updated scripts to support tensorflow v1.2.0

README.md

@@ -1,6 +1,6 @@
 # installTensorFlowTX2
 April 1, 2017
-Install TensorFlow v1.0.1 on NVIDIA Jetson TX2 Development Kit
+Install TensorFlow v1.2.0 on NVIDIA Jetson TX2 Development Kit
 
 Jetson TX2 is flashed with JetPack 3.0 which installs:
 * L4T 27.1 an Ubuntu 16.04 64-bit variant (aarch64)
@@ -16,6 +16,7 @@ Note: This procedure was derived from these discussion threads:
 <li>https://github.com/tensorflow/tensorflow/issues/851</li>
 <li>http://stackoverflow.com/questions/39783919/tensorflow-on-nvidia-tx1/</li>
 <li>https://devtalk.nvidia.com/default/topic/1000717/tensorflow-on-jetson-tx2/</li>
+<li>https://github.com/tensorflow/tensorflow/issues/9697</li>
 </ul>
 
 TensorFlow should be built in the following order:
@@ -27,7 +28,7 @@ Installs Java and other dependencies needed. Also builds:
 Builds version 0.4.5. Includes patches for compiling under aarch64. 
 
 #### cloneTensorFlow.sh
-Git clones v1.0.1 from the TensorFlow repository and patches the source code for aarch64
+Git clones v1.2.0 from the TensorFlow repository and patches the source code for aarch64
 
 #### setTensorFlowEV.sh
 Sets up the TensorFlow environment variables. This script will ask for the default python library path. There are many settings to chose from, the script picks the usual suspects. Uses python 2.7.

cloneTensorFlow.sh

@@ -8,7 +8,7 @@ INSTALL_DIR=$PWD
 cd $HOME
 git clone https://github.com/tensorflow/tensorflow.git
 cd tensorflow
-git checkout v1.0.1
+git checkout v1.2.0
 patch -p1 < $INSTALL_DIR/patches/tensorflow.patch
 
 

packageTensorFlow.sh

@@ -2,5 +2,5 @@
 # NVIDIA Jetson TX1
 cd $HOME/tensorflow
 bazel-bin/tensorflow/tools/pip_package/build_pip_package /tmp/tensorflow_pkg
-mv /tmp/tensorflow_pkg/tensorflow-1.0.1-cp27-cp27mu-linux_aarch64.whl $HOME/
+mv /tmp/tensorflow_pkg/tensorflow-1.2.0-cp27-cp27mu-linux_aarch64.whl $HOME/
 

patches/tensorflow.patch

@@ -1,75 +1,20 @@
-diff --git a/tensorflow/core/kernels/BUILD b/tensorflow/core/kernels/BUILD
-index 2e04827..9d81923 100644
---- a/tensorflow/core/kernels/BUILD
-+++ b/tensorflow/core/kernels/BUILD
-@@ -1184,7 +1184,7 @@ tf_kernel_libraries(
-         "segment_reduction_ops",
-         "scan_ops",
-         "sequence_ops",
--        "sparse_matmul_op",
-+        #DC "sparse_matmul_op",
-     ],
-     deps = [
-         ":bounds_check",
-diff --git a/tensorflow/core/kernels/cwise_op_gpu_select.cu.cc b/tensorflow/core/kernels/cwise_op_gpu_select.cu.cc
-index 02058a8..880a0c3 100644
---- a/tensorflow/core/kernels/cwise_op_gpu_select.cu.cc
-+++ b/tensorflow/core/kernels/cwise_op_gpu_select.cu.cc
-@@ -43,8 +43,14 @@ struct BatchSelectFunctor<GPUDevice, T> {
-     const int all_but_batch = then_flat_outer_dims.dimension(1);
-
- #if !defined(EIGEN_HAS_INDEX_LIST)
--    Eigen::array<int, 2> broadcast_dims{{ 1, all_but_batch }};
--    Eigen::Tensor<int, 2>::Dimensions reshape_dims{{ batch, 1 }};
-+    // Eigen::array<int, 2> broadcast_dims{{ 1, all_but_batch }};
-+    Eigen::array<int, 2> broadcast_dims;
-+   broadcast_dims[0] = 1;
-+    broadcast_dims[1] = all_but_batch;
-+    // Eigen::Tensor<int, 2>::Dimensions reshape_dims{{ batch, 1 }};
-+    Eigen::Tensor<int, 2>::Dimensions reshape_dims;
-+   reshape_dims[0] = batch;
-+   reshape_dims[1] = 1;
- #else
-     Eigen::IndexList<Eigen::type2index<1>, int> broadcast_dims;
-     broadcast_dims.set(1, all_but_batch);
-diff --git a/tensorflow/core/kernels/sparse_tensor_dense_matmul_op_gpu.cu.cc b/tensorflow/core/kernels/sparse_tensor_dense_matmul_op_gpu.cu.cc
-index a177696..28d2f59 100644
---- a/tensorflow/core/kernels/sparse_tensor_dense_matmul_op_gpu.cu.cc
-+++ b/tensorflow/core/kernels/sparse_tensor_dense_matmul_op_gpu.cu.cc
-@@ -104,9 +104,17 @@ struct SparseTensorDenseMatMulFunctor<GPUDevice, T, ADJ_A, ADJ_B> {
-     int n = (ADJ_B) ? b.dimension(0) : b.dimension(1);
-
- #if !defined(EIGEN_HAS_INDEX_LIST)
--    Eigen::Tensor<int, 2>::Dimensions matrix_1_by_nnz{{ 1, nnz }};
--    Eigen::array<int, 2> n_by_1{{ n, 1 }};
--    Eigen::array<int, 1> reduce_on_rows{{ 0 }};
-+    // Eigen::Tensor<int, 2>::Dimensions matrix_1_by_nnz{{ 1, nnz }};
-+    Eigen::Tensor<int, 2>::Dimensions matrix_1_by_nnz;
-+   matrix_1_by_nnz[0] = 1;
-+   matrix_1_by_nnz[1] = nnz;
-+    // Eigen::array<int, 2> n_by_1{{ n, 1 }};
-+    Eigen::array<int, 2> n_by_1;
-+   n_by_1[0] = n;
-+   n_by_1[1] = 1;
-+    // Eigen::array<int, 1> reduce_on_rows{{ 0 }};
-+    Eigen::array<int, 1> reduce_on_rows;
-+   reduce_on_rows[0]= 0;
- #else
-     Eigen::IndexList<Eigen::type2index<1>, int> matrix_1_by_nnz;
-     matrix_1_by_nnz.set(1, nnz);
-diff --git a/tensorflow/stream_executor/cuda/cuda_gpu_executor.cc b/tensorflow/stream_executor/cuda/cuda_gpu_executor.cc
-index b2da109..8ee1f3a 100644
---- a/tensorflow/stream_executor/cuda/cuda_gpu_executor.cc
-+++ b/tensorflow/stream_executor/cuda/cuda_gpu_executor.cc
-@@ -870,7 +870,10 @@ CudaContext* CUDAExecutor::cuda_context() { return context_; }
- // For anything more complicated/prod-focused than this, you'll likely want to
- // turn to gsys' topology modeling.
- static int TryToReadNumaNode(const string &pci_bus_id, int device_ordinal) {
--#if defined(__APPLE__)
-+#ifdef __aarch64__
-+    LOG(INFO) << "ARM64 does not support NUMA - returning NUMA node zero";
-+    return 0;
-+#elif defined(__APPLE__)
-   LOG(INFO) << "OS X does not support NUMA - returning NUMA node zero";
-   return 0;
- #elif defined(PLATFORM_WINDOWS)
+diff --git a/a/tensorflow/workspace.bzl b/b/tensorflow/workspace.bzl
+index 2a206b0..d785473 100644
+--- a/a/tensorflow/workspace.bzl
++++ b/b/tensorflow/workspace.bzl
+@@ -150,11 +150,11 @@ def tf_workspace(path_prefix="", tf_repo_name=""):
+   native.new_http_archive(
+       name = "eigen_archive",
+       urls = [
+-          "http://mirror.bazel.build/bitbucket.org/eigen/eigen/get/f3a22f35b044.tar.gz",
+-          "https://bitbucket.org/eigen/eigen/get/f3a22f35b044.tar.gz",
++          "http://mirror.bazel.build/bitbucket.org/eigen/eigen/get/d781c1de9834.tar.gz",
++          "https://bitbucket.org/eigen/eigen/get/d781c1de9834.tar.gz",
+       ],
+-      sha256 = "ca7beac153d4059c02c8fc59816c82d54ea47fe58365e8aded4082ded0b820c4",
+-      strip_prefix = "eigen-eigen-f3a22f35b044",
++      sha256 = "a34b208da6ec18fa8da963369e166e4a368612c14d956dd2f9d7072904675d9b",
++      strip_prefix = "eigen-eigen-d781c1de9834",
+       build_file = str(Label("//third_party:eigen.BUILD")),
+   )
+