Fix pai examples (#1996)

docs/en_US/TrainingService/PaiMode.md

@@ -37,6 +37,7 @@ trial:
   virtualCluster: default
   nniManagerNFSMountPath: /home/user/mnt
   containerNFSMountPath: /mnt/data/user
+  paiStoragePlugin: team_wise
 # Configuration to access OpenPAI Cluster
 paiConfig:
   userName: your_pai_nni_user

docs/en_US/TrainingService/PaiYarnMode.md

@@ -6,7 +6,7 @@ The original `pai` mode is modificated to `paiYarn` mode, which is a distributed
 Install NNI, follow the install guide [here](../Tutorial/QuickStart.md).
 
 ## Run an experiment
-Use `examples/trials/mnist-annotation` as an example. The NNI config YAML file's content is like:
+Use `examples/trials/mnist-tfv1` as an example. The NNI config YAML file's content is like:
 
 ```yaml
 authorName: your_name
@@ -22,14 +22,14 @@ trainingServicePlatform: paiYarn
 # search space file
 searchSpacePath: search_space.json
 # choice: true, false
-useAnnotation: true
+useAnnotation: false
 tuner:
   builtinTunerName: TPE
   classArgs:
     optimize_mode: maximize
 trial:
   command: python3 mnist.py
-  codeDir: ~/nni/examples/trials/mnist-annotation
+  codeDir: ~/nni/examples/trials/mnist-tfv1
   gpuNum: 0
   cpuNum: 1
   memoryMB: 8196

examples/trials/auto-gbdt/config_pai.yml

@@ -23,10 +23,13 @@ trial:
   memoryMB: 8196
   #The docker image to run nni job on pai
   image: msranni/nni:latest
+  nniManagerNFSMountPath: /home/user/mnt
+  containerNFSMountPath: /mnt/data/user
+  paiStoragePlugin: team_wise
 paiConfig:
   #The username to login pai
   userName: username
-  #The password to login pai
-  passWord: password
+  #The token to login pai
+  token: token
   #The host of restful server of pai
   host: 10.10.10.10
\ No newline at end of file

examples/trials/auto-gbdt/config_paiYarn.yml

+authorName: default
+experimentName: example_auto-gbdt
+trialConcurrency: 1
+maxExecDuration: 10h
+maxTrialNum: 10
+#choice: local, remote, pai
+trainingServicePlatform: paiYarn
+searchSpacePath: search_space.json
+#choice: true, false
+useAnnotation: false
+tuner:
+  #choice: TPE, Random, Anneal, Evolution, BatchTuner, MetisTuner, GPTuner
+  #SMAC (SMAC should be installed through nnictl)
+  builtinTunerName: TPE
+  classArgs:
+    #choice: maximize, minimize
+    optimize_mode: minimize
+trial:
+  command: python3 main.py
+  codeDir: .
+  gpuNum: 0
+  cpuNum: 1
+  memoryMB: 8196
+  #The docker image to run nni job on pai
+  image: msranni/nni:latest
+paiYarnConfig:
+  #The username to login pai
+  userName: username
+  #The password to login pai
+  passWord: password
+  #The host of restful server of pai
+  host: 10.10.10.10
\ No newline at end of file

examples/trials/cifar10_pytorch/config_pai.yml

@@ -23,10 +23,13 @@ trial:
   memoryMB: 8196
   #The docker image to run nni job on pai
   image: msranni/nni:latest
+  nniManagerNFSMountPath: /home/user/mnt
+  containerNFSMountPath: /mnt/data/user
+  paiStoragePlugin: team_wise
 paiConfig:
   #The username to login pai
   userName: username
-  #The password to login pai
-  passWord: password
+  #The token to login pai
+  token: token
   #The host of restful server of pai
   host: 10.10.10.10

examples/trials/cifar10_pytorch/config_paiYarn.yml

+authorName: default
+experimentName: example_pytorch_cifar10
+trialConcurrency: 1
+maxExecDuration: 100h
+maxTrialNum: 10
+#choice: local, remote, pai
+trainingServicePlatform: paiYarn
+searchSpacePath: search_space.json
+#choice: true, false
+useAnnotation: false
+tuner:
+  #choice: TPE, Random, Anneal, Evolution, BatchTuner, MetisTuner
+  #SMAC (SMAC should be installed through nnictl)
+  builtinTunerName: TPE
+  classArgs:
+    #choice: maximize, minimize
+    optimize_mode: maximize
+trial:
+  command: python3 main.py
+  codeDir: .
