init

Makefile

@@ -0,0 +1,85 @@
+GPU=1
+CUDNN=1
+OPENCV=1
+DEBUG=0
+
+# with cudnn6, need to update convolutional_layer.c:
+#  	https://groups.google.com/forum/#!topic/darknet/AEP4qwIPwa4
+
+ARCH= -gencode arch=compute_20,code=[sm_20,sm_21] \
+       -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]
+
+VPATH=./src/
+EXEC=darknet
+OBJDIR=./obj/
+
+CC=gcc
+NVCC=nvcc 
+OPTS=-Ofast
+LDFLAGS= -lm -pthread 
+COMMON=-I/Users/avanetten/anaconda/pkgs/libgdal-2.1.0-0/include
+CFLAGS=-Wall -Wfatal-errors 
+
+ifeq ($(DEBUG), 1) 
+OPTS=-O0 -g
+endif
+
+CFLAGS+=$(OPTS)
+
+ifeq ($(OPENCV), 1) 
+COMMON+= -DOPENCV
+CFLAGS+= -DOPENCV
+LDFLAGS+= `pkg-config --libs opencv` 
+COMMON+= `pkg-config --cflags opencv` 
+endif
+
+ifeq ($(GPU), 1) 
+COMMON+= -DGPU -I/usr/local/cuda/include/
+CFLAGS+= -DGPU
+LDFLAGS+= -L/usr/local/cuda/lib64 -lcuda -lcudart -lcublas -lcurand
+endif
+
+ifeq ($(CUDNN), 1) 
+COMMON+= -DCUDNN 
+CFLAGS+= -DCUDNN
+LDFLAGS+= -lcudnn
+endif
+
+OBJ=gemm.o utils.o cuda.o convolutional_layer.o list.o image.o activations.o im2col.o col2im.o blas.o crop_layer.o dropout_layer.o maxpool_layer.o softmax_layer.o data.o matrix.o network.o connected_layer.o cost_layer.o parser.o option_list.o darknet.o detection_layer.o captcha.o route_layer.o writing.o box.o nightmare.o normalization_layer.o avgpool_layer.o coco.o dice.o yolo.o yolt.o yolt2.o detector.o layer.o compare.o classifier.o local_layer.o swag.o shortcut_layer.o activation_layer.o rnn_layer.o gru_layer.o rnn.o rnn_vid.o crnn_layer.o demo.o tag.o cifar.o go.o batchnorm_layer.o art.o region_layer.o reorg_layer.o super.o voxel.o tree.o
+ifeq ($(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
+endif
+
+OBJS = $(addprefix $(OBJDIR), $(OBJ))
+DEPS = $(wildcard src/*.h) Makefile
+
+all: obj results $(EXEC)
+#all: obj backup results $(EXEC)
+
+
+$(EXEC): $(OBJS)
+	$(CC) $(COMMON) $(CFLAGS) $^ -o $@ $(LDFLAGS)
+
+$(OBJDIR)%.o: %.c $(DEPS)
+	$(CC) $(COMMON) $(CFLAGS) -c $< -o $@
+
+$(OBJDIR)%.o: %.cu $(DEPS)
+	$(NVCC) $(ARCH) $(COMMON) --compiler-options "$(CFLAGS)" -c $< -o $@
+
+obj:
+	mkdir -p obj
+#backup:
+#	mkdir -p backup
+results:
+	mkdir -p results
+
+.PHONY: clean
+
+clean:
+	rm -rf $(OBJS) $(EXEC)
+

