From 0a342d718ede0c363da223345607d493584c4591 Mon Sep 17 00:00:00 2001
From: Edmond Yoo <hj3yoo@uwaterloo.ca>
Date: Sat, 13 Oct 2018 06:16:06 +0000
Subject: [PATCH] Cleaning & commenting #1 - opencv_dnn.py
---
Makefile | 69 +++++++++++++++++++++++++---------
1 files changed, 51 insertions(+), 18 deletions(-)
diff --git a/Makefile b/Makefile
index f8bd4a5..2ffccf7 100644
--- a/Makefile
+++ b/Makefile
@@ -1,26 +1,40 @@
-GPU=0
-CUDNN=0
-OPENCV=0
-DEBUG=0
+GPU=1
+CUDNN=1
+CUDNN_HALF=0
+OPENCV=1
+AVX=0
OPENMP=0
-LIBSO=0
+LIBSO=1
+
+# set GPU=1 and CUDNN=1 to speedup on GPU
+# set CUDNN_HALF=1 to further speedup 3 x times (Mixed-precision using Tensor Cores) on GPU Tesla V100, Titan V, DGX-2
+# set AVX=1 and OPENMP=1 to speedup on CPU (if error occurs then set AVX=0)
+
+DEBUG=0
ARCH= -gencode arch=compute_30,code=sm_30 \
-gencode arch=compute_35,code=sm_35 \
-gencode arch=compute_50,code=[sm_50,compute_50] \
-gencode arch=compute_52,code=[sm_52,compute_52] \
- -gencode arch=compute_61,code=[sm_61,compute_61]
+ -gencode arch=compute_61,code=[sm_61,compute_61]
+OS := $(shell uname)
-# For Jetson Tx1 uncomment:
-# ARCH= -gencode arch=compute_51,code=[sm_51,compute_51]
+# Tesla V100
+# ARCH= -gencode arch=compute_70,code=[sm_70,compute_70]
-# For Jetson Tx2 uncomment:
+# GTX 1080, GTX 1070, GTX 1060, GTX 1050, GTX 1030, Titan Xp, Tesla P40, Tesla P4
+# ARCH= -gencode arch=compute_61,code=sm_61 -gencode arch=compute_61,code=compute_61
+
+# GP100/Tesla P100 � DGX-1
+# ARCH= -gencode arch=compute_60,code=sm_60
+
+# For Jetson TX1, Tegra X1, DRIVE CX, DRIVE PX - uncomment:
+# ARCH= -gencode arch=compute_53,code=[sm_53,compute_53]
+
+# For Jetson Tx2 or Drive-PX2 uncomment:
# ARCH= -gencode arch=compute_62,code=[sm_62,compute_62]
-# This is what I use, uncomment if you know your arch and want to specify
-# ARCH= -gencode arch=compute_52,code=compute_52
-
VPATH=./src/
EXEC=darknet
@@ -37,10 +51,14 @@
OPTS=-Ofast
LDFLAGS= -lm -pthread
COMMON=
-CFLAGS=-Wall -Wfatal-errors
+CFLAGS=-Wall -Wfatal-errors -Wno-unused-result -Wno-unknown-pragmas
ifeq ($(DEBUG), 1)
-OPTS=-O0 -g
+OPTS= -O0 -g
+else
+ifeq ($(AVX), 1)
+CFLAGS+= -ffp-contract=fast -mavx -mavx2 -msse3 -msse4.1 -msse4.2 -msse4a
+endif
endif
CFLAGS+=$(OPTS)
@@ -57,19 +75,34 @@
LDFLAGS+= -lgomp
endif
-ifeq ($(GPU), 1)
+ifeq ($(GPU), 1)
COMMON+= -DGPU -I/usr/local/cuda/include/
CFLAGS+= -DGPU
+ifeq ($(OS),Darwin) #MAC
+LDFLAGS+= -L/usr/local/cuda/lib -lcuda -lcudart -lcublas -lcurand
+else
LDFLAGS+= -L/usr/local/cuda/lib64 -lcuda -lcudart -lcublas -lcurand
endif
+endif
-ifeq ($(CUDNN), 1)
-COMMON+= -DCUDNN
+ifeq ($(CUDNN), 1)
+COMMON+= -DCUDNN
+ifeq ($(OS),Darwin) #MAC
+CFLAGS+= -DCUDNN -I/usr/local/cuda/include
+LDFLAGS+= -L/usr/local/cuda/lib -lcudnn
+else
CFLAGS+= -DCUDNN -I/usr/local/cudnn/include
LDFLAGS+= -L/usr/local/cudnn/lib64 -lcudnn
endif
+endif
-OBJ=http_stream.o gemm.o utils.o cuda.o convolutional_layer.o list.o image.o activations.o im2col.o col2im.o blas.o crop_layer.o dropout_layer.o maxpool_layer.o softmax_layer.o data.o matrix.o network.o connected_layer.o cost_layer.o parser.o option_list.o darknet.o detection_layer.o captcha.o route_layer.o writing.o box.o nightmare.o normalization_layer.o avgpool_layer.o coco.o dice.o yolo.o detector.o layer.o compare.o classifier.o local_layer.o swag.o shortcut_layer.o activation_layer.o rnn_layer.o gru_layer.o rnn.o rnn_vid.o crnn_layer.o demo.o tag.o cifar.o go.o batchnorm_layer.o art.o region_layer.o reorg_layer.o super.o voxel.o tree.o
+ifeq ($(CUDNN_HALF), 1)
+COMMON+= -DCUDNN_HALF
+CFLAGS+= -DCUDNN_HALF
+ARCH+= -gencode arch=compute_70,code=[sm_70,compute_70]
+endif
+
+OBJ=http_stream.o gemm.o utils.o cuda.o convolutional_layer.o list.o image.o activations.o im2col.o col2im.o blas.o crop_layer.o dropout_layer.o maxpool_layer.o softmax_layer.o data.o matrix.o network.o connected_layer.o cost_layer.o parser.o option_list.o darknet.o detection_layer.o captcha.o route_layer.o writing.o box.o nightmare.o normalization_layer.o avgpool_layer.o coco.o dice.o yolo.o detector.o layer.o compare.o classifier.o local_layer.o swag.o shortcut_layer.o activation_layer.o rnn_layer.o gru_layer.o rnn.o rnn_vid.o crnn_layer.o demo.o tag.o cifar.o go.o batchnorm_layer.o art.o region_layer.o reorg_layer.o reorg_old_layer.o super.o voxel.o tree.o yolo_layer.o upsample_layer.o
ifeq ($(GPU), 1)
LDFLAGS+= -lstdc++
OBJ+=convolutional_kernels.o activation_kernels.o im2col_kernels.o col2im_kernels.o blas_kernels.o crop_layer_kernels.o dropout_layer_kernels.o maxpool_layer_kernels.o network_kernels.o avgpool_layer_kernels.o
--
Gitblit v1.10.0