+  gpuNum: 1
+  cpuNum: 1
+  memoryMB: 8196
+  #The docker image to run nni job on pai
+  image: msranni/nni:latest
+paiYarnConfig:
+  #The username to login pai
+  userName: username
+  #The password to login pai
+  passWord: password
+  #The host of restful server of pai
+  host: 10.10.10.10

examples/trials/efficientnet/config_pai.yml

@@ -21,8 +21,11 @@ trial:
   gpuNum: 1
   virtualCluster: nni
   image: msranni/nni:latest
+  nniManagerNFSMountPath: /home/user/mnt
+  containerNFSMountPath: /mnt/data/user
+  paiStoragePlugin: team_wise
 nniManagerIp: <nni_manager_ip>
 paiConfig:
   userName: <username>
-  passWord: <password>
+  token: <token>
   host: <host>

examples/trials/efficientnet/config_paiYarn.yml

+authorName: unknown
+experimentName: example_efficient_net
+trialConcurrency: 8
+maxExecDuration: 48h
+maxTrialNum: 100
+trainingServicePlatform: paiYarn
+searchSpacePath: search_net.json
+useAnnotation: false
+tuner:
+  codeDir: .
+  classFileName: tuner.py
+  className: FixedProductTuner
+  classArgs:
+    product: 2
+trial:
+  codeDir: EfficientNet-PyTorch
+  command: sh train_imagenet.sh
+  cpuNum: 4
+  memoryMB: 25000
+  shmMB: 25000
+  gpuNum: 1
+  virtualCluster: nni
+  image: msranni/nni:latest
+nniManagerIp: <nni_manager_ip>
+paiYarnConfig:
+  userName: <username>
+  passWord: <password>
+  host: <host>

examples/trials/ga_squad/config_pai.yml

@@ -23,10 +23,13 @@ trial:
   memoryMB: 32869
   #The docker image to run nni job on pai
   image: msranni/nni:latest
+  nniManagerNFSMountPath: /home/user/mnt
+  containerNFSMountPath: /mnt/data/user
+  paiStoragePlugin: team_wise
 paiConfig:
   #The username to login pai
   userName: username
-  #The password to login pai
-  passWord: password
+  #The token to login pai
+  token: token
   #The host of restful server of pai
   host: 10.10.10.10

examples/trials/ga_squad/config_paiYarn.yml

+authorName: default
+experimentName: example_ga_squad
+trialConcurrency: 1
+maxExecDuration: 1h
+maxTrialNum: 10
+#choice: local, remote, pai
+trainingServicePlatform: paiYarn
+#choice: true, false
+useAnnotation: false
+#Your nni_manager ip
+nniManagerIp: 10.10.10.10
+tuner:
+  codeDir: ../../tuners/ga_customer_tuner
+  classFileName: customer_tuner.py
+  className: CustomerTuner
+  classArgs:
+    optimize_mode: maximize
+trial:
+  command: chmod +x ./download.sh && ./download.sh && python3 trial.py
+  codeDir: .
