Jerry Li
Jerry Li
It isn't always true that GMACs = 2 * GFLOPs. For example, two models with the same the GMACS, may have very difference GFLOPS. It depends how you implement model...
When you run_train.sh first time, ez will automatically download model to modelZooBasePath. Pleas check your os.getenv("HOME") / eztransfer_modelzoo. flags.DEFINE_string("modelZooBasePath", default=os.path.join(os.getenv("HOME"), ".eztransfer_modelzoo"), help="eztransfer_modelzoo")
You can conduct two experiments to compare the two pretrained models.
下个版本发布的时候会修复
metoo啊！