- Ubuntu >= 14.04, GPU( >= 2GB), CUDA 7.5+, cuDnn 4.0.7+
- Install docker, docker-nvidia
docker pull ck196/py-faster-rcnn
Download pre-trained model. https://drive.google.com/open?id=0B4MXf_cfl_weOEMyTHVSRWF6M0U
Windows.10.and.Office.2016.gVLK | |
##################################################################### | |
# Install/Uninstall keys # | |
##################################################################### | |
1.) Uninstall the current product by entering the “uninstall product key” extension: | |
slmgr.vbs /upk | |
2.) Install the key that you obtained above for “Windows Srv 2012R2 DataCtr/Std KMS for Windows 10” |
docker service scale SERVICE_NAME=0 | |
docker service scale SERVICE_NAME=1 | |
docker stats --all --format "table {{.Container}}\t {{.Name}}\t {{.CPUPerc}}\t{{.MemUsage}}" | |
docker stop $(docker ps -a -q) | |
docker rm $(docker ps -a -q) | |
docker rmi $(docker images -q) |
###################### | |
# panes | |
set -g pane-border-fg black | |
set -g pane-active-border-fg brightred | |
## Status bar design | |
# status line | |
set -g status-justify left | |
set -g status-bg default |
import numpy as np | |
# Make sure that caffe is on the python path: | |
# export PYTHONPATH=${CAFFE_ROOT}/python | |
import caffe | |
import cv2 | |
class AgenDetector: | |
gen_net = None |
docker pull ck196/py-faster-rcnn
Download pre-trained model. https://drive.google.com/open?id=0B4MXf_cfl_weOEMyTHVSRWF6M0U
#!/bin/bash | |
set -x | |
set -e | |
LOG="testing_log.txt" | |
exec &> >(tee -a "$LOG") | |
echo Logging output to "$LOG" | |
rm -rf data/VOCdevkit2007/annotations_cache/annots.pkl |
from __future__ import division | |
import os | |
import math | |
import numpy as np | |
import json | |
from os import listdir | |
from os.path import isfile, join | |
#from nms.gpu_nms import gpu_nms | |
#import gpu_nms | |
import sys |
name: "ResNet_VOC0712_SSD_500x500_train" | |
layer { | |
name: "data" | |
type: "AnnotatedData" | |
top: "data" | |
top: "label" | |
include { | |
phase: TRAIN | |
} | |
transform_param { |
import numpy as np | |
import matplotlib.pyplot as plt | |
#%matplotlib inline | |
import skimage | |
import skimage.io as skio | |
import os | |
from os import path |
name: "ResNet_VOC0712_SSD_300x300_train" | |
layer { | |
name: "data" | |
type: "AnnotatedData" | |
top: "data" | |
top: "label" | |
include { | |
phase: TRAIN | |
} | |
transform_param { |