zsdonghao / u-net-brain-tumor

U-Net Brain Tumor Segmentation

https://github.com/zsdonghao/tensorlayer

499 stars 180 forks source link

when using u_net_bn in model,i get the error #36

Open zmmzzz opened 5 years ago

zmmzzz commented 5 years ago

when using u_net_bn in model,i get the error "train_op = tf.train.AdamOptimizer(lr_v, beta1=beta1).minimize(loss, var_list=t_vars)",and "ValueError: No variables to optimize",what's the reason,how can i figure out ?

zsdonghao commented 5 years ago

please report your TF, TL and python versions.

zmmzzz commented 5 years ago

what i am using now is: TF=1.6 TL=1.7 python=3.5 i had run this code ,but the system error occured: failed call to cuInit: CUDA_ERROR_UNKNOWN ,retrieving CUDA diagnostic information for host: amax.
while the TITAN X was already installed

if convenient,it's very appreciate to tell me what's the suitabe version. i have another doubt,to compare the result of different models, can i add a new model to the file"model.py",without changing other codes in the file"train.py"?

zmmzzz commented 5 years ago

the version i am using is: CUDA: 9.0.176 CUDNN:#define CUDNN_MAJOR 7

define CUDNN_MINOR 0

define CUDNN_PATCHLEVEL 5

define CUDNN_VERSION (CUDNN_MAJOR 1000 + CUDNN_MINOR 100 + CUDNN_PATCHLEVEL)