0
Ich verwende demo.py in https://github.com/rbgirshick/py-faster-rcnn/tree/master/tools.Zeigen Sie Bilder mit Begrenzungsrahmen an, während py-faster-rcnn mit VGG_CNN_M_1024 ausgeführt wird.
Ich habe den Code geändert, um VGG_CNN_M_1024 zu laufen, da ich eine 2GB GPU verwende. Und nach den gegebenen Kommentare in https://github.com/rbgirshick/fast-rcnn/issues/2, wählte ich VGG_CNN_M_1024.caffemodel statt VGG16_faster_rcnn_final.caffemodel
Dies ist der Code in demo.py auszuführen:
#!/usr/bin/env python
# --------------------------------------------------------
# Faster R-CNN
# Copyright (c) 2015 Microsoft
# Licensed under The MIT License [see LICENSE for details]
# Written by Ross Girshick
# --------------------------------------------------------
"""
Demo script showing detections in sample images.
See README.md for installation instructions before running.
"""
import _init_paths
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
import numpy as np
import scipy.io as sio
import caffe, os, sys, cv2
import argparse
CLASSES = ('__background__',
'aeroplane', 'bicycle', 'bird', 'boat',
'bottle', 'bus', 'car', 'cat', 'chair',
'cow', 'diningtable', 'dog', 'horse',
'motorbike', 'person', 'pottedplant',
'sheep', 'sofa', 'train', 'tvmonitor')
NETS = {'vgg16': ('VGG16',
'VGG16_faster_rcnn_final.caffemodel'),
'zf': ('ZF',
'ZF_faster_rcnn_final.caffemodel'),
'vgg16_m_1024':('VGG_CNN_M_1024','VGG_CNN_M_1024.caffemodel')}
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=(12, 12))
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(('{} detections with '
'p({} | box) >= {:.1f}').format(class_name, class_name,
thresh),
fontsize=14)
plt.axis('off')
plt.tight_layout()
plt.draw()
def demo(net, image_name):
"""Detect object classes in an image using pre-computed object proposals."""
# Load the demo image
im_file = os.path.join(cfg.DATA_DIR, 'demo', image_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').format(timer.total_time, boxes.shape[0])
# Visualize detections for each class
CONF_THRESH = 0.8
NMS_THRESH = 0.3
for cls_ind, cls in enumerate(CLASSES[1:]):
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, :]
vis_detections(im, cls, dets, thresh=CONF_THRESH)
def parse_args():
"""Parse input arguments."""
parser = argparse.ArgumentParser(description='Faster R-CNN demo')
parser.add_argument('--gpu', dest='gpu_id', help='GPU device id to use [0]',
default=0, type=int)
parser.add_argument('--cpu', dest='cpu_mode',
help='Use CPU mode (overrides --gpu)',
action='store_true')
parser.add_argument('--net', dest='demo_net', help='Network to use [vgg16]',
choices=NETS.keys(), default='vgg16_m_1024')
args = parser.parse_args()
return args
if __name__ == '__main__':
cfg.TEST.HAS_RPN = True # Use RPN for proposals
args = parse_args()
prototxt = os.path.join(cfg.MODELS_DIR, NETS[args.demo_net][0],
'faster_rcnn_alt_opt', 'faster_rcnn_test.pt')
caffemodel = os.path.join(cfg.DATA_DIR, 'faster_rcnn_models',
NETS[args.demo_net][1])
if not os.path.isfile(caffemodel):
raise IOError(('{:s} not found.\nDid you run ./data/script/'
'fetch_faster_rcnn_models.sh?').format(caffemodel))
if args.cpu_mode:
caffe.set_mode_cpu()
else:
caffe.set_mode_gpu()
caffe.set_device(args.gpu_id)
cfg.GPU_ID = args.gpu_id
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)
im_names = ['000456.jpg', '000542.jpg', '001150.jpg',
'001763.jpg', '004545.jpg']
for im_name in im_names:
print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'
print 'Demo for data/demo/{}'.format(im_name)
demo(net, im_name)
plt.show()
Und das ist config.py
# --------------------------------------------------------
# Fast R-CNN
# Copyright (c) 2015 Microsoft
# Licensed under The MIT License [see LICENSE for details]
# Written by Ross Girshick
# --------------------------------------------------------
"""Fast R-CNN config system.
This file specifies default config options for Fast R-CNN. You should not
change values in this file. Instead, you should write a config file (in yaml)
and use cfg_from_file(yaml_file) to load it and override the default options.
Most tools in $ROOT/tools take a --cfg option to specify an override file.
- See tools/{train,test}_net.py for example code that uses cfg_from_file()
- See experiments/cfgs/*.yml for example YAML config override files
"""
import os
import os.path as osp
import numpy as np
# `pip install easydict` if you don't have it
from easydict import EasyDict as edict
__C = edict()
# Consumers can get config by:
# from fast_rcnn_config import cfg
cfg = __C
#
# Training options
#
__C.TRAIN = edict()
# Scales to use during training (can list multiple scales)
# Each scale is the pixel size of an image's shortest side
__C.TRAIN.SCALES = (600,)
# Max pixel size of the longest side of a scaled input image
__C.TRAIN.MAX_SIZE = 1000
# Images to use per minibatch
__C.TRAIN.IMS_PER_BATCH = 2
# Minibatch size (number of regions of interest [ROIs])
__C.TRAIN.BATCH_SIZE = 128
# Fraction of minibatch that is labeled foreground (i.e. class > 0)
__C.TRAIN.FG_FRACTION = 0.25
# Overlap threshold for a ROI to be considered foreground (if >= FG_THRESH)
__C.TRAIN.FG_THRESH = 0.5
# Overlap threshold for a ROI to be considered background (class = 0 if
# overlap in [LO, HI))
__C.TRAIN.BG_THRESH_HI = 0.5
__C.TRAIN.BG_THRESH_LO = 0.1
# Use horizontally-flipped images during training?
__C.TRAIN.USE_FLIPPED = True
# Train bounding-box regressors
__C.TRAIN.BBOX_REG = True
# Overlap required between a ROI and ground-truth box in order for that ROI to
# be used as a bounding-box regression training example
__C.TRAIN.BBOX_THRESH = 0.5
# Iterations between snapshots
__C.TRAIN.SNAPSHOT_ITERS = 10000
# solver.prototxt specifies the snapshot path prefix, this adds an optional
# infix to yield the path: <prefix>[_<infix>]_iters_XYZ.caffemodel
__C.TRAIN.SNAPSHOT_INFIX = ''
# Use a prefetch thread in roi_data_layer.layer
# So far I haven't found this useful; likely more engineering work is required
__C.TRAIN.USE_PREFETCH = False
# Normalize the targets (subtract empirical mean, divide by empirical stddev)
__C.TRAIN.BBOX_NORMALIZE_TARGETS = True
# Deprecated (inside weights)
__C.TRAIN.BBOX_INSIDE_WEIGHTS = (1.0, 1.0, 1.0, 1.0)
# Normalize the targets using "precomputed" (or made up) means and stdevs
# (BBOX_NORMALIZE_TARGETS must also be True)
__C.TRAIN.BBOX_NORMALIZE_TARGETS_PRECOMPUTED = False
__C.TRAIN.BBOX_NORMALIZE_MEANS = (0.0, 0.0, 0.0, 0.0)
__C.TRAIN.BBOX_NORMALIZE_STDS = (0.1, 0.1, 0.2, 0.2)
# Train using these proposals
__C.TRAIN.PROPOSAL_METHOD = 'selective_search'
# Make minibatches from images that have similar aspect ratios (i.e. both
# tall and thin or both short and wide) in order to avoid wasting computation
# on zero-padding.
__C.TRAIN.ASPECT_GROUPING = True
# Use RPN to detect objects
__C.TRAIN.HAS_RPN = False
# IOU >= thresh: positive example
__C.TRAIN.RPN_POSITIVE_OVERLAP = 0.7
# IOU < thresh: negative example
__C.TRAIN.RPN_NEGATIVE_OVERLAP = 0.3
# If an anchor statisfied by positive and negative conditions set to negative
__C.TRAIN.RPN_CLOBBER_POSITIVES = False
# Max number of foreground examples
__C.TRAIN.RPN_FG_FRACTION = 0.5
# Total number of examples
__C.TRAIN.RPN_BATCHSIZE = 256
# NMS threshold used on RPN proposals
