From ae43c2bc32fbb838bfebeeaf2c2b058ccab5c83c Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@burninator.cs.washington.edu>
Date: Thu, 23 Jun 2016 05:31:14 +0000
Subject: [PATCH] hi
---
data/labels/potted plant.png | 0
data/labels/frisbee.png | 0
data/labels/apple.png | 0
data/labels/orange.png | 0
data/labels/sports ball.png | 0
data/labels/broccoli.png | 0
data/labels/tv.png | 0
data/labels/mouse.png | 0
data/labels/book.png | 0
data/labels/backpack.png | 0
data/labels/sandwich.png | 0
data/labels/sheep.png | 0
data/labels/sofa.png | 0
data/labels/toaster.png | 0
data/labels/toilet.png | 0
data/labels/pottedplant.png | 0
data/labels/remote.png | 0
data/labels/baseball glove.png | 0
data/labels/microwave.png | 0
cfg/yolo-coco.cfg | 4
data/labels/refrigerator.png | 0
data/labels/person.png | 0
data/labels/airplane.png | 0
data/labels/carrot.png | 0
data/labels/horse.png | 0
data/labels/skateboard.png | 0
data/labels/hot dog.png | 0
data/labels/scissors.png | 0
data/labels/bear.png | 0
data/labels/zebra.png | 0
data/labels/hair drier.png | 0
data/labels/spoon.png | 0
src/image.c | 1
src/coco.c | 50 ----
data/labels/truck.png | 0
src/layer.h | 1
data/labels/fork.png | 0
data/labels/motorcycle.png | 0
data/labels/cake.png | 0
src/detection_layer.c | 11 -
data/labels/vase.png | 0
src/activations.h | 14 +
src/parser.c | 2
src/activation_kernels.cu | 16 +
src/activations.c | 7
data/labels/traffic light.png | 0
data/labels/banana.png | 0
data/labels/tvmonitor.png | 0
data/labels/donut.png | 0
data/labels/giraffe.png | 0
data/labels/skis.png | 0
data/labels/baseball bat.png | 0
data/labels/surfboard.png | 0
data/labels/wine glass.png | 0
data/labels/motorbike.png | 0
src/demo.c | 198 ++++++++++++++++++++++
data/labels/dog.png | 0
src/convolutional_kernels.cu | 3
data/labels/clock.png | 0
data/labels/oven.png | 0
data/labels/bottle.png | 0
src/demo.h | 7
data/labels/couch.png | 0
data/labels/cup.png | 0
data/labels/bus.png | 0
data/labels/parking meter.png | 0
data/labels/aeroplane.png | 0
data/labels/diningtable.png | 0
data/labels/bird.png | 0
data/labels/pizza.png | 0
data/labels/kite.png | 0
data/labels/handbag.png | 0
data/labels/knife.png | 0
data/labels/bowl.png | 0
src/yolo.c | 13
data/labels/bench.png | 0
data/labels/bed.png | 0
data/labels/tie.png | 0
data/labels/keyboard.png | 0
Makefile | 4
data/labels/boat.png | 0
data/labels/laptop.png | 0
data/labels/car.png | 0
data/labels/cow.png | 0
data/labels/cell phone.png | 0
data/labels/sink.png | 0
data/labels/umbrella.png | 0
data/labels/chair.png | 0
data/labels/snowboard.png | 0
data/labels/cat.png | 0
src/network.c | 1
src/network.h | 1
data/labels/teddy bear.png | 0
data/labels/tennis racket.png | 0
data/labels/suitcase.png | 0
data/labels/stop sign.png | 0
data/labels/elephant.png | 0
/dev/null | 135 ---------------
cfg/yolo.cfg | 15 -
data/labels/bicycle.png | 0
data/labels/dining table.png | 0
data/labels/train.png | 0
data/labels/toothbrush.png | 0
data/labels/fire hydrant.png | 0
104 files changed, 269 insertions(+), 214 deletions(-)
diff --git a/Makefile b/Makefile
index 879a66d..14f4211 100644
--- a/Makefile
+++ b/Makefile
@@ -1,4 +1,4 @@
-GPU=0
+GPU=1
OPENCV=1
CUDNN=0
DEBUG=0
@@ -41,7 +41,7 @@
LDFLAGS+= -lcudnn
endif
-OBJ=gemm.o utils.o cuda.o deconvolutional_layer.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 imagenet.o captcha.o route_layer.o writing.o box.o nightmare.o normalization_layer.o avgpool_layer.o coco.o dice.o yolo.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 coco_demo.o tag.o cifar.o yolo_demo.o go.o batchnorm_layer.o art.o
+OBJ=gemm.o utils.o cuda.o deconvolutional_layer.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 imagenet.o captcha.o route_layer.o writing.o box.o nightmare.o normalization_layer.o avgpool_layer.o coco.o dice.o yolo.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
ifeq ($(GPU), 1)
LDFLAGS+= -lstdc++
OBJ+=convolutional_kernels.o deconvolutional_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 softmax_layer_kernels.o network_kernels.o avgpool_layer_kernels.o
diff --git a/cfg/yolo-coco.cfg b/cfg/yolo-coco.cfg
index 0c13a31..88438ae 100644
--- a/cfg/yolo-coco.cfg
+++ b/cfg/yolo-coco.cfg
@@ -1,6 +1,6 @@
[net]
-batch=64
-subdivisions=4
+batch=1
+subdivisions=1
height=448
width=448
channels=3
diff --git a/cfg/yolo.cfg b/cfg/yolo.cfg
index 8664831..1f69856 100644
--- a/cfg/yolo.cfg
+++ b/cfg/yolo.cfg
@@ -1,6 +1,6 @@
[net]
-batch=64
-subdivisions=64
+batch=1
+subdivisions=1
height=448
width=448
channels=3
@@ -13,14 +13,6 @@
scales=2.5,2,2,.1,.1
max_batches = 40000
-[crop]
-crop_width=448
-crop_height=448
-flip=0
-angle=0
-saturation = 1.5
-exposure = 1.5
-
[convolutional]
filters=64
size=7
@@ -211,9 +203,6 @@
output=4096
activation=leaky
-[dropout]
-probability=.5
-
[connected]
output= 1470
activation=linear
diff --git a/data/labels/aeroplane.png b/data/labels/aeroplane.png
index a939a2d..5b2f1d7 100644
--- a/data/labels/aeroplane.png
+++ b/data/labels/aeroplane.png
Binary files differ
diff --git a/data/labels/airplane.png b/data/labels/airplane.png
index fdcdec1..9a9ba89 100644
--- a/data/labels/airplane.png
+++ b/data/labels/airplane.png
Binary files differ
diff --git a/data/labels/apple.png b/data/labels/apple.png
index ead41ca..69f1b58 100644
--- a/data/labels/apple.png
+++ b/data/labels/apple.png
Binary files differ
diff --git a/data/labels/backpack.png b/data/labels/backpack.png
index a0d665f..32a9a4a 100644
--- a/data/labels/backpack.png
+++ b/data/labels/backpack.png
Binary files differ
diff --git a/data/labels/banana.png b/data/labels/banana.png
index 746a541..a77eac6 100644
--- a/data/labels/banana.png
+++ b/data/labels/banana.png
Binary files differ
diff --git a/data/labels/baseball bat.png b/data/labels/baseball bat.png
index 0c2a03d..134830e 100644
--- a/data/labels/baseball bat.png
+++ b/data/labels/baseball bat.png
Binary files differ
diff --git a/data/labels/baseball glove.png b/data/labels/baseball glove.png
index 0e562f2..4416e05 100644
--- a/data/labels/baseball glove.png
+++ b/data/labels/baseball glove.png
Binary files differ
diff --git a/data/labels/bear.png b/data/labels/bear.png
index f924210..2247068 100644
--- a/data/labels/bear.png
+++ b/data/labels/bear.png
Binary files differ
diff --git a/data/labels/bed.png b/data/labels/bed.png
index d590698..c316d70 100644
--- a/data/labels/bed.png
+++ b/data/labels/bed.png
Binary files differ
diff --git a/data/labels/bench.png b/data/labels/bench.png
index 65b5343..e8edceb 100644
--- a/data/labels/bench.png
+++ b/data/labels/bench.png
Binary files differ
diff --git a/data/labels/bicycle.png b/data/labels/bicycle.png
index 0576db1..6c2bfbc 100644
--- a/data/labels/bicycle.png
+++ b/data/labels/bicycle.png
Binary files differ
diff --git a/data/labels/bird.png b/data/labels/bird.png
index 1eac3d8..8d1510a 100644
--- a/data/labels/bird.png
+++ b/data/labels/bird.png
Binary files differ
diff --git a/data/labels/boat.png b/data/labels/boat.png
index f8e6cda..b43070e 100644
--- a/data/labels/boat.png
+++ b/data/labels/boat.png
Binary files differ
diff --git a/data/labels/book.png b/data/labels/book.png
index 46683b9..401b513 100644
--- a/data/labels/book.png
+++ b/data/labels/book.png
Binary files differ
diff --git a/data/labels/bottle.png b/data/labels/bottle.png
index e78961f..0410974 100644
--- a/data/labels/bottle.png
+++ b/data/labels/bottle.png
Binary files differ
diff --git a/data/labels/bowl.png b/data/labels/bowl.png
index cc4c136..da19ad9 100644
--- a/data/labels/bowl.png
+++ b/data/labels/bowl.png
Binary files differ
diff --git a/data/labels/broccoli.png b/data/labels/broccoli.png
index 8b114b2..c96bcfc 100644
--- a/data/labels/broccoli.png
+++ b/data/labels/broccoli.png
Binary files differ
diff --git a/data/labels/bus.png b/data/labels/bus.png
index bdd7a01..661d653 100644
--- a/data/labels/bus.png
+++ b/data/labels/bus.png
Binary files differ
diff --git a/data/labels/cake.png b/data/labels/cake.png
index 2994447..39b8ea5 100644
--- a/data/labels/cake.png
+++ b/data/labels/cake.png
Binary files differ
diff --git a/data/labels/car.png b/data/labels/car.png
index f3e5c2a..430637a 100644
--- a/data/labels/car.png
+++ b/data/labels/car.png
Binary files differ
diff --git a/data/labels/carrot.png b/data/labels/carrot.png
index 562749f..5fe7dd3 100644
--- a/data/labels/carrot.png
+++ b/data/labels/carrot.png
Binary files differ
diff --git a/data/labels/cat.png b/data/labels/cat.png
index 25ac630..6b46270 100644
--- a/data/labels/cat.png
+++ b/data/labels/cat.png
Binary files differ
diff --git a/data/labels/cell phone.png b/data/labels/cell phone.png
index e85c55f..40fee52 100644
--- a/data/labels/cell phone.png
+++ b/data/labels/cell phone.png
Binary files differ
diff --git a/data/labels/chair.png b/data/labels/chair.png
index 4178d45..f306c4b 100644
--- a/data/labels/chair.png
+++ b/data/labels/chair.png
Binary files differ
diff --git a/data/labels/clock.png b/data/labels/clock.png
index 082dafc..aacf1e9 100644
--- a/data/labels/clock.png
+++ b/data/labels/clock.png
Binary files differ
diff --git a/data/labels/couch.png b/data/labels/couch.png
index c2ae17f..94c0beb 100644
--- a/data/labels/couch.png
+++ b/data/labels/couch.png
Binary files differ
diff --git a/data/labels/cow.png b/data/labels/cow.png
index 53a3bb5..c908484 100644
--- a/data/labels/cow.png
+++ b/data/labels/cow.png
Binary files differ
diff --git a/data/labels/cup.png b/data/labels/cup.png
index f6b4dbd..67caab4 100644
--- a/data/labels/cup.png
+++ b/data/labels/cup.png
Binary files differ
diff --git a/data/labels/dining table.png b/data/labels/dining table.png
index 68a8f86..f5c173e 100644
--- a/data/labels/dining table.png
+++ b/data/labels/dining table.png
Binary files differ
diff --git a/data/labels/diningtable.png b/data/labels/diningtable.png
index 9e11cb1..6fb8ce9 100644
--- a/data/labels/diningtable.png
+++ b/data/labels/diningtable.png
Binary files differ
diff --git a/data/labels/dog.png b/data/labels/dog.png
index 10455f4..f5cf46b 100644
--- a/data/labels/dog.png
+++ b/data/labels/dog.png
Binary files differ
diff --git a/data/labels/donut.png b/data/labels/donut.png
index 1c89e6b..79c21f6 100644
--- a/data/labels/donut.png
+++ b/data/labels/donut.png
Binary files differ
diff --git a/data/labels/elephant.png b/data/labels/elephant.png
index 3680eb3..ca391e8 100644
--- a/data/labels/elephant.png
+++ b/data/labels/elephant.png
Binary files differ
diff --git a/data/labels/fire hydrant.png b/data/labels/fire hydrant.png
index 21ea272..f78bd90 100644
--- a/data/labels/fire hydrant.png
+++ b/data/labels/fire hydrant.png
Binary files differ
diff --git a/data/labels/fork.png b/data/labels/fork.png
index 2eb1e1d..06ce2b4 100644
--- a/data/labels/fork.png
+++ b/data/labels/fork.png
Binary files differ
diff --git a/data/labels/frisbee.png b/data/labels/frisbee.png
index d285f33..153ef9f 100644
--- a/data/labels/frisbee.png
+++ b/data/labels/frisbee.png
Binary files differ
diff --git a/data/labels/giraffe.png b/data/labels/giraffe.png
index 70dfbec..dedf3d6 100644
--- a/data/labels/giraffe.png
+++ b/data/labels/giraffe.png
Binary files differ
diff --git a/data/labels/hair drier.png b/data/labels/hair drier.png
index 69fcb5c..d015ed5 100644
--- a/data/labels/hair drier.png
+++ b/data/labels/hair drier.png
Binary files differ
diff --git a/data/labels/handbag.png b/data/labels/handbag.png
index f46a21b..7954984 100644
--- a/data/labels/handbag.png
+++ b/data/labels/handbag.png
Binary files differ
diff --git a/data/labels/horse.png b/data/labels/horse.png
index 9fefa40..b0df7c5 100644
--- a/data/labels/horse.png
+++ b/data/labels/horse.png
Binary files differ
diff --git a/data/labels/hot dog.png b/data/labels/hot dog.png
index 537bf77..5812a40 100644
--- a/data/labels/hot dog.png
+++ b/data/labels/hot dog.png
Binary files differ
diff --git a/data/labels/keyboard.png b/data/labels/keyboard.png
index f4a2232..3fb76c5 100644
--- a/data/labels/keyboard.png
+++ b/data/labels/keyboard.png
Binary files differ
diff --git a/data/labels/kite.png b/data/labels/kite.png
index 04629e2..b3b96e0 100644
--- a/data/labels/kite.png
+++ b/data/labels/kite.png
Binary files differ
diff --git a/data/labels/knife.png b/data/labels/knife.png
index ab563d8..28037e3 100644
--- a/data/labels/knife.png
+++ b/data/labels/knife.png
Binary files differ
diff --git a/data/labels/laptop.png b/data/labels/laptop.png
index d4ec1c5..55d95e8 100644
--- a/data/labels/laptop.png
+++ b/data/labels/laptop.png
Binary files differ
diff --git a/data/labels/microwave.png b/data/labels/microwave.png
index ffe97e7..4bb5326 100644
--- a/data/labels/microwave.png
+++ b/data/labels/microwave.png
Binary files differ
diff --git a/data/labels/motorbike.png b/data/labels/motorbike.png
index 1363f86..7091ca4 100644
--- a/data/labels/motorbike.png
+++ b/data/labels/motorbike.png
Binary files differ
diff --git a/data/labels/motorcycle.png b/data/labels/motorcycle.png
index 2f13ec4..fc8b0de 100644
--- a/data/labels/motorcycle.png
+++ b/data/labels/motorcycle.png
Binary files differ
diff --git a/data/labels/mouse.png b/data/labels/mouse.png
index 2fc818e..915a5f3 100644
--- a/data/labels/mouse.png
+++ b/data/labels/mouse.png
Binary files differ
diff --git a/data/labels/orange.png b/data/labels/orange.png
index 5eaf17f..9c4363e 100644
--- a/data/labels/orange.png
+++ b/data/labels/orange.png
Binary files differ
diff --git a/data/labels/oven.png b/data/labels/oven.png
index ba3f088..cd48c8b 100644
--- a/data/labels/oven.png
+++ b/data/labels/oven.png
Binary files differ
diff --git a/data/labels/parking meter.png b/data/labels/parking meter.png
index dfc3e96..afb6a7a 100644
--- a/data/labels/parking meter.png
+++ b/data/labels/parking meter.png
Binary files differ
diff --git a/data/labels/person.png b/data/labels/person.png
index 3763fb0..33a9666 100644
--- a/data/labels/person.png
+++ b/data/labels/person.png
Binary files differ
diff --git a/data/labels/pizza.png b/data/labels/pizza.png
index 7ca82d5..a08c016 100644
--- a/data/labels/pizza.png
+++ b/data/labels/pizza.png
Binary files differ
diff --git a/data/labels/potted plant.png b/data/labels/potted plant.png
index 00c2c0f..07bb49c 100644
--- a/data/labels/potted plant.png
+++ b/data/labels/potted plant.png
Binary files differ
diff --git a/data/labels/pottedplant.png b/data/labels/pottedplant.png
index 4b054c5..569b86b 100644
--- a/data/labels/pottedplant.png
+++ b/data/labels/pottedplant.png
Binary files differ
diff --git a/data/labels/refrigerator.png b/data/labels/refrigerator.png
index 0e54f3c..0f8c959 100644
--- a/data/labels/refrigerator.png
+++ b/data/labels/refrigerator.png
Binary files differ
diff --git a/data/labels/remote.png b/data/labels/remote.png
index a706e68..714893b 100644
--- a/data/labels/remote.png
+++ b/data/labels/remote.png
Binary files differ
diff --git a/data/labels/sandwich.png b/data/labels/sandwich.png
index 717021a..5d2d77e 100644
--- a/data/labels/sandwich.png
+++ b/data/labels/sandwich.png
Binary files differ
diff --git a/data/labels/scissors.png b/data/labels/scissors.png
index 2c58d0f..b5583c8 100644
--- a/data/labels/scissors.png
+++ b/data/labels/scissors.png
Binary files differ
diff --git a/data/labels/sheep.png b/data/labels/sheep.png
index dc3e5ee..2b32bf8 100644
--- a/data/labels/sheep.png
+++ b/data/labels/sheep.png
Binary files differ
diff --git a/data/labels/sink.png b/data/labels/sink.png
index 4053cd6..d97981e 100644
--- a/data/labels/sink.png
+++ b/data/labels/sink.png
Binary files differ
diff --git a/data/labels/skateboard.png b/data/labels/skateboard.png
index cbb4c94..e5df255 100644
--- a/data/labels/skateboard.png
+++ b/data/labels/skateboard.png
Binary files differ
diff --git a/data/labels/skis.png b/data/labels/skis.png
index 4b7f65f..f222197 100644
--- a/data/labels/skis.png
+++ b/data/labels/skis.png
Binary files differ
diff --git a/data/labels/snowboard.png b/data/labels/snowboard.png
index 2703ce1..8c2b06c 100644
--- a/data/labels/snowboard.png
+++ b/data/labels/snowboard.png
Binary files differ
diff --git a/data/labels/sofa.png b/data/labels/sofa.png
index 5aeea31..a555a31 100644
--- a/data/labels/sofa.png
+++ b/data/labels/sofa.png
Binary files differ
diff --git a/data/labels/spoon.png b/data/labels/spoon.png
index ebc2d9f..127dfd1 100644
--- a/data/labels/spoon.png
+++ b/data/labels/spoon.png
Binary files differ
diff --git a/data/labels/sports ball.png b/data/labels/sports ball.png
index 1a92e7e..957d37a 100644
--- a/data/labels/sports ball.png
+++ b/data/labels/sports ball.png
Binary files differ
diff --git a/data/labels/stop sign.png b/data/labels/stop sign.png
index cdeb932..e32e371 100644
--- a/data/labels/stop sign.png
+++ b/data/labels/stop sign.png
Binary files differ
diff --git a/data/labels/suitcase.png b/data/labels/suitcase.png
index 4c3231b..c5b3898 100644
--- a/data/labels/suitcase.png
+++ b/data/labels/suitcase.png
Binary files differ
diff --git a/data/labels/surfboard.png b/data/labels/surfboard.png
index 257b0eb..adbc0d9 100644
--- a/data/labels/surfboard.png
+++ b/data/labels/surfboard.png
Binary files differ
diff --git a/data/labels/teddy bear.png b/data/labels/teddy bear.png
index c0ea2cc..b79fb20 100644
--- a/data/labels/teddy bear.png
+++ b/data/labels/teddy bear.png
Binary files differ
diff --git a/data/labels/tennis racket.png b/data/labels/tennis racket.png
index 95bfb14..2390718 100644
--- a/data/labels/tennis racket.png
+++ b/data/labels/tennis racket.png
Binary files differ
diff --git a/data/labels/tie.png b/data/labels/tie.png
index 16ac404..a547fad 100644
--- a/data/labels/tie.png
+++ b/data/labels/tie.png
Binary files differ
diff --git a/data/labels/toaster.png b/data/labels/toaster.png
index e87e076..4c59a91 100644
--- a/data/labels/toaster.png
+++ b/data/labels/toaster.png
Binary files differ
diff --git a/data/labels/toilet.png b/data/labels/toilet.png
index f2a0274..c7aa726 100644
--- a/data/labels/toilet.png
+++ b/data/labels/toilet.png
Binary files differ
diff --git a/data/labels/toothbrush.png b/data/labels/toothbrush.png
index 2f943ed..67877b0 100644
--- a/data/labels/toothbrush.png
+++ b/data/labels/toothbrush.png
Binary files differ
diff --git a/data/labels/traffic light.png b/data/labels/traffic light.png
index ef8aa18..bd1e7c9 100644
--- a/data/labels/traffic light.png
+++ b/data/labels/traffic light.png
Binary files differ
diff --git a/data/labels/train.png b/data/labels/train.png
index ee216d2..ec6d0dd 100644
--- a/data/labels/train.png
+++ b/data/labels/train.png
Binary files differ
diff --git a/data/labels/truck.png b/data/labels/truck.png
index e00f6a1..e6173f2 100644
--- a/data/labels/truck.png
+++ b/data/labels/truck.png
Binary files differ
diff --git a/data/labels/tv.png b/data/labels/tv.png
index 929a43b..92b23c3 100644
--- a/data/labels/tv.png
+++ b/data/labels/tv.png
Binary files differ
diff --git a/data/labels/tvmonitor.png b/data/labels/tvmonitor.png
index ff27a7a..2250e41 100644
--- a/data/labels/tvmonitor.png
+++ b/data/labels/tvmonitor.png
Binary files differ
diff --git a/data/labels/umbrella.png b/data/labels/umbrella.png
index 05de2d9..4e32d8b 100644
--- a/data/labels/umbrella.png
+++ b/data/labels/umbrella.png
Binary files differ
diff --git a/data/labels/vase.png b/data/labels/vase.png
index a4a3f15..54cdf07 100644
--- a/data/labels/vase.png
+++ b/data/labels/vase.png
Binary files differ
diff --git a/data/labels/wine glass.png b/data/labels/wine glass.png
index 2c00a75..1cac27d 100644
--- a/data/labels/wine glass.png
+++ b/data/labels/wine glass.png
Binary files differ
diff --git a/data/labels/zebra.png b/data/labels/zebra.png
index feb1ca0..a05c115 100644
--- a/data/labels/zebra.png
+++ b/data/labels/zebra.png
Binary files differ
diff --git a/src/activation_kernels.cu b/src/activation_kernels.cu
index 362d5d7..5d61529 100644
--- a/src/activation_kernels.cu
+++ b/src/activation_kernels.cu
@@ -8,6 +8,18 @@
}
+__device__ float lhtan_activate_kernel(float x)
+{
+ if(x < 0) return .001*x;
+ if(x > 1) return .001*(x-1) + 1;
+ return x;
+}
+__device__ float lhtan_gradient_kernel(float x)
+{
+ if(x > 0 && x < 1) return 1;
+ return .001;
+}
+
__device__ float hardtan_activate_kernel(float x)
{
if (x < -1) return -1;
@@ -89,6 +101,8 @@
return stair_activate_kernel(x);
case HARDTAN:
return hardtan_activate_kernel(x);
+ case LHTAN:
+ return lhtan_activate_kernel(x);
}
return 0;
}
@@ -120,6 +134,8 @@
return stair_gradient_kernel(x);
case HARDTAN:
return hardtan_gradient_kernel(x);
+ case LHTAN:
+ return lhtan_gradient_kernel(x);
}
return 0;
}
diff --git a/src/activations.c b/src/activations.c
index 6ab4963..0cbb2f5 100644
--- a/src/activations.c
+++ b/src/activations.c
@@ -32,6 +32,8 @@
return "stair";
case HARDTAN:
return "hardtan";
+ case LHTAN:
+ return "lhtan";
default:
break;
}
@@ -47,6 +49,7 @@
if (strcmp(s, "relie")==0) return RELIE;
if (strcmp(s, "plse")==0) return PLSE;
if (strcmp(s, "hardtan")==0) return HARDTAN;
+ if (strcmp(s, "lhtan")==0) return LHTAN;
if (strcmp(s, "linear")==0) return LINEAR;
if (strcmp(s, "ramp")==0) return RAMP;
if (strcmp(s, "leaky")==0) return LEAKY;
@@ -83,6 +86,8 @@
return stair_activate(x);
case HARDTAN:
return hardtan_activate(x);
+ case LHTAN:
+ return lhtan_activate(x);
}
return 0;
}
@@ -122,6 +127,8 @@
return stair_gradient(x);
case HARDTAN:
return hardtan_gradient(x);
+ case LHTAN:
+ return lhtan_gradient(x);
}
return 0;
}
diff --git a/src/activations.h b/src/activations.h
index fed2908..d1b8c37 100644
--- a/src/activations.h
+++ b/src/activations.h
@@ -4,7 +4,7 @@
#include "math.h"
typedef enum{
- LOGISTIC, RELU, RELIE, LINEAR, RAMP, TANH, PLSE, LEAKY, ELU, LOGGY, STAIR, HARDTAN
+ LOGISTIC, RELU, RELIE, LINEAR, RAMP, TANH, PLSE, LEAKY, ELU, LOGGY, STAIR, HARDTAN, LHTAN
}ACTIVATION;
ACTIVATION get_activation(char *s);
@@ -47,6 +47,18 @@
return .125*x + .5;
}
+static inline float lhtan_activate(float x)
+{
+ if(x < 0) return .001*x;
+ if(x > 1) return .001*(x-1) + 1;
+ return x;
+}
+static inline float lhtan_gradient(float x)
+{
+ if(x > 0 && x < 1) return 1;
+ return .001;
+}
+
static inline float hardtan_gradient(float x)
{
if (x > -1 && x < 1) return 1;
diff --git a/src/coco.c b/src/coco.c
index 947bef2..43feb7d 100644
--- a/src/coco.c
+++ b/src/coco.c
@@ -6,11 +6,14 @@
#include "utils.h"
#include "parser.h"
#include "box.h"
+#include "demo.h"
#ifdef OPENCV
#include "opencv2/highgui/highgui_c.h"
#endif
+void convert_detections(float *predictions, int classes, int num, int square, int side, int w, int h, float thresh, float **probs, box *boxes, int only_objectness);
+
char *coco_classes[] = {"person","bicycle","car","motorcycle","airplane","bus","train","truck","boat","traffic light","fire hydrant","stop sign","parking meter","bench","bird","cat","dog","horse","sheep","cow","elephant","bear","zebra","giraffe","backpack","umbrella","handbag","tie","suitcase","frisbee","skis","snowboard","sports ball","kite","baseball bat","baseball glove","skateboard","surfboard","tennis racket","bottle","wine glass","cup","fork","knife","spoon","bowl","banana","apple","sandwich","orange","broccoli","carrot","hot dog","pizza","donut","cake","chair","couch","potted plant","bed","dining table","toilet","tv","laptop","mouse","remote","keyboard","cell phone","microwave","oven","toaster","sink","refrigerator","book","clock","vase","scissors","teddy bear","hair drier","toothbrush"};
int coco_ids[] = {1,2,3,4,5,6,7,8,9,10,11,13,14,15,16,17,18,19,20,21,22,23,24,25,27,28,31,32,33,34,35,36,37,38,39,40,41,42,43,44,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,67,70,72,73,74,75,76,77,78,79,80,81,82,84,85,86,87,88,89,90};
