In [1]:
RCNN_DIR = '/opt/py-faster-rcnn/'
import os
os.environ["PYTHONPATH"] = RCNN_DIR + 'caffe-fast-rcnn/python'
!sudo unlink /usr/local/cuda
!sudo ln -s /usr/local/cuda-7.5 /usr/local/cuda
In [2]:
import os.path as osp
import sys
def add_path(path):
if path not in sys.path:
sys.path.insert(0, path)
caffe_path = osp.join(RCNN_DIR, 'caffe-fast-rcnn', 'python')
add_path(caffe_path)
lib_path = osp.join(RCNN_DIR, 'lib')
add_path(lib_path)
In [3]:
from fast_rcnn.config import cfg
from fast_rcnn.test import im_detect
from fast_rcnn.nms_wrapper import nms
from utils.timer import Timer
import matplotlib.pyplot as plt
from matplotlib.font_manager import FontProperties
import numpy as np
import scipy.io as sio
import caffe, os, sys, cv2
%matplotlib inline
In [4]:
NET = 'vgg16' # Options: vgg16, zf
GPU = 0 # Set to GPU ID
NUM_IMAGES = 2 # Options: 1 - a single image, 2 - an image set
IMG_DIR = '/home/qtb9744/data/test_images/' # Set location of test images
CLASS_DIR = '/home/qtb9744/data/test_images/classified/' # Set location for classified images
FILE_DISPLAY = 1 # Options: 0 - write to file, 1 - display to window
CLASSES = ('__background__', 'aeroplane', 'bicycle', 'bird', 'boat',
'bottle', 'bus', 'car', 'cat', 'chair', 'cow', 'diningtable',
'dog', 'horse', 'motorbike', 'person',
'pottedplant', 'sheep' 'sofa', 'train', 'tvmonitor')
COLORS = ('green', 'green', 'yellow', 'green', 'green',
'green', 'red', 'red', 'green', 'green', 'green', 'green',
'green', 'green', 'yellow', 'blue',
'green', 'green' 'green', 'green', 'green')
NETS = {'vgg16': ('VGG16', 'VGG16_faster_rcnn_final.caffemodel'),
'zf': ('ZF', 'ZF_faster_rcnn_final.caffemodel')}
In [5]:
def vis_detections(im, scores, boxes, im_name, conf_thresh=0.5,
nms_thresh=0.4):
"""Draw detected bounding boxes."""
im = im[:, :, (2, 1, 0)]
fig, ax = plt.subplots(figsize=(12, 12))
ax.imshow(im, aspect='equal')
font0 = FontProperties()
alignment = {'horizontalalignment': 'center',
'verticalalignment': 'baseline'}
font = font0.copy()
font.set_weight('bold')
font.set_size('x-large')
col_idx = 0
for cls_ind, cls in enumerate(CLASSES[1:]):
if cls_ind == 6 or cls_ind == 14:
cls_ind += 1 # because we skipped background
cls_boxes = boxes[:, 4*cls_ind:4*(cls_ind + 1)]
cls_scores = scores[:, cls_ind]
dets = np.hstack((cls_boxes, cls_scores[:,
np.newaxis])).astype(np.float32)
keep = nms(dets, nms_thresh)
dets = dets[keep, :]
inds = np.where(dets[:, -1] >= conf_thresh)[0]
row_idx = 0
if len(inds) != 0:
row_idx += 1
for i in inds:
bbox = dets[i, :4]
score = dets[i, -1]
ax.add_patch(plt.Rectangle((bbox[0], bbox[1]),
bbox[2] - bbox[0], bbox[3] - bbox[1], fill=False,
edgecolor=COLORS[cls_ind], linewidth = 2.0))
row_idx += 1
col_idx += 1
plt.axis('off')
plt.tight_layout()
plt.draw()
if FILE_DISPLAY == 0:
out_file = os.path.join(CLASS_DIR, os.path.basename(im_name))
plt.savefig(out_file)
elif FILE_DISPLAY == 1:
plt.show()
plt.clf()
plt.close()
In [6]:
def demo(net, im_name):
"""Detect object classes in an image using pre-computed object proposals"""
# Load the test image
im_file = os.path.join(IMG_DIR, im_name)
im = cv2.imread(im_file)
# Detect all object classes and regress object bounds
timer = Timer()
timer.tic()
scores, boxes = im_detect(net, im)
timer.toc()
print ('Detection took {:3f}s for '
'{:d} object proposals\n').format(timer.total_time, boxes.shape[0])
# Visualize detections for each class
CONF_THRESH = 0.7
NMS_THRESH = 0.3
vis_detections(im, scores, boxes, im_name, CONF_THRESH, NMS_THRESH)
In [7]:
if __name__ == '__main__':
cfg.TEST.HAS_RPN = True # Use RPN for proposals
prototxt = os.path.join(cfg.MODELS_DIR, NETS[NET][0],
'faster_rcnn_alt_opt', 'faster_rcnn_test.pt')
caffemodel = os.path.join(cfg.DATA_DIR, 'faster_rcnn_models',
NETS[NET][1])
if not os.path.isfile(caffemodel):
raise IOError(('{:s} not found.\nDid you run ./data/scripts/'
'fetch_faster_rcnn_models.sh?').format(caffemodel))
caffe.set_mode_gpu()
caffe.set_device(GPU)
cfg.GPU_ID = GPU
net = caffe.Net(prototxt, caffemodel, caffe.TEST)
print '\n\nLoaded network {:s}'.format(caffemodel)
# Warmup on a dummy image
im = 128 * np.ones((300, 500, 3), dtype=np.uint8)
for i in xrange(2):
_, _ = im_detect(net, im)
if NUM_IMAGES == 1:
print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'
IM_NAME = 'test_images1.png'
im_name = IMG_DIR + IM_NAME
demo(net, im_name)
else:
for im_name in sorted(os.listdir(IMG_DIR)):
if im_name.endswith('.png'):
print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'
demo(net, im_name)
In [ ]: