wit543

I also have the same problem but solved it by adding '-std=gnu++11' flag in Makefile. ``` output: v380.o UtlSocket.o UtlDiscovery.o aes.o g++ v380.o UtlSocket.o UtlDiscovery.o aes.o -o v380 v380.o: v380.cpp...

I was successful using this command ``` python run.py --mode=train_then_eval --train_mode=finetune \ --fine_tune_after_block=4 --zero_init_logits_layer=True \ --global_bn=False --optimizer=momentum --learning_rate=0.1 --weight_decay=0.0 \ --train_epochs=100 --train_batch_size=63 --warmup_epochs=0 \ --dataset=imagenet --image_size=224 --eval_split=test --resnet_depth=152 \ --checkpoint=pretrianed_model/r152_1x_sk0/saved_model...