constants gpu1 change

answer_classifier_cached_features/train.py

@@ -418,7 +418,7 @@ class graph_creator():
 
                 self.mil_atr_loss += losses.mil_loss(
                     self.attribute_scores_with_answers[j],
-                    self.plh['positive_attributes_vec_enc'][j],
+                    self.plh['positive_adjectives_vec_enc'][j],
                     'atr')
 
             self.mil_obj_loss = self.mil_loss_wt*self.mil_obj_loss / self.batch_size
@@ -690,7 +690,8 @@ class attach_optimizer():
             self.learning_rate = tf.train.exponential_decay(
                 self.lr, 
                 self.global_step,
-                self.decay_step)
+                self.decay_step,
+                self.decay_rate)
             
             self.optimizer = multi_rate_train.MultiRateOptimizer(
                 tf.train.AdamOptimizer)

constants_vision_gpu_1.py

@@ -5,7 +5,7 @@ def mkdir_if_not_exists(dir_name):
     if not os.path.exists(dir_name):
         os.mkdir(dir_name)
         
-experiment_name = 'QA_pretrain_genome_split'
+experiment_name = 'obj_atr_through_ans_mil'
 #experiment_name = 'object_attribute_classifier_large_images'
 # Global output directory (all subexperiments will be saved here)
 global_output_dir = '/data/tanmay/GenVQA_Exp_Results'
@@ -100,11 +100,10 @@ pretrained_vocab_word_vectors_npy = os.path.join(
 
 # Object Attribute Classifier Training Params
 region_batch_size = 200
-# region_num_samples = num_train_regions
-region_num_epochs = 4
+region_num_epochs = 20
 region_offset = 0
 region_queue_size = 400
-region_regularization_coeff = 1e-4
+region_regularization_coeff = 1e-5
 region_lr = 1e-3
 region_log_every_n_iter = 500
 region_output_dir = os.path.join(
@@ -180,15 +179,18 @@ vqa_answer_vocab_json = os.path.join(
 # num_test_questions = 0
 
 # Answer classifier training params
-answer_batch_size = 50
-answer_num_epochs = 10
+answer_batch_size = 25
+answer_num_epochs = 20
 answer_offset = 0
-answer_obj_atr_loss_wt = 0.0
+answer_obj_atr_loss_wt = 1.0
+answer_ans_loss_wt = 0.1
+answer_mil_loss_wt = 0.2
 answer_regularization_coeff = 1e-5
 answer_queue_size = 500
 answer_embedding_dim = 600
 answer_lr = 1e-3
 answer_log_every_n_iter = 500
+answer_train_from_scratch = True
 answer_output_dir = os.path.join(
     global_experiment_dir,
     'answer_classifiers')