt_ds_list)
    return corr2d, target_disparity, gt_ds   

#from http://warmspringwinds.github.io/tensorflow/tf-slim/2016/12/21/tfrecords-guide/
def read_and_decode(filename_queue):
    reader = tf.TFRecordReader()
    _, serialized_example = reader.read(filename_queue)

    features = tf.parse_single_example(
      serialized_example,
      # Defaults are not specified since both keys are required.
      features={
        'corr2d':           tf.FixedLenFeature([324],tf.float32), #string),
        'target_disparity': tf.FixedLenFeature([1],   tf.float32), #.string),
        'gt_ds':            tf.FixedLenFeature([2],  tf.float32)  #.string)
        })
    corr2d =           features['corr2d'] # tf.decode_raw(features['corr2d'], tf.float32)
    target_disparity = features['target_disparity'] # tf.decode_raw(features['target_disparity'], tf.float32)
    gt_ds =            tf.cast(features['gt_ds'], tf.float32) # tf.decode_raw(features['gt_ds'], tf.float32)
    in_features = tf.concat([corr2d,target_disparity],0)
    # still some nan-s in correlation data?
#    in_features_clean = tf.where(tf.is_nan(in_features), tf.zeros_like(in_features), in_features)     
#    corr2d_out, target_disparity_out, gt_ds_out = tf.train.shuffle_batch( [in_features_clean, target_disparity, gt_ds],
    corr2d_out, target_disparity_out, gt_ds_out = tf.train.shuffle_batch( [in_features, target_disparity, gt_ds],
                                                 batch_size=1000, # 2,
                                                 capacity=30,
                                                 num_threads=2,
                                                 min_after_dequeue=10)
    return corr2d_out, target_disparity_out, gt_ds_out

#http://adventuresinmachinelearning.com/introduction-tensorflow-queuing/

#Main code
116
"""
Andrey Filippov's avatar
Andrey Filippov committed
117 118 119 120 121 122 123 124 125
try:
    train_filenameTFR =  sys.argv[1]
except IndexError:
    train_filenameTFR = "/mnt/dde6f983-d149-435e-b4a2-88749245cc6c/home/eyesis/x3d_data/data_sets/tf_data/train_00.tfrecords"
try:
    test_filenameTFR =  sys.argv[2]
except IndexError:
    test_filenameTFR = "/mnt/dde6f983-d149-435e-b4a2-88749245cc6c/home/eyesis/x3d_data/data_sets/tf_data/test.tfrecords"
train_filenameTFR1 = "/mnt/dde6f983-d149-435e-b4a2-88749245cc6c/home/eyesis/x3d_data/data_sets/tf_data/train_01.tfrecords"
126 127
"""    
#FILES_PER_SCENE
Andrey Filippov's avatar
Andrey Filippov committed
128

129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147
files_train_lvar = ["/home/eyesis/x3d_data/data_sets/tf_data_3x3/train-000_R1_GT_1.5.tfrecords",
                    "/home/eyesis/x3d_data/data_sets/tf_data_3x3/train-001_R1_GT_1.5.tfrecords",
                    
                    "/home/eyesis/x3d_data/data_sets/tf_data_3x3/train-002_R1_GT_1.5.tfrecords",
                    "/home/eyesis/x3d_data/data_sets/tf_data_3x3/train-003_R1_GT_1.5.tfrecords",
                    "/home/eyesis/x3d_data/data_sets/tf_data_3x3/train-004_R1_GT_1.5.tfrecords",
                    "/home/eyesis/x3d_data/data_sets/tf_data_3x3/train-005_R1_GT_1.5.tfrecords",
                    "/home/eyesis/x3d_data/data_sets/tf_data_3x3/train-006_R1_GT_1.5.tfrecords",
                    "/home/eyesis/x3d_data/data_sets/tf_data_3x3/train-007_R1_GT_1.5.tfrecords",
                    ]

#files_train_hvar = ["/home/eyesis/x3d_data/data_sets/tf_data_3x3/train-000_R1_LE_1.5.tfrecords",
#                    "/home/eyesis/x3d_data/data_sets/tf_data_3x3/train-001_R1_LE_1.5.tfrecords"]

files_train_hvar = []
#file_test_lvar=     "/home/eyesis/x3d_data/data_sets/tf_data_3x3/train-002_R1_LE_1.5.tfrecords" # "/home/eyesis/x3d_data/data_sets/train-000_R1_LE_1.5.tfrecords"
#file_test_hvar=     "/home/eyesis/x3d_data/data_sets/tf_data_3x3/train-002_R1_LE_1.5.tfrecords" # "/home/eyesis/x3d_data/data_sets/train-000_R1_LE_1.5.tfrecords"
file_test_lvar=     "/home/eyesis/x3d_data/data_sets/tf_data_3x3/test-TEST_R1_GT_1.5.tfrecords"
file_test_hvar=     None
Andrey Filippov's avatar
Andrey Filippov committed
148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205

weight_hvar = 0.13
weight_lvar = 1.0 - weight_hvar 



import tensorflow as tf
import tensorflow.contrib.slim as slim

datasets_train_lvar = []
for fpath in files_train_lvar:
    print_time("Importing train data (low variance) from "+fpath, end="")
    corr2d, target_disparity, gt_ds = readTFRewcordsEpoch(fpath)
    datasets_train_lvar.append({"corr2d":corr2d,
                                "target_disparity":target_disparity,
                                "gt_ds":gt_ds})
    print_time("  Done")
datasets_train_hvar = []
for fpath in files_train_hvar:
    print_time("Importing train data (high variance) from "+fpath, end="")
    corr2d, target_disparity, gt_ds = readTFRewcordsEpoch(fpath)
    datasets_train_hvar.append({"corr2d":corr2d,
                                "target_disparity":target_disparity,
                                "gt_ds":gt_ds})
    print_time("  Done")
if (file_test_lvar):
    print_time("Importing test data (low variance) from "+fpath, end="")
    corr2d, target_disparity, gt_ds = readTFRewcordsEpoch(file_test_lvar)
    datasets_test_lvar = {"corr2d":corr2d,
                           "target_disparity":target_disparity,
                           "gt_ds":gt_ds}
    print_time("  Done")
if (file_test_hvar):
    print_time("Importing test data (high variance) from "+fpath, end="")
    corr2d, target_disparity, gt_ds = readTFRewcordsEpoch(file_test_hvar)
    datasets_test_hvar = {"corr2d":corr2d,
                           "target_disparity":target_disparity,
                           "gt_ds":gt_ds}
    print_time("  Done")
corr2d_train_placeholder =           tf.placeholder(datasets_train_lvar[0]['corr2d'].dtype,           (None,324)) # corr2d_train.shape)
target_disparity_train_placeholder = tf.placeholder(datasets_train_lvar[0]['target_disparity'].dtype, (None,1))  #target_disparity_train.shape)
gt_ds_train_placeholder =            tf.placeholder(datasets_train_lvar[0]['gt_ds'].dtype,            (None,2)) #gt_ds_train.shape)

dataset_tt = tf.data.Dataset.from_tensor_slices({
    "corr2d":corr2d_train_placeholder,
    "target_disparity": target_disparity_train_placeholder,
    "gt_ds": gt_ds_train_placeholder})


#dataset_train_size = len(corr2d_train)

dataset_train_size = len(datasets_train_lvar[0]['corr2d'])
dataset_train_size //= BATCH_SIZE
dataset_test_size = len(datasets_test_lvar['corr2d'])
dataset_test_size //= BATCH_SIZE

#print_time("dataset_tt.output_types "+str(dataset_train.output_types)+", dataset_train.output_shapes "+str(dataset_train.output_shapes)+", number of elements="+str(dataset_train_size))
dataset_tt = dataset_tt.batch(BATCH_SIZE)
206 207
dataset_tt = dataset_tt.prefetch(BATCH_SIZE)

Andrey Filippov's avatar
Andrey Filippov committed
208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528
iterator_tt = dataset_tt.make_initializable_iterator()
next_element_tt = iterator_tt.get_next()
#print("dataset_tt.output_types "+str(dataset_tt.output_types)+", dataset_tt.output_shapes "+str(dataset_tt.output_shapes)+", number of elements="+str(dataset_train_size))


"""
iterator_test =  dataset_test.make_initializable_iterator()
next_element_test =  iterator_test.get_next()
"""
#https://www.tensorflow.org/versions/r1.5/programmers_guide/datasets

result_dir = './attic/result_inmem50_'+     SUFFIX+'/'
checkpoint_dir = './attic/result_inmem5_'+ SUFFIX+'/'
save_freq = 500

def lrelu(x):
    return tf.maximum(x*0.2,x)
#    return tf.nn.relu(x)

def network_fc_simple(input, arch = 0):
    layouts = {0:[0,   0,   0,   32,  20,  16],
               1:[0,   0,   0,  256, 128,  64],
               2:[0, 128,  32,   32,  32,  16],
               3:[0,   0,  40,   32,  20,  16]}
    layout = layouts[arch]
    last_indx = None;
    fc = []
    for i, num_outs in enumerate (layout):
        if num_outs:
           if fc:
               inp = fc[-1]
           else:
               inp = input
           fc.append(slim.fully_connected(inp, num_outs, activation_fn=lrelu,scope='g_fc'+str(i)))    
    """
#  fc1  = slim.fully_connected(input, 256, activation_fn=lrelu,scope='g_fc1')
#  fc2  = slim.fully_connected(fc1,   128, activation_fn=lrelu,scope='g_fc2')
    fc3  =     slim.fully_connected(input, 256, activation_fn=lrelu,scope='g_fc3')
    fc4  =     slim.fully_connected(fc3,   128, activation_fn=lrelu,scope='g_fc4')
    fc5  =     slim.fully_connected(fc4,    64, activation_fn=lrelu,scope='g_fc5')
    """
###  fc3  =     slim.fully_connected(input,    32, activation_fn=lrelu,scope='g_fc3')
###  fc4  =     slim.fully_connected(fc3,    20, activation_fn=lrelu,scope='g_fc4')
###  fc5  =     slim.fully_connected(fc4,    16, activation_fn=lrelu,scope='g_fc5')
  
    if USE_CONFIDENCE:
        fc_out  = slim.fully_connected(fc[-1],     2, activation_fn=lrelu,scope='g_fc_out')
    else:     
        fc_out  = slim.fully_connected(fc[-1],     1, activation_fn=None,scope='g_fc_out')
        #If using residual disparity, split last layer into 2 or remove activation and add rectifier to confidence only  
    return fc_out

def batchLoss(out_batch,                   # [batch_size,(1..2)] tf_result
              target_disparity_batch,      # [batch_size]        tf placeholder
              gt_ds_batch,                 # [batch_size,2]      tf placeholder
              absolute_disparity =     True, #when false there should be no activation on disparity output ! 
              use_confidence =         True, 
              lambda_conf_avg =        0.01,
              lambda_conf_pwr =        0.1,
              conf_pwr =               2.0,
              gt_conf_offset =         0.08,
              gt_conf_pwr =            1.0,
              error2_offset =          0.0025, # (0.05^2)
              disp_wmin =              1.0,    # minimal disparity to apply weight boosting for small disparities
              disp_wmax =              8.0,    # maximal disparity to apply weight boosting for small disparities
              use_out =                False):  # use calculated disparity for disparity weight boosting (False - use target disparity)
               
