Commit acb591ac authored by Ross Girshick's avatar Ross Girshick

demo

parent c70cf0dd
#!/usr/bin/env python
# --------------------------------------------------------
# Fast R-CNN
# Copyright (c) 2015 Microsoft
# Licensed under The MIT License [see LICENSE for details]
# Written by Ross Girshick
# --------------------------------------------------------
import _init_paths
from fast_rcnn.config import cfg
from fast_rcnn.test import im_detect
from utils.cython_nms import nms
from utils.timer import Timer
import matplotlib.pyplot as plt
import numpy as np
import caffe, cPickle, os, cv2
CLASSES = ('__background__',
'aeroplane', 'bicycle', 'bird', 'boat',
'bottle', 'bus', 'car', 'cat', 'chair',
'cow', 'diningtable', 'dog', 'horse',
'motorbike', 'person', 'pottedplant',
'sheep', 'sofa', 'train', 'tvmonitor')
def vis_detections(im, class_name, dets, thresh=0.5):
"""Draw detected bounding boxes."""
inds = np.where(dets[:, -1] >= thresh)[0]
if len(inds) == 0:
return
im = im[:, :, (2, 1, 0)]
fig, ax = plt.subplots(figsize=(14, 14))
ax.imshow(im, aspect='equal')
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='red', linewidth=3.5)
)
ax.text(bbox[0], bbox[1] - 2,
'{:s} {:.3f}'.format(class_name, score),
bbox=dict(facecolor='blue', alpha=0.5),
fontsize=14, color='white')
ax.set_title(('All {} detections with '
'score >= {:.1f}').format(class_name, thresh),
fontsize=18)
plt.axis('off')
plt.tight_layout()
plt.show()
def demo(net, image_name, classes):
"""Detect object classes in an image using pre-computed object proposals."""
# Load pre-computed Selected Search object proposals
box_file = os.path.join(cfg.ROOT_DIR, 'data', 'demo',
image_name + '_boxes.pkl')
with open(box_file, 'rb') as f:
obj_proposals = cPickle.load(f)
# Load the demo image
im_file = os.path.join(cfg.ROOT_DIR, 'data', 'demo', image_name + '.jpg')
im = cv2.imread(im_file)
# Detect all object classes and regress object bounds
timer = Timer()
timer.tic()
scores, boxes = im_detect(net, im, obj_proposals)
timer.toc()
print ('Detection took {:.3f}s for '
'{:d} object proposals').format(timer.total_time, boxes.shape[0])
# Visualize detections for each class
CONF_THRESH = 0.8
NMS_THRESH = 0.3
for cls in classes:
cls_ind = CLASSES.index(cls)
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, :]
print 'All {} detections with score >= {:.1f}'.format(cls, CONF_THRESH)
print 'Close image window (ctrl-w) to continue'
vis_detections(im, cls, dets, thresh=CONF_THRESH)
if __name__ == '__main__':
gpu_id = 0
prototxt = 'models/VGG16/test.prototxt'
caffemodel = ('data/fast_rcnn_models/'
'vgg16_fast_rcnn_iter_40000.caffemodel')
# prototxt = 'models/VGG_CNN_M_1024/test.prototxt'
# caffemodel = ('data/fast_rcnn_models/'
# 'vgg_cnn_m_1024_fast_rcnn_iter_40000.caffemodel')
if not os.path.isfile(caffemodel):
raise IOError(('{:s} not found.\nDid you run ./data/script/'
'fetch_fast_rcnn_models.sh?').format(caffemodel))
caffe.set_mode_gpu()
caffe.set_device(gpu_id)
net = caffe.Net(prototxt, caffemodel, caffe.TEST)
print '\n\nLoaded network {:s}'.format(caffemodel)
print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'
print 'Demo for data/demo/000004.jpg'
demo(net, '000004', ('car',))
print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'
print 'Demo for data/demo/001551.jpg'
demo(net, '001551', ('sofa', 'tvmonitor'))
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment