From db9753241eeda89ab7a926c3892bd1f8487edb3f Mon Sep 17 00:00:00 2001 From: Mu Li Date: Wed, 23 Sep 2015 12:19:23 -0400 Subject: [PATCH 1/4] update cifar perf on cudnn v3 --- example/cifar10/README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/example/cifar10/README.md b/example/cifar10/README.md index 196df6617f52..6ed39ca34054 100644 --- a/example/cifar10/README.md +++ b/example/cifar10/README.md @@ -12,6 +12,7 @@ run `cifar.py`: | --- | --- | --- | --- | | cxxnet | 362 img/sec | 675 img/sec | 1282 img/sec | | mxnet | 420 img/sec | 804 img/sec | 1436 img/sec | +| mxnet + cudnn v3 | 835 img/sec | 1525 img/sec | 2270 img/sec | sample output From b2dff701f4d73b24dd04c0779cacf3cbfa02677a Mon Sep 17 00:00:00 2001 From: Mu Li Date: Wed, 23 Sep 2015 12:20:47 -0400 Subject: [PATCH 2/4] add include/lib path in makefile for cudnn --- Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Makefile b/Makefile index d1e082d1f202..6bf1bff184b4 100644 --- a/Makefile +++ b/Makefile @@ -55,8 +55,8 @@ ifeq ($(USE_OPENMP), 1) endif ifeq ($(USE_CUDNN), 1) - CFLAGS += -DMSHADOW_USE_CUDNN=1 - LDFLAGS += -lcudnn + CFLAGS += -DMSHADOW_USE_CUDNN=1 -I$(USE_CUDNN_PATH) + LDFLAGS += -L$(USE_CUDNN_PATH) -lcudnn endif ifeq ($(USE_THREADED_ENGINE), 1) From 468397116e8fc69633c087fbc306f9d1d9a11766 Mon Sep 17 00:00:00 2001 From: muli Date: Wed, 23 Sep 2015 18:42:35 +0000 Subject: [PATCH 3/4] comment out USE_CUDNN_PATH --- Makefile | 4 ++-- make/config.mk | 3 ++- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/Makefile b/Makefile index 6bf1bff184b4..d1e082d1f202 100644 --- a/Makefile +++ b/Makefile @@ -55,8 +55,8 @@ ifeq ($(USE_OPENMP), 1) endif ifeq ($(USE_CUDNN), 1) - CFLAGS += -DMSHADOW_USE_CUDNN=1 -I$(USE_CUDNN_PATH) - LDFLAGS += -L$(USE_CUDNN_PATH) -lcudnn + CFLAGS += -DMSHADOW_USE_CUDNN=1 + LDFLAGS += -lcudnn endif ifeq ($(USE_THREADED_ENGINE), 1) diff --git a/make/config.mk b/make/config.mk index 7108875df432..d2884833c01f 100644 --- a/make/config.mk +++ b/make/config.mk @@ -43,7 +43,8 @@ USE_CUDNN = 0 # add the path to CUDNN libary to link and compile flag # if you do not need that, or do not have that, leave it as NONE -USE_CUDNN_PATH = NONE +# (NOTE: not enable at this moment) +# USE_CUDNN_PATH = NONE # whether use opencv during compilation # you can disable it, however, you will not able to use From ea18aeb2ab0c06b6319c8850432974a2d88bb165 Mon Sep 17 00:00:00 2001 From: muli Date: Wed, 23 Sep 2015 18:53:02 +0000 Subject: [PATCH 4/4] [example] update mnist --- example/mnist/README.md | 7 ++++--- example/mnist/lenet.py | 3 ++- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/example/mnist/README.md b/example/mnist/README.md index 6fc1bd4eefd1..e35c6a2d014a 100644 --- a/example/mnist/README.md +++ b/example/mnist/README.md @@ -17,9 +17,10 @@ Cortes, and Christopher J.C. Burges. Using 100 minibatch size and 20 data passes (not fine tuned.) -Machine: Dual Xeon E5-2680 2.8GHz, Dual GTX 980, Intel MKL, and CUDA 7.0 +Machine: Dual Xeon E5-2680 2.8GHz, Dual GTX 980, Ubuntu 14.0, GCC 4.8. Intel MKL, and CUDA 7.0 | | val accuracy | 2 x E5-2680 | 1 x GTX 980 | 2 x GTX 980 | | --- | ---: | ---: | ---: | ---: | -| `mlp.py` | 97.8% | 40K img/sec | 103K img/sec | 60K img/sec | -| `lenet.py` | 99% | 368 img/sec | 22.5K img/sec | 33K img/sec | +| `mlp.py` MKL + CUDA 7 | 97.8% | 40K img/sec | 103K img/sec | 60K img/sec | +| `lenet.py` MKL + CUDA 7 | 99% | 368 img/sec | 22.5K img/sec | 33K img/sec | +| `lenet.py` MKL + CUDA 7 + CUDNN v3 | - | - | 19K img/sec | 29 K img/sec | diff --git a/example/mnist/lenet.py b/example/mnist/lenet.py index d9b30b316413..18066adb6f2f 100644 --- a/example/mnist/lenet.py +++ b/example/mnist/lenet.py @@ -41,4 +41,5 @@ ctx = dev, symbol = lenet, num_round = 20, learning_rate = 0.01, momentum = 0.9, wd = 0.00001) -model.fit(X=train, eval_data=val) +model.fit(X=train, eval_data=val, + epoch_end_callback=mx.callback.Speedometer(100))