    with tf.name_scope("BatchLoss"):
        """
        Here confidence should be after relU. Disparity - may be also if absolute, but no activation if output is residual disparity
        """
        tf_lambda_conf_avg = tf.constant(lambda_conf_avg, dtype=tf.float32, name="tf_lambda_conf_avg")
        tf_lambda_conf_pwr = tf.constant(lambda_conf_pwr, dtype=tf.float32, name="tf_lambda_conf_pwr")
        tf_conf_pwr =        tf.constant(conf_pwr,        dtype=tf.float32, name="tf_conf_pwr")
        tf_gt_conf_offset =  tf.constant(gt_conf_offset,  dtype=tf.float32, name="tf_gt_conf_offset")
        tf_gt_conf_pwr =     tf.constant(gt_conf_pwr,     dtype=tf.float32, name="tf_gt_conf_pwr")
        tf_num_tiles =       tf.shape(gt_ds_batch)[0]
        tf_0f =              tf.constant(0.0,             dtype=tf.float32, name="tf_0f")
        tf_1f =              tf.constant(1.0,             dtype=tf.float32, name="tf_1f")
        tf_maxw =            tf.constant(1.0,             dtype=tf.float32, name="tf_maxw")
        if gt_conf_pwr == 0:
            w = tf.ones((out_batch.shape[0]), dtype=tf.float32,name="w_ones")
        else:
    #        w_slice = tf.slice(gt_ds_batch,[0,1],[-1,1],              name = "w_gt_slice")
            w_slice = tf.reshape(gt_ds_batch[:,1],[-1],                     name = "w_gt_slice")
            
            w_sub =   tf.subtract      (w_slice, tf_gt_conf_offset,         name = "w_sub")
    #        w_clip =  tf.clip_by_value(w_sub, tf_0f,tf_maxw,              name = "w_clip")
            w_clip =  tf.maximum(w_sub, tf_0f,                              name = "w_clip")
            if gt_conf_pwr == 1.0:
                w = w_clip
            else:
                w=tf.pow(w_clip, tf_gt_conf_pwr, name = "w_pow")
    
        if use_confidence:
            tf_num_tilesf =      tf.cast(tf_num_tiles, dtype=tf.float32,     name="tf_num_tilesf")
    #        conf_slice =     tf.slice(out_batch,[0,1],[-1,1],                name = "conf_slice")
            conf_slice =     tf.reshape(out_batch[:,1],[-1],                 name = "conf_slice")
            conf_sum =       tf.reduce_sum(conf_slice,                       name = "conf_sum")
            conf_avg =       tf.divide(conf_sum, tf_num_tilesf,              name = "conf_avg")
            conf_avg1 =      tf.subtract(conf_avg, tf_1f,                    name = "conf_avg1")
            conf_avg2 =      tf.square(conf_avg1,                            name = "conf_avg2")
            cost2 =          tf.multiply (conf_avg2, tf_lambda_conf_avg,     name = "cost2")
    
            iconf_avg =      tf.divide(tf_1f, conf_avg,                      name = "iconf_avg")
            nconf =          tf.multiply (conf_slice, iconf_avg,             name = "nconf") #normalized confidence
            nconf_pwr =      tf.pow(nconf, conf_pwr,                         name = "nconf_pwr")
            nconf_pwr_sum =  tf.reduce_sum(nconf_pwr,                        name = "nconf_pwr_sum")
            nconf_pwr_offs = tf.subtract(nconf_pwr_sum, tf_1f,               name = "nconf_pwr_offs")
            cost3 =          tf.multiply (conf_avg2, nconf_pwr_offs,         name = "cost3")
            w_all =          tf.multiply (w, nconf,                          name = "w_all")
        else:
            w_all = w
#            cost2 = 0.0
#            cost3 = 0.0    
        # normalize weights
        w_sum =              tf.reduce_sum(w_all,                            name = "w_sum")
        iw_sum =             tf.divide(tf_1f, w_sum,                         name = "iw_sum")
        w_norm =             tf.multiply (w_all, iw_sum,                     name = "w_norm")
        
    #    disp_slice =         tf.slice(out_batch,[0,0],[-1,1],                name = "disp_slice")
    #    d_gt_slice =         tf.slice(gt_ds_batch,[0,0],[-1,1],              name = "d_gt_slice")
        disp_slice =         tf.reshape(out_batch[:,0],[-1],                 name = "disp_slice")
        d_gt_slice =         tf.reshape(gt_ds_batch[:,0],[-1],               name = "d_gt_slice")
        
        """
        if absolute_disparity:
            out_diff =       tf.subtract(disp_slice, d_gt_slice,             name = "out_diff")
        else:
            td_flat =        tf.reshape(target_disparity_batch,[-1],         name = "td_flat")
            residual_disp =  tf.subtract(d_gt_slice, td_flat,                name = "residual_disp")
            out_diff =       tf.subtract(disp_slice, residual_disp,          name = "out_diff")
        """    
        td_flat =        tf.reshape(target_disparity_batch,[-1],         name = "td_flat")
        if absolute_disparity:
            adisp =          disp_slice
        else:
#            td_flat =        tf.reshape(target_disparity_batch,[-1],         name = "td_flat")
            adisp =          tf.add(disp_slice, td_flat,                     name = "adisp")
        out_diff =           tf.subtract(adisp, d_gt_slice,                  name = "out_diff")
            
            
        out_diff2 =          tf.square(out_diff,                             name = "out_diff2")
        out_wdiff2 =         tf.multiply (out_diff2, w_norm,                 name = "out_wdiff2")
        
        cost1 =              tf.reduce_sum(out_wdiff2,                       name = "cost1")
        
        out_diff2_offset =   tf.subtract(out_diff2, error2_offset,           name = "out_diff2_offset")
        out_diff2_biased =   tf.maximum(out_diff2_offset, 0.0,               name = "out_diff2_biased")
        
        # calculate disparity-based weight boost
        if use_out:
            dispw =          tf.clip_by_value(adisp, disp_wmin, disp_wmax,   name = "dispw")
        else:
            dispw =          tf.clip_by_value(td_flat, disp_wmin, disp_wmax, name = "dispw")
        dispw_boost =        tf.divide(disp_wmax, dispw,                     name = "dispw_boost")
        dispw_comp =         tf.multiply (dispw_boost, w_norm,               name = "dispw_comp")
        dispw_sum =          tf.reduce_sum(dispw_comp,                       name = "dispw_sum")
        idispw_sum =         tf.divide(tf_1f, dispw_sum,                     name = "idispw_sum")
        dispw_norm =         tf.multiply (dispw_comp, idispw_sum,            name = "dispw_norm")
        
        out_diff2_wbiased =  tf.multiply(out_diff2_biased, dispw_norm,       name = "out_diff2_wbiased")
#        out_diff2_wbiased =  tf.multiply(out_diff2_biased, w_norm,       name = "out_diff2_wbiased")
        cost1b =             tf.reduce_sum(out_diff2_wbiased,                name = "cost1b")
        
        if use_confidence:
            cost12 =         tf.add(cost1b, cost2,                           name = "cost12")
            cost123 =        tf.add(cost12, cost3,                           name = "cost123")    
            
            return cost123, disp_slice, d_gt_slice, out_diff,out_diff2, w_norm, out_wdiff2, cost1
        else:
            return cost1b,  disp_slice, d_gt_slice, out_diff,out_diff2, w_norm, out_wdiff2, cost1
    

#corr2d325 = tf.concat([corr2d,target_disparity],0)
#corr2d325 = tf.concat([next_element_tt['corr2d'],tf.reshape(next_element_tt['target_disparity'],(-1,1))],1)
corr2d325 = tf.concat([next_element_tt['corr2d'], next_element_tt['target_disparity']],1)
#next_element_tt

