Created
April 19, 2018 05:47
-
-
Save guoxiaolu/7e9a31138a9da9e9c1da3d5aff56e4b9 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
curl -o 1234.jpg --insecure https://encrypted-tbn0.gstatic.com/images\?q\=tbn:ANd9GcRInmM91ktXEFNjponNkRx9VUp8Xx9REIIsfZoGvZlt6ohBSLP7DQ --socks5-hostname 127.0.0.1:1080 | |
bazel build -c opt --copt=-msse4.1 --copt=-msse4.2 tensorflow/contrib/lite/toco:toco | |
bazel run --config=opt --copt=-msse4.1 --copt=-msse4.2 \ | |
//tensorflow/contrib/lite/toco:toco -- \ | |
--input_file=/Users/Lavector/code/keras_to_tensorflow/mobilenet_regression.pb \ | |
--output_file=/Users/Lavector/mobilenet_regression.lite \ | |
--input_format=TENSORFLOW_GRAPHDEF \ | |
--output_format=TFLITE \ | |
--inference_type=FLOAT \ | |
--input_shape=1,224,224,3 \ | |
--input_array=input \ | |
--output_array=output_node0 | |
bazel run --config=opt --copt=-msse4.1 --copt=-msse4.2 //tensorflow/contrib/lite/toco:toco -- --input_file=/tmp/mobilenet_v1_0.50_128/frozen_graph.pb --output_file=/tmp/foo.lite --input_format=TENSORFLOW_GRAPHDEF --output_format=TFLITE --inference_type=FLOAT --input_shape=1,128,128,3 --input_array=input --output_array=MobilenetV1/Predictions/Reshape_1 | |
bazel run --config=opt --copt=-msse4.1 --copt=-msse4.2 //tensorflow/contrib/lite/toco:toco -- --input_file=/Users/Lavector/code/keras_to_tensorflow/mobilenet_regression.pb --output_file=/tmp/mobilenet_regression.lite --input_format=TENSORFLOW_GRAPHDEF --output_format=TFLITE --inference_type=FLOAT --input_shape=1,224,224,3 --input_array=input --output_array=output_node0 | |
bazel-bin/tensorflow/contrib/lite/toco/toco -- \ | |
--input_file=/Users/Lavector/Downloads/mobilenet_v1_1.0_224/frozen_graph.pb \ | |
--input_format=TENSORFLOW_GRAPHDEF --output_format=TFLITE \ | |
--output_file=/tmp/mobilenet_v1_1.0_224.lite --inference_type=FLOAT \ | |
--input_type=FLOAT --input_arrays=input \ | |
--output_arrays=MobilenetV1/Predictions/Reshape_1 --input_shapes=1,224,224,3 | |
bazel build -c opt --copt=-msse4.1 --copt=-msse4.2 tensorflow/python/tools:optimize_for_inference && \ | |
bazel-bin/tensorflow/python/tools/optimize_for_inference \ | |
--input_graph=/Users/Lavector/code/keras_to_tensorflow/mobilenet_regression.pb \ | |
--output_graph=/tmp/optimized_graph.pb \ | |
--input_names=input_1 \ | |
--output_names=output_node0 | |
elasticsearch-dump | |
1. 将一个EleasticSearch 集群的索引,导入到另一个EleasticSearch集群中 | |
elasticsearch-dump/bin/elasticdump --input=http://es_cluster1:9200/index1 --output=http://es_cluster2:9200/index2 --limit=10000 --type=data | |
2. 将索引导出为文本文件 | |
elasticdump --input=http://es_cluster1:9200/index --output=fliename --type=data | |
3. 将文本文件导入到索引中 | |
elasticdump --input kafka.duowan.flowsize.batchinfo --output=http://192.168.100.3:9200/kafka.duowan.flowsize.batchinfo |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment