From 1d2c84e60280319bdff2cce446b7df5e8bb8b870 Mon Sep 17 00:00:00 2001 From: Tommy Li Date: Mon, 23 Jul 2018 10:26:16 -0700 Subject: [PATCH 1/2] update dl framework versions --- docs/user-guide.md | 6 +++--- templates/services/learner-configmap.yml | 12 ++++++------ 2 files changed, 9 insertions(+), 9 deletions(-) diff --git a/docs/user-guide.md b/docs/user-guide.md index d766c3e4..b7f8caf9 100644 --- a/docs/user-guide.md +++ b/docs/user-guide.md @@ -25,15 +25,15 @@ Currently, Fabric for Deep Learning supports following community frameworks | Framework | Versions | Processing Unit | | ------------- | ------------- | --------------- | -| [tensorflow](https://hub.docker.com/r/tensorflow/tensorflow/) | 1.3.0, 1.3.0-py3, 1.4.0, 1.4.0-py3, 1.5.0, 1.5.0-py3, 1.5.1, 1.5.1-py3, 1.6.0, 1.6.0-py3, 1.7.0, 1.7.0-py3, 1.8.0, 1.8.0-py3, latest, latest-py3 | CPU | -| [tensorflow](https://hub.docker.com/r/tensorflow/tensorflow/) | 1.3.0-gpu, 1.3.0-gpu-py3, 1.4.0-gpu, 1.4.0-gpu-py3, 1.5.0-gpu, 1.5.0-gpu-py3, 1.5.1-gpu, 1.5.1-gpu-py3, 1.6.0-gpu, 1.6.0-gpu-py3, 1.7.0-gpu, 1.7.0-gpu-py3, 1.8.0-gpu, 1.8.0-gpu-py3, latest-gpu, latest-gpu-py3 | GPU | +| [tensorflow](https://hub.docker.com/r/tensorflow/tensorflow/) | 1.4.0, 1.4.0-py3, 1.5.0, 1.5.0-py3, 1.5.1, 1.5.1-py3, 1.6.0, 1.6.0-py3, 1.7.0, 1.7.0-py3, 1.8.0, 1.8.0-py3, 1.9.0, 1.9.0-py3, latest, latest-py3 | CPU | +| [tensorflow](https://hub.docker.com/r/tensorflow/tensorflow/) | 1.4.0-gpu, 1.4.0-gpu-py3, 1.5.0-gpu, 1.5.0-gpu-py3, 1.5.1-gpu, 1.5.1-gpu-py3, 1.6.0-gpu, 1.6.0-gpu-py3, 1.7.0-gpu, 1.7.0-gpu-py3, 1.8.0-gpu, 1.8.0-gpu-py3, 1.9.0-gpu, 1.9.0-gpu-py3, latest-gpu, latest-gpu-py3 | GPU | | [caffe](https://hub.docker.com/r/bvlc/caffe/) | cpu, intel | CPU | | [caffe](https://hub.docker.com/r/bvlc/caffe/) | gpu | GPU | | [pytorch](https://hub.docker.com/r/pytorch/pytorch/) | v0.2, latest | CPU, GPU | | [caffe2](https://hub.docker.com/r/caffe2ai/caffe2/) | c2v0.8.1.cpu.full.ubuntu14.04, c2v0.8.0.cpu.full.ubuntu16.04 | CPU | | [caffe2](https://hub.docker.com/r/caffe2ai/caffe2/) | c2v0.8.1.cuda8.cudnn7.ubuntu16.04, latest | GPU | | [h2o3](https://hub.docker.com/r/opsh2oai/h2o3-ffdl/) | latest | CPU | -| [horovod](https://hub.docker.com/r/uber/horovod/) | 0.13.4-tf1.8.0-torch0.4.0-py3.5, 0.13.4-tf1.8.0-torch0.4.0-py2.7 | CPU, GPU | +| [horovod](https://hub.docker.com/r/uber/horovod/) | 0.13.10-tf1.9.0-torch0.4.0-py2.7, 0.13.10-tf1.9.0-torch0.4.0-py3.5 | CPU, GPU | You can deploy models based on these frameworks and then train your models using the FfDL CLI or FfDL