+  gpuNum: 0
+  cpuNum: 1
+  memoryMB: 32869
+  #The docker image to run nni job on pai
+  image: msranni/nni:latest
+paiYarnConfig:
+  #The username to login pai
+  userName: username
+  #The password to login pai
+  passWord: password
+  #The host of restful server of pai
+  host: 10.10.10.10

examples/trials/mnist-advisor/config_pai.yml

@@ -27,10 +27,13 @@ trial:
   memoryMB: 8196
   #The docker image to run nni job on pai
   image: msranni/nni:latest
+  nniManagerNFSMountPath: /home/user/mnt
+  containerNFSMountPath: /mnt/data/user
+  paiStoragePlugin: team_wise
 paiConfig:
   #The username to login pai
   userName: username
-  #The password to login pai
-  passWord: password
+  #The token to login pai
+  token: token
   #The host of restful server of pai
   host: 10.10.10.10

examples/trials/mnist-advisor/config_paiYarn.yml

+authorName: default
+experimentName: example_mnist_hyperband
+maxExecDuration: 1h
+maxTrialNum: 10000
+trialConcurrency: 10
+#choice: local, remote, pai
+trainingServicePlatform: paiYarn
+searchSpacePath: search_space.json
+#choice: true, false
+useAnnotation: false
+advisor:
+  #choice: Hyperband, BOHB
+  #(BOHB should be installed through nnictl)
+  builtinAdvisorName: Hyperband
+  classArgs:
+    #R: the maximum trial budget
+    R: 100
+    #eta: proportion of discarded trials
+    eta: 3
+    #choice: maximize, minimize
+    optimize_mode: maximize
+trial:
+  command: python3 mnist.py
+  codeDir: .
+  gpuNum: 0
+  cpuNum: 1
+  memoryMB: 8196
+  #The docker image to run nni job on pai
+  image: msranni/nni:latest
+paiYarnConfig:
+  #The username to login pai
+  userName: username
+  #The password to login pai
+  passWord: password
+  #The host of restful server of pai
+  host: 10.10.10.10

examples/trials/mnist-annotation/config_pai.yml

@@ -22,10 +22,13 @@ trial:
   memoryMB: 8196
   #The docker image to run nni job on pai
   image: msranni/nni:latest
+  nniManagerNFSMountPath: /home/user/mnt
+  containerNFSMountPath: /mnt/data/user
+  paiStoragePlugin: team_wise
 paiConfig:
   #The username to login pai
   userName: username
-  #The password to login pai
-  passWord: password
+  #The token to login pai
+  token: token
   #The host of restful server of pai
   host: 10.10.10.10
\ No newline at end of file

examples/trials/mnist-annotation/config_paiYarn.yml

+authorName: default
+experimentName: example_mnist
+trialConcurrency: 1
+maxExecDuration: 1h
+maxTrialNum: 10
+#choice: local, remote, pai
+trainingServicePlatform: paiYarn
+#choice: true, false
+useAnnotation: true
+tuner:
+  #choice: TPE, Random, Anneal, Evolution, BatchTuner, MetisTuner
+  #SMAC (SMAC should be installed through nnictl)
+  builtinTunerName: TPE
+  classArgs:
+    #choice: maximize, minimize
+    optimize_mode: maximize
+trial:
+  command: python3 mnist.py
+  codeDir: .
+  gpuNum: 0
+  cpuNum: 1
+  memoryMB: 8196
+  #The docker image to run nni job on pai
+  image: msranni/nni:latest
+paiYarnConfig:
+  #The username to login pai
+  userName: username
+  #The password to login pai
+  passWord: password
+  #The host of restful server of pai
+  host: 10.10.10.10
\ No newline at end of file

examples/trials/mnist-batch-tune-keras/config_pai.yml

@@ -20,10 +20,13 @@ trial:
   memoryMB: 8196
   #The docker image to run nni job on pai
   image: msranni/nni:latest
+  nniManagerNFSMountPath: /home/user/mnt
+  containerNFSMountPath: /mnt/data/user
+  paiStoragePlugin: team_wise
 paiConfig:
   #The username to login pai
   userName: username
-  #The password to login pai
-  passWord: password
+  #The token to login pai
+  token: token
   #The host of restful server of pai
   host: 10.10.10.10

examples/trials/mnist-batch-tune-keras/config_paiYarn.yml

+authorName: default
+experimentName: example_mnist-keras
+trialConcurrency: 1
+maxExecDuration: 1h
+maxTrialNum: 10
+#choice: local, remote, pai
+trainingServicePlatform: paiYarn
+searchSpacePath: search_space.json
+#choice: true, false
+useAnnotation: false
+tuner:
+  #choice: TPE, Random, Anneal, Evolution, BatchTuner, MetisTuner
+  #SMAC (SMAC should be installed through nnictl)
+  builtinTunerName: BatchTuner
+trial:
+  command: python3 mnist-keras.py
+  codeDir: .
+  gpuNum: 0
+  cpuNum: 1
+  memoryMB: 8196
+  #The docker image to run nni job on pai
+  image: msranni/nni:latest
+paiYarnConfig:
+  #The username to login pai
+  userName: username
+  #The password to login pai
+  passWord: password
+  #The host of restful server of pai
+  host: 10.10.10.10

examples/trials/mnist-keras/config_pai.yml

@@ -23,10 +23,13 @@ trial:
   memoryMB: 8196
   #The docker image to run nni job on pai
   image: msranni/nni:latest
+  nniManagerNFSMountPath: /home/user/mnt
+  containerNFSMountPath: /mnt/data/user
+  paiStoragePlugin: team_wise
 paiConfig:
   #The username to login pai
   userName: username
-  #The password to login pai
-  passWord: password
+  #The token to login pai
+  token: token
   #The host of restful server of pai
   host: 10.10.10.10
\ No newline at end of file

examples/trials/mnist-keras/config_paiYarn.yml

+authorName: default
+experimentName: example_mnist-keras
+trialConcurrency: 1
+maxExecDuration: 1h
+maxTrialNum: 10
+#choice: local, remote, pai
+trainingServicePlatform: paiYarn
+searchSpacePath: search_space.json
+#choice: true, false
+useAnnotation: false
+tuner:
+  #choice: TPE, Random, Anneal, Evolution, BatchTuner, MetisTuner
+  #SMAC (SMAC should be installed through nnictl)
+  builtinTunerName: TPE
+  classArgs:
+    #choice: maximize, minimize
+    optimize_mode: maximize
+trial:
+  command: python3 mnist-keras.py
+  codeDir: .
+  gpuNum: 0
+  cpuNum: 1
+  memoryMB: 8196
+  #The docker image to run nni job on pai
+  image: msranni/nni:latest
+paiYarnConfig:
+  #The username to login pai
+  userName: username
+  #The password to login pai
+  passWord: password
+  #The host of restful server of pai
+  host: 10.10.10.10
\ No newline at end of file

examples/trials/mnist-pytorch/config_pai.yml

@@ -23,10 +23,13 @@ trial:
   memoryMB: 8196
   #The docker image to run nni job on pai
   image: msranni/nni:latest
+  nniManagerNFSMountPath: /home/user/mnt
+  containerNFSMountPath: /mnt/data/user
+  paiStoragePlugin: team_wise
 paiConfig:
   #The username to login pai
   userName: username
-  #The password to login pai
-  passWord: password
+  #The token to login pai
+  token: token
   #The host of restful server of pai
   host: 10.10.10.10
\ No newline at end of file

examples/trials/mnist-pytorch/config_paiYarn.yml

+authorName: default
+experimentName: example_mnist_pytorch
+trialConcurrency: 1
+maxExecDuration: 1h
+maxTrialNum: 10
+#choice: local, remote, pai
+trainingServicePlatform: paiYarn
+searchSpacePath: search_space.json
+#choice: true, false
+useAnnotation: false
+tuner:
+  #choice: TPE, Random, Anneal, Evolution, BatchTuner, MetisTuner, GPTuner
+  #SMAC (SMAC should be installed through nnictl)
+  builtinTunerName: TPE
+  classArgs:
+    #choice: maximize, minimize
+    optimize_mode: maximize
+trial:
+  command: python3 mnist.py
+  codeDir: .
+  gpuNum: 0
+  cpuNum: 1
+  memoryMB: 8196
+  #The docker image to run nni job on pai
+  image: msranni/nni:latest
+paiYarnConfig:
+  #The username to login pai
+  userName: username
+  #The password to login pai
+  passWord: password
+  #The host of restful server of pai
+  host: 10.10.10.10
\ No newline at end of file