#    in_features = tf.concat([corr2d,target_disparity],0)

out =       network_fc_simple(input=corr2d325, arch = NET_ARCH)
#Try standard loss functions first
G_loss, _disp_slice, _d_gt_slice, _out_diff, _out_diff2, _w_norm, _out_wdiff2, _cost1 = batchLoss(out_batch =         out,        # [batch_size,(1..2)] tf_result
              target_disparity_batch=  next_element_tt['target_disparity'], # target_disparity, ### target_d,   # [batch_size]        tf placeholder
              gt_ds_batch =            next_element_tt['gt_ds'], # gt_ds, ### gt,         # [batch_size,2]      tf placeholder
              absolute_disparity =     ABSOLUTE_DISPARITY,
              use_confidence =         USE_CONFIDENCE, # True, 
              lambda_conf_avg =        0.01,
              lambda_conf_pwr =        0.1,
              conf_pwr =               2.0,
              gt_conf_offset =         0.08,
              gt_conf_pwr =            2.0,
              error2_offset =          0.0025, # (0.05^2)
              disp_wmin =              1.0,    # minimal disparity to apply weight boosting for small disparities
              disp_wmax =              8.0,    # maximal disparity to apply weight boosting for small disparities
              use_out =                False)  # use calculated disparity for disparity weight boosting (False - use target disparity)
              
tf_ph_G_loss = tf.placeholder(tf.float32,shape=None,name='G_loss_avg')
tf_ph_sq_diff = tf.placeholder(tf.float32,shape=None,name='sq_diff_avg')
with tf.name_scope('sample'):
    tf.summary.scalar("G_loss",G_loss)
    tf.summary.scalar("sq_diff",_cost1)
with tf.name_scope('epoch_average'):
    tf.summary.scalar("G_loss_epoch",tf_ph_G_loss)
    tf.summary.scalar("sq_diff_epoch",tf_ph_sq_diff)

t_vars=tf.trainable_variables()
lr=tf.placeholder(tf.float32)
G_opt=tf.train.AdamOptimizer(learning_rate=lr).minimize(G_loss)

saver=tf.train.Saver()

ROOT_PATH  = './attic/nn_ds_inmem50_graph'+SUFFIX+"/"
TRAIN_PATH = ROOT_PATH + 'train'
TEST_PATH  = ROOT_PATH + 'test'

# CLEAN OLD STAFF
shutil.rmtree(TRAIN_PATH, ignore_errors=True)
shutil.rmtree(TEST_PATH, ignore_errors=True)

with tf.Session()  as sess:
    
    sess.run(tf.global_variables_initializer())
    sess.run(tf.local_variables_initializer())
    
    merged = tf.summary.merge_all()
    train_writer = tf.summary.FileWriter(TRAIN_PATH, sess.graph)
    test_writer  = tf.summary.FileWriter(TEST_PATH, sess.graph)
    loss_train_hist= np.empty(dataset_train_size, dtype=np.float32)
    loss_test_hist=  np.empty(dataset_test_size, dtype=np.float32)
    loss2_train_hist= np.empty(dataset_train_size, dtype=np.float32)
    loss2_test_hist=  np.empty(dataset_test_size, dtype=np.float32)
    train_avg = 0.0     
    train2_avg = 0.0
    test_avg = 0.0     
    test2_avg = 0.0
    num_train_variants = len(files_train_lvar)
    for epoch in range (EPOCHS_TO_RUN):
#        file_index = (epoch // 20) % 2 
        file_index = epoch  % num_train_variants 
    #       if SHUFFLE_EPOCH:
    #        dataset_tt = dataset_tt.shuffle(buffer_size=10000)
        sess.run(iterator_tt.initializer, feed_dict={corr2d_train_placeholder:           datasets_train_lvar[file_index]['corr2d'],
                                                        target_disparity_train_placeholder: datasets_train_lvar[file_index]['target_disparity'],
                                                        gt_ds_train_placeholder:            datasets_train_lvar[file_index]['gt_ds']})
        for i in range(dataset_train_size):
            try:
                train_summary,_, G_loss_trained,  output, disp_slice, d_gt_slice, out_diff, out_diff2, w_norm, out_wdiff2, out_cost1, corr2d325_out  = sess.run(
                    [   merged,
                        G_opt,
                        G_loss,
                        out,
                        _disp_slice,
                        _d_gt_slice,
                        _out_diff,
                        _out_diff2,
                        _w_norm,
                        _out_wdiff2,
                        _cost1,
                        corr2d325,
                    ],
                    feed_dict={lr:LR,tf_ph_G_loss:train_avg, tf_ph_sq_diff:train2_avg}) # pfrevious value of *_avg
                
                # save all for now as a test
                #train_writer.add_summary(summary, i)
                #train_writer.add_summary(train_summary, i)
                loss_train_hist[i] =  G_loss_trained
                loss2_train_hist[i] = out_cost1
            except tf.errors.OutOfRangeError:
                print("train done at step %d"%(i))
                break
        train_avg = np.average(loss_train_hist).astype(np.float32)     
        train2_avg = np.average(loss2_train_hist).astype(np.float32)
#        _,_=sess.run([tf_ph_G_loss,tf_ph_sq_diff],feed_dict={tf_ph_G_loss:train_avg, tf_ph_sq_diff:train2_avg})
#tf_ph_G_loss = tf.placeholder(tf.float32,shape=None,name='G_loss_avg')
#tf_ph_sq_diff = tf.placeholder(tf.float32,shape=None,name='sq_diff_avg')
        sess.run(iterator_tt.initializer, feed_dict={corr2d_train_placeholder:   datasets_test_lvar['corr2d'],
                                                target_disparity_train_placeholder: datasets_test_lvar['target_disparity'],
                                                gt_ds_train_placeholder:            datasets_test_lvar['gt_ds']})

        for i in range(dataset_test_size):
            try:
                test_summary, G_loss_tested, output, disp_slice, d_gt_slice, out_diff, out_diff2, w_norm, out_wdiff2, out_cost1, corr2d325_out = sess.run(
                    [merged,
                     G_loss,
                     out,
                     _disp_slice,
                     _d_gt_slice,
                     _out_diff,
                     _out_diff2,
                     _w_norm,
                     _out_wdiff2,
                     _cost1,
                     corr2d325,
                     ],
                        feed_dict={lr:LR,tf_ph_G_loss:test_avg, tf_ph_sq_diff:test2_avg})  # pfrevious value of *_avg
                loss_test_hist[i] =  G_loss_tested
                loss2_test_hist[i] = out_cost1
            except tf.errors.OutOfRangeError:
                print("test done at step %d"%(i))
                break
            
#            print_time("%d:%d -> %f"%(epoch,i,G_current))
        test_avg =  np.average(loss_test_hist).astype(np.float32)     
        test2_avg = np.average(loss2_test_hist).astype(np.float32)
             
#        _,_=sess.run([tf_ph_G_loss,tf_ph_sq_diff],feed_dict={tf_ph_G_loss:test_avg, tf_ph_sq_diff:test2_avg})
        
        train_writer.add_summary(train_summary, epoch)
        test_writer.add_summary(test_summary, epoch)
        
        print_time("%d:%d -> %f %f (%f %f)"%(epoch,i,train_avg, test_avg,train2_avg, test2_avg))
     
     # Close writers
    train_writer.close()
    test_writer.close()
#reports error: Exception ignored in: <bound method BaseSession.__del__ of <tensorflow.python.client.session.Session object at 0x7efc5f720ef0>> if there is no print before exit()

print("All done")
exit (0)