Merge pull request #233 from microsoft/master

merge master

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/cifar10_pytorch/main.py

@@ -99,7 +99,7 @@ def prepare(args):
 
 
 # Training
-def train(epoch):
+def train(epoch, batches=-1):
     global trainloader
     global testloader
     global net
@@ -129,6 +129,9 @@ def train(epoch):
         progress_bar(batch_idx, len(trainloader), 'Loss: %.3f | Acc: %.3f%% (%d/%d)'
             % (train_loss/(batch_idx+1), 100.*correct/total, correct, total))
 
+        if batches > 0 and (batch_idx+1) >= batches:
+            return
+
 def test(epoch):
     global best_acc
     global trainloader
@@ -176,6 +179,10 @@ def test(epoch):
 if __name__ == '__main__':
     parser = argparse.ArgumentParser()
     parser.add_argument("--epochs", type=int, default=200)
+
+    # Maximum mini-batches per epoch, for code testing purpose
+    parser.add_argument("--batches", type=int, default=-1)
+
     args, _ = parser.parse_known_args()
 
     try:
@@ -187,7 +194,7 @@ if __name__ == '__main__':
         acc = 0.0
         best_acc = 0.0
         for epoch in range(start_epoch, start_epoch+args.epochs):
-            train(epoch)
+            train(epoch, args.batches)
             acc, best_acc = test(epoch)
             nni.report_intermediate_result(acc)
 

examples/trials/efficientnet/README_zh_CN.md

-[文档](https://nni.readthedocs.io/en/latest/TrialExample/EfficientNet.html)
\ No newline at end of file
+[文档](https://nni.readthedocs.io/zh/latest/TrialExample/EfficientNet.html)
\ No newline at end of file

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

examples/trials/mnist-tfv1/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-tfv1/config_paiYarn.yml

+authorName: default
+experimentName: example_mnist
+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

examples/trials/nas_cifar10/config_paiYarn_ppo.yml

+authorName: Unknown
+experimentName: enas_macro
+trialConcurrency: 20
+maxExecDuration: 2400h
+maxTrialNum: 20000
+#choice: local, remote
+trainingServicePlatform: paiYarn
+#choice: true, false
+useAnnotation: true
+multiPhase: false
+versionCheck: false
+nniManagerIp: 0.0.0.0
+tuner:
+  builtinTunerName: PPOTuner
+  classArgs:
+    optimize_mode: maximize
+    trials_per_update: 60
+    epochs_per_update: 20
+    minibatch_size: 6
+trial:
+  command: sh ./macro_cifar10_pai.sh
+  codeDir: ./
+  gpuNum: 1
+  cpuNum: 1
+  memoryMB: 8196
+  image: msranni/nni:latest
+  virtualCluster: nni
+paiYarnConfig:
+  userName: your_account
+  passWord: your_passwd
+  host: 0.0.0.0