@@ -98,34 +101,6 @@
save_weights(net, buff);
}
-void convert_coco_detections(float *predictions, int classes, int num, int square, int side, int w, int h, float thresh, float **probs, box *boxes, int only_objectness)
-{
- int i,j,n;
- //int per_cell = 5*num+classes;
- for (i = 0; i < side*side; ++i){
- int row = i / side;
- int col = i % side;
- for(n = 0; n < num; ++n){
- int index = i*num + n;
- int p_index = side*side*classes + i*num + n;
- float scale = predictions[p_index];
- int box_index = side*side*(classes + num) + (i*num + n)*4;
- boxes[index].x = (predictions[box_index + 0] + col) / side * w;
- boxes[index].y = (predictions[box_index + 1] + row) / side * h;
- boxes[index].w = pow(predictions[box_index + 2], (square?2:1)) * w;
- boxes[index].h = pow(predictions[box_index + 3], (square?2:1)) * h;
- for(j = 0; j < classes; ++j){
- int class_index = i*classes;
- float prob = scale*predictions[class_index+j];
- probs[index][j] = (prob > thresh) ? prob : 0;
- }
- if(only_objectness){
- probs[index][0] = scale;
- }
- }
- }
-}
-
void print_cocos(FILE *fp, int image_id, box *boxes, float **probs, int num_boxes, int classes, int w, int h)
{
int i, j;
@@ -235,7 +210,7 @@
float *predictions = network_predict(net, X);
int w = val[t].w;
int h = val[t].h;
- convert_coco_detections(predictions, classes, l.n, square, side, w, h, thresh, probs, boxes, 0);
+ convert_detections(predictions, classes, l.n, square, side, w, h, thresh, probs, boxes, 0);
if (nms) do_nms_sort(boxes, probs, side*side*l.n, classes, iou_thresh);
print_cocos(fp, image_id, boxes, probs, side*side*l.n, classes, w, h);
free_image(val[t]);
@@ -298,7 +273,7 @@
image sized = resize_image(orig, net.w, net.h);
char *id = basecfg(path);
float *predictions = network_predict(net, sized.data);
- convert_coco_detections(predictions, classes, l.n, square, side, 1, 1, thresh, probs, boxes, 1);
+ convert_detections(predictions, classes, l.n, square, side, 1, 1, thresh, probs, boxes, 1);
if (nms) do_nms(boxes, probs, side*side*l.n, 1, nms_thresh);
char *labelpath = find_replace(path, "images", "labels");
@@ -370,7 +345,7 @@
time=clock();
float *predictions = network_predict(net, X);
printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
- convert_coco_detections(predictions, l.classes, l.n, l.sqrt, l.side, 1, 1, thresh, probs, boxes, 0);
+ convert_detections(predictions, l.classes, l.n, l.sqrt, l.side, 1, 1, thresh, probs, boxes, 0);
if (nms) do_nms_sort(boxes, probs, l.side*l.side*l.n, l.classes, nms);
draw_detections(im, l.side*l.side*l.n, thresh, boxes, probs, coco_classes, coco_labels, 80);
show_image(im, "predictions");
@@ -386,16 +361,6 @@
}
}
-void demo_coco(char *cfgfile, char *weightfile, float thresh, int cam_index, char *filename);
-static void demo(char *cfgfile, char *weightfile, float thresh, int cam_index, char* filename)
-{
- #if defined(OPENCV)
- demo_coco(cfgfile, weightfile, thresh, cam_index, filename);
- #else
- fprintf(stderr, "Need to compile with OpenCV for demo.\n");
- #endif
-}
-
void run_coco(int argc, char **argv)
{
int i;
@@ -406,7 +371,6 @@
}
float thresh = find_float_arg(argc, argv, "-thresh", .2);
int cam_index = find_int_arg(argc, argv, "-c", 0);
- char *file = find_char_arg(argc, argv, "-file", 0);
if(argc < 4){
fprintf(stderr, "usage: %s %s [train/test/valid] [cfg] [weights (optional)]\n", argv[0], argv[1]);
@@ -420,5 +384,5 @@
else if(0==strcmp(argv[2], "train")) train_coco(cfg, weights);
else if(0==strcmp(argv[2], "valid")) validate_coco(cfg, weights);
else if(0==strcmp(argv[2], "recall")) validate_coco_recall(cfg, weights);
- else if(0==strcmp(argv[2], "demo")) demo(cfg, weights, thresh, cam_index, file);
+ else if(0==strcmp(argv[2], "demo")) demo(cfg, weights, thresh, cam_index, filename, coco_classes, coco_labels, 80);
}
diff --git a/src/coco_demo.c b/src/coco_demo.c
deleted file mode 100644
index 370516d..0000000
--- a/src/coco_demo.c
+++ /dev/null
@@ -1,161 +0,0 @@
-#include "network.h"
-#include "detection_layer.h"
-#include "cost_layer.h"
-#include "utils.h"
-#include "parser.h"
-#include "box.h"
-#include "image.h"
-#include <sys/time.h>
-
-#define FRAMES 1
-
-#ifdef OPENCV
-#include "opencv2/highgui/highgui_c.h"
-#include "opencv2/imgproc/imgproc_c.h"
-void convert_coco_detections(float *predictions, int classes, int num, int square, int side, int w, int h, float thresh, float **probs, box *boxes, int only_objectness);
-
-extern char *coco_classes[];
-extern image coco_labels[];
-
-static float **probs;
-static box *boxes;
-static network net;
-static image in ;
-static image in_s ;
-static image det ;
-static image det_s;
-static image disp ;
-static CvCapture * cap;
-static float fps = 0;
-static float demo_thresh = 0;
-
-static float *predictions[FRAMES];
-static int demo_index = 0;
-static image images[FRAMES];
-static float *avg;
-
-void *fetch_in_thread_coco(void *ptr)
-{
- in = get_image_from_stream(cap);
- in_s = resize_image(in, net.w, net.h);
- return 0;
-}
-
-void *detect_in_thread_coco(void *ptr)
-{
- float nms = .4;
-
- detection_layer l = net.layers[net.n-1];
- float *X = det_s.data;
- float *prediction = network_predict(net, X);
-
- memcpy(predictions[demo_index], prediction, l.outputs*sizeof(float));
- mean_arrays(predictions, FRAMES, l.outputs, avg);
-
- free_image(det_s);
- convert_coco_detections(avg, l.classes, l.n, l.sqrt, l.side, 1, 1, demo_thresh, probs, boxes, 0);
- if (nms > 0) do_nms(boxes, probs, l.side*l.side*l.n, l.classes, nms);
- printf("\033[2J");
- printf("\033[1;1H");
- printf("\nFPS:%.0f\n",fps);
- printf("Objects:\n\n");
-
- images[demo_index] = det;
- det = images[(demo_index + FRAMES/2 + 1)%FRAMES];
- demo_index = (demo_index + 1)%FRAMES;
-
- draw_detections(det, l.side*l.side*l.n, demo_thresh, boxes, probs, coco_classes, coco_labels, 80);
- return 0;
-}
-
-void demo_coco(char *cfgfile, char *weightfile, float thresh, int cam_index, const char *filename)