README.md

@@ -0,0 +1,103 @@
+# YOLT #
+
+# You Only Look Twice: Rapid Multi-Scale Object Detection In Satellite Imagery
+
+YOLT is an extension of the YOLO framework (https://pjreddie.com/darknet/yolov2/) that can evaluation satellite images of arbitrary size, and runs at ~50 frames per second.
+
+References:
+
+arxiv
+
+https://medium.com/the-downlinq/you-only-look-twice-multi-scale-object-detection-in-satellite-imagery-with-convolutional-neural-38dad1cf7571
+
+https://medium.com/the-downlinq/you-only-look-twice-multi-scale-object-detection-in-satellite-imagery-with-convolutional-neural-34f72f659588
+
+https://medium.com/the-downlinq/building-extraction-with-yolt2-and-spacenet-data-a926f9ffac4f
+
+https://medium.com/the-downlinq/car-localization-and-counting-with-overhead-imagery-an-interactive-exploration-9d5a029a596b
+
+https://medium.com/the-downlinq/the-satellite-utility-manifold-object-detection-accuracy-as-a-function-of-image-resolution-ebb982310e8c
+
+https://medium.com/the-downlinq/panchromatic-to-multispectral-object-detection-performance-as-a-function-of-imaging-bands-51ecaaa3dc56
+
+If you plan on using YOLT in your work, please consider citing YOLO (https://arxiv.org/abs/1612.08242) and YOLT (arxiv)
+
+
+
+The YOLT code alters a number of the files in src/*.c to allow further functionality.  We also build a python wrapper around the C functions to improve flexibility.  We utililize the default data format of YOLO, which places images and labels in different forlders.  
+An example training data and image: 
+
+        /data/images/train1.tif
+        /data/labels/train1.txt
+        
+Each line of the .txt file has the format
+
+    <object-class> <x> <y> <width> <height>
+    Where x, y, width, and height are relative to the image's width and height.
+
+Labels can be created with https://github.com/tzutalin/labelImg, and converted to the appropriate format with the /yolt/scripts/convert.py script.  Also see https://github.com/Guanghan/darknet for an example of YOLO modifications.
+
+
+# Execution #
+
+##############################################
+# HELP
+python yolt2.py --help
+
+##############################################
+# COMPILE (gpu machine)
+python yolt2.py \
+--mode compile
+
+
+##############################################
+# TRAIN (gpu_machine)
+
+
+# Boats and planes
+python ../scripts/yolt2.py \
+--mode train \
+--outname 3class_boat_plane \
+--object_labels_str  boat,boat_harbor,airplane \
+--cfg_file ave_13x13.cfg  \
+--nbands 3 \
+--weight_file ave_13x13_boats_planes_voc.weights \
+--train_images_list_file boat_airplane_all.txt \
+--single_gpu_machine 0 \
+--keep_valid_slices False \
+--max_batches 60000 \
+--gpu 1
+
+##############################################
+# VALIDATE (gpu_machine)
+
+# test on all: boats, cars, and airplanes with new model
+cd /raid/local/src/yolt2/results/
+python ../scripts/yolt2.py \
+--mode valid \
+--outname qgis_labels_all_boats_planes_cars_buffer \
+--object_labels_str airplane,airport,boat,boat_harbor,car \
+--cfg_file ave_26x26.cfg \
+--valid_weight_dir train_cowc_cars_qgis_boats_planes_cfg=ave_26x26_2017_11_28_23-11-36 \
+--weight_file ave_26x26_30000_tmp.weights \
+--valid_testims_dir qgis_validation/all \
+--keep_valid_slices False \
+--valid_make_pngs True \
+--valid_make_legend_and_title False \
+--edge_buffer_valid 1 \
+--valid_box_rescale_frac 1 \
+--plot_thresh_str 0.4 \
+--slice_sizes_str 416 \
+--slice_overlap 0.2 \
+--gpu 2
+
+
+##############################################
+
+TBD:
+
+Upload data preparation scripts
+Describe multispectral data handling
+Describle initial results with YOLOv3
+Describle better labeling methods
+

cfg/alexnet.cfg

@@ -0,0 +1,95 @@
+[net]
+batch=128
+subdivisions=1
+height=227
+width=227
+channels=3
+momentum=0.9
+decay=0.0005
+max_crop=256
+
+learning_rate=0.01
+policy=poly
+power=4
+max_batches=800000
+
+angle=7
+hue = .1
+saturation=.75
+exposure=.75
+aspect=.75
+
+[convolutional]
+filters=96
+size=11
+stride=4
+pad=0
+activation=relu
+
+[maxpool]
+size=3
+stride=2
+padding=0
+
+[convolutional]
+filters=256
+size=5
+stride=1
+pad=1
+activation=relu
+
+[maxpool]
+size=3
+stride=2
+padding=0
+
+[convolutional]
+filters=384
+size=3
+stride=1
+pad=1
+activation=relu
+
+[convolutional]
+filters=384
+size=3
+stride=1
+pad=1
+activation=relu
+
+[convolutional]
+filters=256
+size=3
+stride=1
+pad=1
+activation=relu
+
+[maxpool]
+size=3
+stride=2
+padding=0
+
+[connected]
+output=4096
+activation=relu
+
+[dropout]
+probability=.5
+
+[connected]
+output=4096
+activation=relu
+
+[dropout]
+probability=.5
+
+[connected]
+output=1000
+activation=linear
+
+[softmax]
+groups=1
+
+[cost]
+type=sse
+