enas
enas copied to clipboard
TensorFlow Code for paper "Efficient Neural Architecture Search via Parameter Sharing"
Process finished with exit code -1073741571 (0xC00000FD)
Hello, have anyone known how to use the well-trained model to do some inference? I directly use tf.train.import_meta_graph and saver.restore to load the model and use the sess.run to the...
how use the output of ENAS ? is it a neural architecture, if yes, how get the name of operations and activations functions ?
Hi, I'm running the cifar10_macro_search.sh file and it seems that everything is fine because the training process goes well until the end, there in the last epcoh I get :...
Hi, I tried to run the ENAS project and I am blocked by this error : File "/enas-add-license-1/enas-add-license-1/src/cifar10/micro_child.py", line 258, in _model raise ValueError("Unknown data_format '{0}'".format(self.data_format)) ValueError: Unknown data_format 'NHWC'...
@melodyguan @hyhieu , Is there a `requirements.py` file I can use so that I can run this code? If there isn't one, how can I run this code in a...
While running the "cifar10_macro_search.sh" script, I get the following error. Is it related to the tensorflow version? I am using 1.6.0. ================ Build train graph Tensor("child/layer_0/case/cond/Merge:0", shape=(?, 36, 32, 32),...
I am getting the following error after running the script cfar10_macro_search. sh: Starting session 2018-10-10 19:20:31.254266: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are...
HI Guys: when tring to run cifar10_micro_search, I always met the below error, I tried to switch to official tensorflow docker image, which should contain all op support, but it...
The following is the print information I executed the command "./scripts/cifar10_macro_search.sh" (progress was killed): ```python jovyan@219394b7f111$ ./scripts/cifar10_macro_search.sh -------------------------------------------------------------------------------- Path outputs exists. Remove and remake. -------------------------------------------------------------------------------- Logging to outputs/stdout -------------------------------------------------------------------------------- batch_size...................................................................128...