UI. diff --git a/templates/services/learner-configmap.yml b/templates/services/learner-configmap.yml index 465fb3a3..b78f39ed 100644 --- a/templates/services/learner-configmap.yml +++ b/templates/services/learner-configmap.yml @@ -31,10 +31,10 @@ data: tensorflow_gpu_1.4.0-gpu_CURRENT: manual tensorflow_cpu_1.4.0_CURRENT: manual tensorflow_cpu_1.4.0-py3_CURRENT: manual - tensorflow_gpu_1.3.0-gpu-py3_CURRENT: manual - tensorflow_gpu_1.3.0-gpu_CURRENT: manual - tensorflow_cpu_1.3.0_CURRENT: manual - tensorflow_cpu_1.3.0-py3_CURRENT: manual + tensorflow_gpu_1.9.0-gpu-py3_CURRENT: manual + tensorflow_gpu_1.9.0-gpu_CURRENT: manual + tensorflow_cpu_1.9.0_CURRENT: manual + tensorflow_cpu_1.9.0-py3_CURRENT: manual h2o3_cpu_latest_CURRENT: manual caffe_cpu_cpu_CURRENT: master-39 caffe_gpu_gpu_CURRENT: master-39 @@ -45,8 +45,8 @@ data: caffe2_gpu_c2v0.8.1.cuda8.cudnn7.ubuntu16.04_CURRENT: master-39 caffe2_cpu_c2v0.8.0.cpu.full.ubuntu16.04_CURRENT: master-39 caffe2_gpu_latest_CURRENT: master-39 - horovod_gpu_0.13.4-tf1.8.0-torch0.4.0-py3.5_CURRENT: manual - horovod_gpu_0.13.4-tf1.8.0-torch0.4.0-py2.7_CURRENT: manual + horovod_gpu_0.13.10-tf1.9.0-torch0.4.0-py3.5_CURRENT: manual + horovod_gpu_0.13.10-tf1.9.0-torch0.4.0-py2.7_CURRENT: manual --- apiVersion: v1 From 9cfeeba534f55ac6843d252baf6564972cb56899 Mon Sep 17 00:00:00 2001 From: Tommy Li Date: Mon, 23 Jul 2018 10:30:52 -0700 Subject: [PATCH 2/2] update examples with new framework tags --- etc/examples/horovod/manifest_pytorchmnist.yml | 2 +- etc/examples/horovod/manifest_tfmnist.yml | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/etc/examples/horovod/manifest_pytorchmnist.yml b/etc/examples/horovod/manifest_pytorchmnist.yml index 4b713102..c1811d35 100644 --- a/etc/examples/horovod/manifest_pytorchmnist.yml +++ b/etc/examples/horovod/manifest_pytorchmnist.yml @@ -20,5 +20,5 @@ data_stores: framework: name: horovod - version: "0.13.4-tf1.8.0-torch0.4.0-py3.5" + version: "0.13.10-tf1.9.0-torch0.4.0-py3.5" command: python pytorch_mnist.py diff --git a/etc/examples/horovod/manifest_tfmnist.yml b/etc/examples/horovod/manifest_tfmnist.yml index 9fff6e78..17f11a97 100644 --- a/etc/examples/horovod/manifest_tfmnist.yml +++ b/etc/examples/horovod/manifest_tfmnist.yml @@ -20,6 +20,6 @@ data_stores: framework: name: horovod - version: "0.13.4-tf1.8.0-torch0.4.0-py3.5" + version: "0.13.10-tf1.9.0-torch0.4.0-py3.5" command: python tensorflow_mnist.py # the command is basically running the above command via openmpi, feel free to remove -x NCCL_DEBUG=INFO