-{
- demo_thresh = thresh;
- printf("COCO demo\n");
- net = parse_network_cfg(cfgfile);
- if(weightfile){
- load_weights(&net, weightfile);
- }
- set_batch_network(&net, 1);
-
- srand(2222222);
-
- if(filename){
- cap = cvCaptureFromFile(filename);
- }else{
- cap = cvCaptureFromCAM(cam_index);
- }
-
- if(!cap) error("Couldn't connect to webcam.\n");
-
- detection_layer l = net.layers[net.n-1];
- int j;
-
- avg = (float *) calloc(l.outputs, sizeof(float));
- for(j = 0; j < FRAMES; ++j) predictions[j] = (float *) calloc(l.outputs, sizeof(float));
- for(j = 0; j < FRAMES; ++j) images[j] = make_image(1,1,3);
-
- boxes = (box *)calloc(l.side*l.side*l.n, sizeof(box));
- probs = (float **)calloc(l.side*l.side*l.n, sizeof(float *));
- for(j = 0; j < l.side*l.side*l.n; ++j) probs[j] = (float *)calloc(l.classes, sizeof(float *));
-
- pthread_t fetch_thread;
- pthread_t detect_thread;
-
- fetch_in_thread_coco(0);
- det = in;
- det_s = in_s;
-
- fetch_in_thread_coco(0);
- detect_in_thread_coco(0);
- disp = det;
- det = in;
- det_s = in_s;
-
- for(j = 0; j < FRAMES/2; ++j){
- fetch_in_thread_coco(0);
- detect_in_thread_coco(0);
- disp = det;
- det = in;
- det_s = in_s;
- }
-
- int count = 0;
- cvNamedWindow("COCO", CV_WINDOW_NORMAL);
- cvMoveWindow("COCO", 0, 0);
- cvResizeWindow("COCO", 1352, 1013);
-
- while(1){
- ++count;
- struct timeval tval_before, tval_after, tval_result;
- gettimeofday(&tval_before, NULL);
- if(pthread_create(&fetch_thread, 0, fetch_in_thread_coco, 0)) error("Thread creation failed");
- if(pthread_create(&detect_thread, 0, detect_in_thread_coco, 0)) error("Thread creation failed");
- show_image(disp, "COCO");
- /*
- char buff[256];
- sprintf(buff, "/home/pjreddie/coco/coco_%05d", count);
- save_image(disp, buff);
- */
-
- free_image(disp);
- cvWaitKey(10);
- pthread_join(fetch_thread, 0);
- pthread_join(detect_thread, 0);
-
- disp = det;
- det = in;
- det_s = in_s;
-
- gettimeofday(&tval_after, NULL);
- timersub(&tval_after, &tval_before, &tval_result);
- float curr = 1000000.f/((long int)tval_result.tv_usec);
- fps = .9*fps + .1*curr;
- }
-}
-#else
-void demo_coco(char *cfgfile, char *weightfile, float thresh, int cam_index){
- fprintf(stderr, "YOLO-COCO demo needs OpenCV for webcam images.\n");
-}
-#endif
-
diff --git a/src/convolutional_kernels.cu b/src/convolutional_kernels.cu
index 2376835..96398df 100644
--- a/src/convolutional_kernels.cu
+++ b/src/convolutional_kernels.cu
@@ -71,8 +71,6 @@
void forward_convolutional_layer_gpu(convolutional_layer l, network_state state)
{
- int i;
-
fill_ongpu(l.outputs*l.batch, 0, l.output_gpu, 1);
if(l.binary){
binarize_filters_gpu(l.filters_gpu, l.n, l.c*l.size*l.size, l.binary_filters_gpu);
@@ -103,6 +101,7 @@
l.output_gpu);
#else
+ int i;
int m = l.n;
int k = l.size*l.size*l.c;
int n = l.out_w*l.out_h;
diff --git a/src/demo.c b/src/demo.c
new file mode 100644
index 0000000..d05ff6b
--- /dev/null
+++ b/src/demo.c
@@ -0,0 +1,198 @@
+#include "network.h"
+#include "detection_layer.h"
+#include "cost_layer.h"
+#include "utils.h"
+#include "parser.h"
+#include "box.h"
+#include "image.h"
+#include "demo.h"
+#include <sys/time.h>
+
+#define FRAMES 3
+
+#ifdef OPENCV
+#include "opencv2/highgui/highgui_c.h"
+#include "opencv2/imgproc/imgproc_c.h"
+void convert_detections(float *predictions, int classes, int num, int square, int side, int w, int h, float thresh, float **probs, box *boxes, int only_objectness);
+
+#define DELAY 0
+static int delay = DELAY;
+
+static char **demo_names;
+static image *demo_labels;
+static int demo_classes;
+
+static float **probs;
+static box *boxes;
+static network net;
+static image in ;
+static image in_s ;
+static image det ;
+static image det_s;
+static image disp = {0};
+static CvCapture * cap;
+static float fps = 0;
+static float demo_thresh = 0;
+
+static float *predictions[FRAMES];
+static int demo_index = 0;
+static image images[FRAMES];
+static float *avg;
+
+void *fetch_in_thread(void *ptr)
+{
+ in = get_image_from_stream(cap);
+ if(!in.data){
+ in = disp;
+ if(delay == DELAY) error("Stream closed.");
+ }else{
+ if(disp.data){
+ free_image(disp);
+ }
+ in_s = resize_image(in, net.w, net.h);
+ }
+ return 0;
+}
+
+void *detect_in_thread(void *ptr)
+{
+ float nms = .4;
+
+ detection_layer l = net.layers[net.n-1];
+ float *X = det_s.data;
+ float *prediction = network_predict(net, X);
+
+ memcpy(predictions[demo_index], prediction, l.outputs*sizeof(float));
+ if(delay == DELAY){
+ mean_arrays(predictions, FRAMES, l.outputs, avg);
+ }
+
+ free_image(det_s);
+ convert_detections(avg, l.classes, l.n, l.sqrt, l.side, 1, 1, demo_thresh, probs, boxes, 0);
+ if (nms > 0) do_nms(boxes, probs, l.side*l.side*l.n, l.classes, nms);
+ printf("\033[2J");
+ printf("\033[1;1H");
+ printf("\nFPS:%.1f\n",fps);
+ printf("Objects:\n\n");
+
+ images[demo_index] = det;
+ det = images[(demo_index + FRAMES/2 + 1)%FRAMES];
+ demo_index = (demo_index + 1)%FRAMES;
+
+ draw_detections(det, l.side*l.side*l.n, demo_thresh, boxes, probs, demo_names, demo_labels, demo_classes);
+ if(delay == 0){
+ delay = DELAY;
+ } else {
+ --delay;
+ }
+ return 0;
+}
+
+double get_wall_time()
+{
+ struct timeval time;
+ if (gettimeofday(&time,NULL)){
+ return 0;
+ }
+ return (double)time.tv_sec + (double)time.tv_usec * .000001;
+}
+
+void demo(char *cfgfile, char *weightfile, float thresh, int cam_index, const char *filename, char **names, image *labels, int classes)
+{
+ demo_names = names;
+ demo_labels = labels;
+ demo_classes = classes;
+ demo_thresh = thresh;
+ printf("Demo\n");
+ net = parse_network_cfg(cfgfile);
+ if(weightfile){
+ load_weights(&net, weightfile);
+ }
+ set_batch_network(&net, 1);
+
+ srand(2222222);
+
+ if(filename){
+ cap = cvCaptureFromFile(filename);
+ }else{
+ cap = cvCaptureFromCAM(cam_index);
+ }
+
+ if(!cap) error("Couldn't connect to webcam.\n");
+
+ detection_layer l = net.layers[net.n-1];
+ int j;
+
+ avg = (float *) calloc(l.outputs, sizeof(float));
+ for(j = 0; j < FRAMES; ++j) predictions[j] = (float *) calloc(l.outputs, sizeof(float));
+ for(j = 0; j < FRAMES; ++j) images[j] = make_image(1,1,3);
+
+ boxes = (box *)calloc(l.side*l.side*l.n, sizeof(box));
+ probs = (float **)calloc(l.side*l.side*l.n, sizeof(float *));
+ for(j = 0; j < l.side*l.side*l.n; ++j) probs[j] = (float *)calloc(l.classes, sizeof(float *));
+
+ pthread_t fetch_thread;
+ pthread_t detect_thread;
+
+ fetch_in_thread(0);
+ det = in;
+ det_s = in_s;
+
+ fetch_in_thread(0);
+ detect_in_thread(0);
+ disp = det;
+ det = in;
+ det_s = in_s;
+
+ for(j = 0; j < FRAMES/2; ++j){
+ fetch_in_thread(0);
+ detect_in_thread(0);
+ disp = det;
+ det = in;
+ det_s = in_s;
+ }
+
+ int count = 0;
+ cvNamedWindow("Demo", CV_WINDOW_NORMAL);
+ cvMoveWindow("Demo", 0, 0);
+ cvResizeWindow("Demo", 1352, 1013);
+
+ double before = get_wall_time();
+
+ while(1){
+ ++count;
+ if(pthread_create(&fetch_thread, 0, fetch_in_thread, 0)) error("Thread creation failed");
+ if(pthread_create(&detect_thread, 0, detect_in_thread, 0)) error("Thread creation failed");
+ //fetch_in_thread(0);
+ //detect_in_thread(0);
+
+ show_image(disp, "Demo");
+ cvWaitKey(1);
+ //char buff[256];
+ //sprintf(buff, "coco/coco_%05d", count);
+ //save_image(disp, buff);
+
+ //free_image(disp);
+ //cvWaitKey(10);
+ pthread_join(fetch_thread, 0);
+ pthread_join(detect_thread, 0);
+
+ disp = det;
+ det = in;
+ det_s = in_s;
+
+ if(delay == DELAY){
+ double after = get_wall_time();
+ float curr = 1./(after - before);
+ fps = curr;
+ before = after;
+ }
+ }
+}
+#else
+void demo(char *cfgfile, char *weightfile, float thresh, int cam_index, const char *filename, char **names, image *labels, int classes)
+{
+ fprintf(stderr, "Demo needs OpenCV for webcam images.\n");
+}
+#endif
+
diff --git a/src/demo.h b/src/demo.h
new file mode 100644
index 0000000..1a091cd
--- /dev/null
+++ b/src/demo.h
@@ -0,0 +1,7 @@
+#ifndef DEMO
+#define DEMO
+
+#include "image.h"
+void demo(char *cfgfile, char *weightfile, float thresh, int cam_index, const char *filename, char **names, image *labels, int classes);
+
+#endif
diff --git a/src/detection_layer.c b/src/detection_layer.c
index 1b0f126..8b4045a 100644
--- a/src/detection_layer.c
+++ b/src/detection_layer.c
@@ -53,8 +53,6 @@
softmax_array(l.output + index + offset, l.classes, 1,
l.output + index + offset);
}
- int offset = locations*l.classes;
- activate_array(l.output + index + offset, locations*l.n*(1+l.coords), LOGISTIC);
}
}
if(state.train){
@@ -133,11 +131,9 @@
best_index = 0;
}
}
- /*
- if(1 && *(state.net.seen) < 100000){
+ if(l.random && *(state.net.seen) < 64000){
best_index = rand()%l.n;
}
- */
int box_index = index + locations*(l.classes + l.n) + (i*l.n + best_index) * l.coords;
int tbox_index = truth_index + 1 + l.classes;
@@ -175,10 +171,6 @@
avg_iou += iou;
++count;
}
- if(l.softmax){
- gradient_array(l.output + index + locations*l.classes, locations*l.n*(1+l.coords),
- LOGISTIC, l.delta + index + locations*l.classes);
- }
}
if(0){
@@ -208,6 +200,7 @@
}
+ *(l.cost) = pow(mag_array(l.delta, l.outputs * l.batch), 2);
printf("Detection Avg IOU: %f, Pos Cat: %f, All Cat: %f, Pos Obj: %f, Any Obj: %f, count: %d\n", avg_iou/count, avg_cat/count, avg_allcat/(count*l.classes), avg_obj/count, avg_anyobj/(l.batch*locations*l.n), count);
diff --git a/src/image.c b/src/image.c
index 92833df..0309ef1 100644
--- a/src/image.c
+++ b/src/image.c
@@ -365,6 +365,7 @@
image get_image_from_stream(CvCapture *cap)
{
IplImage* src = cvQueryFrame(cap);
+ if (!src) return make_empty_image(0,0,0);
image im = ipl_to_image(src);
rgbgr_image(im);
return im;
diff --git a/src/layer.h b/src/layer.h
index 0c457f7..18f98c7 100644
--- a/src/layer.h
+++ b/src/layer.h
@@ -88,6 +88,7 @@
float object_scale;
float noobject_scale;
float class_scale;
+ int random;
int dontload;
int dontloadscales;
diff --git a/src/network.c b/src/network.c
index 51f74d9..a9e5027 100644
--- a/src/network.c
+++ b/src/network.c
@@ -64,6 +64,7 @@
case EXP:
return net.learning_rate * pow(net.gamma, batch_num);
case POLY:
+ if (batch_num < net.burn_in) return net.learning_rate * pow((float)batch_num / net.burn_in, net.power);
return net.learning_rate * pow(1 - (float)batch_num / net.max_batches, net.power);
case RANDOM:
return net.learning_rate * pow(rand_uniform(0,1), net.power);
diff --git a/src/network.h b/src/network.h
index 15b58b8..af64e06 100644
--- a/src/network.h
+++ b/src/network.h
@@ -34,6 +34,7 @@
float *scales;
int *steps;
int num_steps;
+ int burn_in;
int inputs;
int h, w, c;
diff --git a/src/parser.c b/src/parser.c
index 71f54cc..1e5be4d 100644
--- a/src/parser.c
+++ b/src/parser.c
@@ -264,6 +264,7 @@
layer.noobject_scale = option_find_float(options, "noobject_scale", 1);
layer.class_scale = option_find_float(options, "class_scale", 1);
layer.jitter = option_find_float(options, "jitter", .2);
+ layer.random = option_find_int_quiet(options, "random", 0);
return layer;
}
@@ -467,6 +468,7 @@
char *policy_s = option_find_str(options, "policy", "constant");
net->policy = get_policy(policy_s);
+ net->burn_in = option_find_int_quiet(options, "burn_in", 0);
if(net->policy == STEP){
net->step = option_find_int(options, "step", 1);
net->scale = option_find_float(options, "scale", 1);
diff --git a/src/yolo.c b/src/yolo.c
index 2b99935..057abcf 100644
--- a/src/yolo.c
+++ b/src/yolo.c
@@ -4,6 +4,7 @@
#include "utils.h"
#include "parser.h"
#include "box.h"
+#include "demo.h"
#ifdef OPENCV
#include "opencv2/highgui/highgui_c.h"
@@ -83,7 +84,7 @@
save_weights(net, buff);
}
-void convert_yolo_detections(float *predictions, int classes, int num, int square, int side, int w, int h, float thresh, float **probs, box *boxes, int only_objectness)
+void convert_detections(float *predictions, int classes, int num, int square, int side, int w, int h, float thresh, float **probs, box *boxes, int only_objectness)
{
int i,j,n;
//int per_cell = 5*num+classes;
@@ -211,7 +212,7 @@
float *predictions = network_predict(net, X);
int w = val[t].w;
int h = val[t].h;
- convert_yolo_detections(predictions, classes, l.n, square, side, w, h, thresh, probs, boxes, 0);
+ convert_detections(predictions, classes, l.n, square, side, w, h, thresh, probs, boxes, 0);
if (nms) do_nms_sort(boxes, probs, side*side*l.n, classes, iou_thresh);
print_yolo_detections(fps, id, boxes, probs, side*side*l.n, classes, w, h);
free(id);
@@ -270,7 +271,7 @@
image sized = resize_image(orig, net.w, net.h);
char *id = basecfg(path);
float *predictions = network_predict(net, sized.data);
- convert_yolo_detections(predictions, classes, l.n, square, side, 1, 1, thresh, probs, boxes, 1);
+ convert_detections(predictions, classes, l.n, square, side, 1, 1, thresh, probs, boxes, 1);
if (nms) do_nms(boxes, probs, side*side*l.n, 1, nms);
char *labelpath = find_replace(path, "images", "labels");
@@ -342,7 +343,7 @@
time=clock();
float *predictions = network_predict(net, X);
printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
- convert_yolo_detections(predictions, l.classes, l.n, l.sqrt, l.side, 1, 1, thresh, probs, boxes, 0);
+ convert_detections(predictions, l.classes, l.n, l.sqrt, l.side, 1, 1, thresh, probs, boxes, 0);
if (nms) do_nms_sort(boxes, probs, l.side*l.side*l.n, l.classes, nms);
//draw_detections(im, l.side*l.side*l.n, thresh, boxes, probs, voc_names, voc_labels, 20);
draw_detections(im, l.side*l.side*l.n, thresh, boxes, probs, voc_names, voc_labels, 20);
@@ -360,8 +361,6 @@
}
}
-void demo_yolo(char *cfgfile, char *weightfile, float thresh, int cam_index, char *filename);
-
void run_yolo(int argc, char **argv)
{
int i;
@@ -385,5 +384,5 @@
else if(0==strcmp(argv[2], "train")) train_yolo(cfg, weights);
else if(0==strcmp(argv[2], "valid")) validate_yolo(cfg, weights);
else if(0==strcmp(argv[2], "recall")) validate_yolo_recall(cfg, weights);
- else if(0==strcmp(argv[2], "demo")) demo_yolo(cfg, weights, thresh, cam_index, filename);
+ else if(0==strcmp(argv[2], "demo")) demo(cfg, weights, thresh, cam_index, filename, voc_names, voc_labels, 20);
}
diff --git a/src/yolo_demo.c b/src/yolo_demo.c
deleted file mode 100644
index 377218d..0000000
--- a/src/yolo_demo.c
+++ /dev/null
@@ -1,135 +0,0 @@
-#include "network.h"
-#include "detection_layer.h"
-#include "cost_layer.h"
-#include "utils.h"
-#include "parser.h"
-#include "box.h"
-#include "image.h"
-#include <sys/time.h>
-
-#ifdef OPENCV
-#include "opencv2/highgui/highgui_c.h"
-#include "opencv2/imgproc/imgproc_c.h"
-image ipl_to_image(IplImage* src);
-void convert_yolo_detections(float *predictions, int classes, int num, int square, int side, int w, int h, float thresh, float **probs, box *boxes, int only_objectness);
-
-extern char *voc_names[];
-extern image voc_labels[];
-
-static float **probs;
-static box *boxes;
-static network net;
-static image in ;
-static image in_s ;
-static image det ;
-static image det_s;
-static image disp ;
-static CvCapture * cap;
-static float fps = 0;
-static float demo_thresh = 0;
-
-void *fetch_in_thread(void *ptr)
-{
- in = get_image_from_stream(cap);
- in_s = resize_image(in, net.w, net.h);
- return 0;
-}
-
-void *detect_in_thread(void *ptr)
-{
- float nms = .4;
-
- detection_layer l = net.layers[net.n-1];
- float *X = det_s.data;
- float *predictions = network_predict(net, X);
- free_image(det_s);
- convert_yolo_detections(predictions, l.classes, l.n, l.sqrt, l.side, 1, 1, demo_thresh, probs, boxes, 0);
- if (nms > 0) do_nms(boxes, probs, l.side*l.side*l.n, l.classes, nms);
- printf("\033[2J");
- printf("\033[1;1H");
- printf("\nFPS:%.0f\n",fps);
- printf("Objects:\n\n");
- draw_detections(det, l.side*l.side*l.n, demo_thresh, boxes, probs, voc_names, voc_labels, 20);
- return 0;
-}
-
-void demo_yolo(char *cfgfile, char *weightfile, float thresh, int cam_index, char *filename)
-{
- demo_thresh = thresh;
- printf("YOLO demo\n");
- net = parse_network_cfg(cfgfile);
- if(weightfile){
- load_weights(&net, weightfile);
- }
- set_batch_network(&net, 1);
-
- srand(2222222);
-
- if(filename){
- cap = cvCaptureFromFile(filename);
- }else{
- cap = cvCaptureFromCAM(cam_index);
- }
-
- if(!cap) error("Couldn't connect to webcam.\n");
- cvNamedWindow("YOLO", CV_WINDOW_NORMAL);
- cvResizeWindow("YOLO", 512, 512);
-
- detection_layer l = net.layers[net.n-1];
- int j;
-
- boxes = (box *)calloc(l.side*l.side*l.n, sizeof(box));
- probs = (float **)calloc(l.side*l.side*l.n, sizeof(float *));
- for(j = 0; j < l.side*l.side*l.n; ++j) probs[j] = (float *)calloc(l.classes, sizeof(float *));
-
- pthread_t fetch_thread;
- pthread_t detect_thread;
-
- fetch_in_thread(0);
- det = in;
- det_s = in_s;
-
- fetch_in_thread(0);
- detect_in_thread(0);
- disp = det;
- det = in;
- det_s = in_s;
-
- while(1){
- struct timeval tval_before, tval_after, tval_result;
- gettimeofday(&tval_before, NULL);
- /*
- if(pthread_create(&fetch_thread, 0, fetch_in_thread, 0)) error("Thread creation failed");
- if(pthread_create(&detect_thread, 0, detect_in_thread, 0)) error("Thread creation failed");
- show_image(disp, "YOLO");
- free_image(disp);
- cvWaitKey(1);
- pthread_join(fetch_thread, 0);
- pthread_join(detect_thread, 0);
-
- disp = det;
- det = in;
- det_s = in_s;
- */
-
- fetch_in_thread(0);
- det = in;
- det_s = in_s;
- detect_in_thread(0);
- disp = det;
- show_image(disp, "YOLO");
- free_image(disp);
- cvWaitKey(1);
-
- gettimeofday(&tval_after, NULL);
- timersub(&tval_after, &tval_before, &tval_result);
- float curr = 1000000.f/((long int)tval_result.tv_usec);
- fps = .9*fps + .1*curr;
- }
-}
-#else
-void demo_yolo(char *cfgfile, char *weightfile, float thresh, int cam_index, char *filename){
- fprintf(stderr, "YOLO demo needs OpenCV for webcam images.\n");
-}
-#endif
-
--
Gitblit v1.10.0