Cannot compile with CudNN and yolo.weights file issue #1
Description
Hi,
I tried compiling darknet-cpp with GPU=1, CUDNN=1, OPENCV=1, DEBUG=1. I get the following error:
g++ -Wno-unused-result -std=c++11 -DOPENCV `pkg-config --cflags opencv` -DGPU -I/usr/local/cuda/include/ -I"/usr/local/lib/restbed/distribution/include/" -DCUDNN -Wno-write-strings -Wall -O0 -g -DOPENCV -DGPU -DCUDNN -c ./src/convolutional_layer.c -o obj-cpp/convolutional_layer.o
./src/convolutional_layer.c: In function 'void cudnn_convolutional_setup(layer*)':
./src/convolutional_layer.c:145:117: error: too few arguments to function 'cudnnStatus_t cudnnSetConvolution2dDescriptor(cudnnConvolutionDescriptor_t, int, int, int, int, int, int, cudnnConvolutionMode_t, cudnnDataType_t)'
lution2dDescriptor(l->convDesc, l->pad, l->pad, l->stride, l->stride, 1, 1, CUDNN_CROSS_CORRELATION);
^
In file included from ./src/cuda.h:15:0,
from ./src/convolutional_layer.h:4,
from ./src/convolutional_layer.c:1:
/usr/local/cuda/include/cudnn.h:500:27: note: declared here
cudnnStatus_t CUDNNWINAPI cudnnSetConvolution2dDescriptor( cudnnConvolutionDescriptor_t convDesc,
^
Makefile:114: recipe for target 'obj-cpp/convolutional_layer.o' failed
make: *** [obj-cpp/convolutional_layer.o] Error 1
I successfully compile with CUDNN=0. I then ran the following:
wget https://pjreddie.com/media/files/yolo.weights
./darknet-cpp detector test cfg/coco.data cfg/yolo.cfg yolo.weights data/dog.jpg
I get no detections in the image (as in no bounding box) have I the wrong weights downloaded?
usage: ./darknet-cpp <function>
usage: ./darknet-cpp <function>
Cannot load image "data/labels/32_0.png"
Cannot load image "data/labels/33_0.png"
Cannot load image "data/labels/34_0.png"
Cannot load image "data/labels/35_0.png"
Cannot load image "data/labels/36_0.png"
....
....
26 reorg / 2 26 x 26 x 512 -> 13 x 13 x2048
27 route 26 24
28 conv 1024 3 x 3 / 1 13 x 13 x3072 -> 13 x 13 x1024
29 conv 425 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 425
30 detection
Setup: net.n = 31
net.layers[0].batch = 1
Loading weights from yolo.weights...mj = 0, mn = 1, *(net->seen) = 32013312
load_convolutional_weights: l.n*l.c*l.size*l.size = 864
load_convolutional_weights: l.n*l.c*l.size*l.size = 18432
load_convolutional_weights: l.n*l.c*l.size*l.size = 73728
load_convolutional_weights: l.n*l.c*l.size*l.size = 8192
load_convolutional_weights: l.n*l.c*l.size*l.size = 73728
load_convolutional_weights: l.n*l.c*l.size*l.size = 294912
load_convolutional_weights: l.n*l.c*l.size*l.size = 32768
load_convolutional_weights: l.n*l.c*l.size*l.size = 294912
load_convolutional_weights: l.n*l.c*l.size*l.size = 1179648
load_convolutional_weights: l.n*l.c*l.size*l.size = 131072
load_convolutional_weights: l.n*l.c*l.size*l.size = 1179648
load_convolutional_weights: l.n*l.c*l.size*l.size = 131072
load_convolutional_weights: l.n*l.c*l.size*l.size = 1179648
load_convolutional_weights: l.n*l.c*l.size*l.size = 4718592
load_convolutional_weights: l.n*l.c*l.size*l.size = 524288
load_convolutional_weights: l.n*l.c*l.size*l.size = 4718592
load_convolutional_weights: l.n*l.c*l.size*l.size = 524288
load_convolutional_weights: l.n*l.c*l.size*l.size = 4718592
load_convolutional_weights: l.n*l.c*l.size*l.size = 9437184
load_convolutional_weights: l.n*l.c*l.size*l.size = 9437184
load_convolutional_weights: l.n*l.c*l.size*l.size = 28311552
load_convolutional_weights: l.n*l.c*l.size*l.size = 435200
Done!
test_detector: layers = 13, 13, 5
data/dog.jpg: Predicted in 0.236138 seconds.
When using yolo-tiny I get the following:
wget https://pjreddie.com/media/files/tiny-yolo-voc.weights
./darknet-cpp detector test cfg/voc.data cfg/tiny-yolo-voc.cfg tiny-yolo-voc.weights data/dog.jpg
usage: ./darknet-cpp <function>
usage: ./darknet-cpp <function>
Cannot load image "data/labels/32_0.png"
Cannot load image "data/labels/33_0.png"
Cannot load image "data/labels/34_0.png"
Cannot load image "data/labels/35_0.png"
Cannot load image "data/labels/36_0.png"
....
....
12 conv 1024 3 x 3 / 1 13 x 13 x 512 -> 13 x 13 x1024
13 conv 1024 3 x 3 / 1 13 x 13 x1024 -> 13 x 13 x1024
14 conv 125 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 125
15 detection
Setup: net.n = 16
net.layers[0].batch = 8
Loading weights from tiny-yolo-voc.weights...mj = 0, mn = 1, *(net->seen) = 2566400
load_convolutional_weights: l.n*l.c*l.size*l.size = 432
load_convolutional_weights: l.n*l.c*l.size*l.size = 4608
load_convolutional_weights: l.n*l.c*l.size*l.size = 18432
load_convolutional_weights: l.n*l.c*l.size*l.size = 73728
load_convolutional_weights: l.n*l.c*l.size*l.size = 294912
load_convolutional_weights: l.n*l.c*l.size*l.size = 1179648
load_convolutional_weights: l.n*l.c*l.size*l.size = 4718592
load_convolutional_weights: l.n*l.c*l.size*l.size = 9437184
load_convolutional_weights: l.n*l.c*l.size*l.size = 128000
Done!
test_detector: layers = 13, 13, 5
data/dog.jpg: Predicted in 0.189172 seconds.
cat: 76%
bird: 25%
horse: 79%