Trying next versions with partial second stage - 5x5+3x3+1x1

explore_data2.py

@@ -1030,7 +1030,7 @@ if __name__ == "__main__":
   
   ml_list_train=ex_data.getMLList(ml_subdir, ex_data.files_train)
   ml_list_test= ex_data.getMLList(ml_subdir, ex_data.files_test)
-  num_test_scenes = [ex_data.files_test, ex_data.files_train][TEST_SAME_LENGTH_AS_TRAIN]    
+  num_test_scenes = len([ex_data.files_test, ex_data.files_train][TEST_SAME_LENGTH_AS_TRAIN])    
           
 
   if RADIUS == 0 :

nn_ds_neibs9.py

@@ -58,13 +58,13 @@ SHUFFLE_EPOCH =    True
 NET_ARCH1 =       0 # 4 # #4 # 8 # 4 # 0 #3 # 0 #  0 # 0 # 0 # 8 # 0 # 7 # 2 #0 # 6 #0 # 4 # 3 # overwrite with argv?
 NET_ARCH2 =       0 # 4 # 0 # 0 # 4 # 0 # 0 # 3 #  0 # 3 # 0 # 3 # 0 # 2 #0 # 6 # 0 # 3 # overwrite with argv?
 SYM8_SUB =        False # True #False #  True # False # True # False # True # False # enforce inputs from 2d correlation have symmetrical ones (groups of 8)
-ONLY_TILE =        None # 4 # None # 0 # 4# None # (remove all but center tile data), put None here for normal operation)
+ONLY_TILE =        12 # None # 4 # None # 0 # 4# None # (remove all but center tile data), put None here for normal operation)
 ZIP_LHVAR =        True # combine _lvar and _hvar as odd/even elements 
 #DEBUG_PACK_TILES = True
 # CLUSTER_RADIUS should match input data
 CLUSTER_RADIUS =     2 # 1 # 1 - 3x3, 2 - 5x5 tiles
 SHUFFLE_FILES  =     True
-WLOSS_LAMBDA =       0.0 # 50.0 # 5.0 # 1.0 # fraction of the W_loss (input layers weight non-uniformity) added to G_loss
+WLOSS_LAMBDA =       2.0 #3.0 # 1.0 # 0.3 # 0.0 # 50.0 # 5.0 # 1.0 # fraction of the W_loss (input layers weight non-uniformity) added to G_loss
 WBORDERS_ZERO =      True # Border conditions for first layer weights: False - free, True - tied to 0
 MAX_FILES_PER_GROUP = 6 # just to try, normally should be 8
 FILE_UPDATE_EPOCHS =  2 # update train files each this many epochs. 0 - do not update
@@ -439,7 +439,8 @@ dir_train_hvar =  data_dir # "/home/eyesis/x3d_data/data_sets/tf_data_5x5_main"
 dir_train_lvar1 = data_dir1 #"/home/eyesis/x3d_data/data_sets/tf_data_5x5_main_1" # data_dir # "/home/eyesis/x3d_data/data_sets/tf_data_5x5_main"
 dir_train_hvar1 = data_dir1 # "/home/eyesis/x3d_data/data_sets/tf_data_5x5_main"
 dir_test_lvar =   data_dir # data_dir #"/home/eyesis/x3d_data/data_sets/tf_data_5x5_center/" # data_dir # "/home/eyesis/x3d_data/data_sets/tf_data_5x5_main"
-dir_test_hvar =   "/home/eyesis/x3d_data/data_sets/tf_data_5x5_main_3" # data_dir #"/home/eyesis/x3d_data/data_sets/tf_data_5x5_center" #  data_dir # "/home/eyesis/x3d_data/data_sets/tf_data_5x5_main"
+#dir_test_hvar =   "/home/eyesis/x3d_data/data_sets/tf_data_5x5_main_3" # data_dir #"/home/eyesis/x3d_data/data_sets/tf_data_5x5_center" #  data_dir # "/home/eyesis/x3d_data/data_sets/tf_data_5x5_main"
+dir_test_hvar =   "/home/eyesis/x3d_data/data_sets/tf_data_5x5_main_5" # data_dir #"/home/eyesis/x3d_data/data_sets/tf_data_5x5_center" #  data_dir # "/home/eyesis/x3d_data/data_sets/tf_data_5x5_main"
 dir_img =         os.path.join(img_dir,"img") # "/home/eyesis/x3d_data/data_sets/tf_data_5x5_main/img"
 dir_result =      os.path.join(data_dir,"result") # "/home/eyesis/x3d_data/data_sets/tf_data_5x5_main/result"
 
@@ -574,7 +575,7 @@ Compare with other (not used) train sets (use 7 of each instead of 8, 8-th as te
 #just testing:
 #files_train_lvar = files_train_hvar
 files_test_lvar =  ["train004_R2_GT_1.5.tfrecords"]# ["train007_R2_LE_1.5.tfrecords"]# "testTEST_R2_LE_1.5.tfrecords"] # testTEST_R2_LE_1.5.tfrecords"]
-files_test_hvar =  ["train000_R2_GT_1.5.tfrecords"]#"testTEST_R2_GT_1.5.tfrecords"] # "testTEST_R2_GT_1.5.tfrecords"]
+files_test_hvar =  ["testTEST_R2_GT_1.5.tfrecords"] # Now same size as train! # ["train000_R2_GT_1.5.tfrecords"]#"testTEST_R2_GT_1.5.tfrecords"] # "testTEST_R2_GT_1.5.tfrecords"]
 #files_img =        ['1527257933_150165-v04'] # overlook
 #files_img =        ['1527256858_150165-v01'] # State Street
 #files_img =        ['1527256816_150165-v02'] # State Street
@@ -1067,7 +1068,7 @@ def weightsLoss(inp_weights):       # [batch_size,(1..2)] tf_result
         tf_inp =     tf.reshape(inp_weights[:TILE_LAYERS * TILE_SIZE,:], [TILE_LAYERS, FILE_TILE_SIDE, FILE_TILE_SIDE, inp_weights.shape[1]], name = "tf_inp")
         if WBORDERS_ZERO:
             tf_zero_col = tf.constant(0.0, dtype=tf.float32, shape=[tf_inp.shape[0], tf_inp.shape[1], 1,                   tf_inp.shape[3]], name = "tf_zero_col")
-            tf_zero_row = tf.constant(0.0, dtype=tf.float32, shape=[tf_inp.shape[0], 1 ,              tf_inp.shape[2], tf_inp.shape[3]], name = "tf_zero_row")
+            tf_zero_row = tf.constant(0.0, dtype=tf.float32, shape=[tf_inp.shape[0], 1 ,              tf_inp.shape[2] + 2, tf_inp.shape[3]], name = "tf_zero_row")
             tf_inp_ext_h = tf.concat([tf_zero_col,                 tf_inp,       tf_zero_col                 ], axis = 2, name ="tf_inp_ext_h")
             tf_inp_ext   = tf.concat([tf_zero_row,                 tf_inp_ext_h, tf_zero_row                 ], axis = 1, name ="tf_inp_ext")
         else: