faceAlignment_tensorflow
faceAlignment_tensorflow copied to clipboard
按照这个DAN的代码,跑出来的测试效果不好,误差为0.9?
('valid num ', 554) 2019-07-08 21:45:57.680160: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2019-07-08 21:45:57.900107: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1411] Found device 0 with properties: name: GeForce GTX 1080 Ti major: 6 minor: 1 memoryClockRate(GHz): 1.582 pciBusID: 0000:85:00.0 totalMemory: 10.92GiB freeMemory: 10.76GiB 2019-07-08 21:45:57.900156: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1490] Adding visible gpu devices: 5 2019-07-08 21:45:58.257631: I tensorflow/core/common_runtime/gpu/gpu_device.cc:971] Device interconnect StreamExecutor with strength 1 edge matrix: 2019-07-08 21:45:58.257683: I tensorflow/core/common_runtime/gpu/gpu_device.cc:977] 5 2019-07-08 21:45:58.257694: I tensorflow/core/common_runtime/gpu/gpu_device.cc:990] 5: N 2019-07-08 21:45:58.258003: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1103] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4471 MB memory) -> physical GPU (device: 5, name: GeForce GTX 1080 Ti, pci bus id: 0000:85:00.0, compute capability: 6.1) Pre-trained model has been loaded! The overall mean error is: 94.49 ('valid num ', 135) 2019-07-08 21:46:06.834196: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1490] Adding visible gpu devices: 5 2019-07-08 21:46:06.834259: I tensorflow/core/common_runtime/gpu/gpu_device.cc:971] Device interconnect StreamExecutor with strength 1 edge matrix: 2019-07-08 21:46:06.834269: I tensorflow/core/common_runtime/gpu/gpu_device.cc:977] 5 2019-07-08 21:46:06.834277: I tensorflow/core/common_runtime/gpu/gpu_device.cc:990] 5: N 2019-07-08 21:46:06.834696: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1103] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4471 MB memory) -> physical GPU (device: 5, name: GeForce GTX 1080 Ti, pci bus id: 0000:85:00.0, compute capability: 6.1) Pre-trained model has been loaded! The overall mean error is: 80.05