__C.TRAIN.RPN_NMS_THRESH = 0.7
# Number of top scoring boxes to keep before apply NMS to RPN proposals
__C.TRAIN.RPN_PRE_NMS_TOP_N = 12000
# Number of top scoring boxes to keep after applying NMS to RPN proposals
__C.TRAIN.RPN_POST_NMS_TOP_N = 2000
# Proposal height and width both need to be greater than RPN_MIN_SIZE (at orig image scale)
__C.TRAIN.RPN_MIN_SIZE = 16
# Deprecated (outside weights)
__C.TRAIN.RPN_BBOX_INSIDE_WEIGHTS = (1.0, 1.0, 1.0, 1.0)
# Give the positive RPN examples weight of p * 1/{num positives}
# and give negatives a weight of (1 - p)
# Set to -1.0 to use uniform example weighting
__C.TRAIN.RPN_POSITIVE_WEIGHT = -1.0
#
# Testing options
#
__C.TEST = edict()
# Scales to use during testing (can list multiple scales)
# Each scale is the pixel size of an image's shortest side
__C.TEST.SCALES = (600,)
# Max pixel size of the longest side of a scaled input image
__C.TEST.MAX_SIZE = 1000
# Overlap threshold used for non-maximum suppression (suppress boxes with
# IoU >= this threshold)
__C.TEST.NMS = 0.3
# Experimental: treat the (K+1) units in the cls_score layer as linear
# predictors (trained, eg, with one-vs-rest SVMs).
__C.TEST.SVM = False
# Test using bounding-box regressors
__C.TEST.BBOX_REG = True
# Propose boxes
__C.TEST.HAS_RPN = False
# Test using these proposals
__C.TEST.PROPOSAL_METHOD = 'selective_search'
## NMS threshold used on RPN proposals
__C.TEST.RPN_NMS_THRESH = 0.7
## Number of top scoring boxes to keep before apply NMS to RPN proposals
__C.TEST.RPN_PRE_NMS_TOP_N = 6000
## Number of top scoring boxes to keep after applying NMS to RPN proposals
__C.TEST.RPN_POST_NMS_TOP_N = 300
# Proposal height and width both need to be greater than RPN_MIN_SIZE (at orig image scale)
__C.TEST.RPN_MIN_SIZE = 16
#
# MISC
#
# The mapping from image coordinates to feature map coordinates might cause
# some boxes that are distinct in image space to become identical in feature
# coordinates. If DEDUP_BOXES > 0, then DEDUP_BOXES is used as the scale factor
# for identifying duplicate boxes.
# 1/16 is correct for {Alex,Caffe}Net, VGG_CNN_M_1024, and VGG16
__C.DEDUP_BOXES = 1./16.
# Pixel mean values (BGR order) as a (1, 1, 3) array
# We use the same pixel mean for all networks even though it's not exactly what
# they were trained with
__C.PIXEL_MEANS = np.array([[[102.9801, 115.9465, 122.7717]]])
# For reproducibility
__C.RNG_SEED = 3
# A small number that's used many times
__C.EPS = 1e-14
# Root directory of project
__C.ROOT_DIR = osp.abspath(osp.join(osp.dirname(__file__), '..', '..'))
# Data directory
__C.DATA_DIR = osp.abspath(osp.join(__C.ROOT_DIR, 'data'))
# Model directory
__C.MODELS_DIR = osp.abspath(osp.join(__C.ROOT_DIR, 'models', 'pascal_voc'))
# Name (or path to) the matlab executable
__C.MATLAB = 'matlab'
# Place outputs under an experiments directory
__C.EXP_DIR = 'default'
# Use GPU implementation of non-maximum suppression
__C.USE_GPU_NMS = False
# Default GPU device id
__C.GPU_ID = 0
def get_output_dir(imdb, net=None):
"""Return the directory where experimental artifacts are placed.
If the directory does not exist, it is created.
A canonical path is built using the name from an imdb and a network
(if not None).
"""
outdir = osp.abspath(osp.join(__C.ROOT_DIR, 'output', __C.EXP_DIR, imdb.name))
if net is not None:
outdir = osp.join(outdir, net.name)
if not os.path.exists(outdir):
os.makedirs(outdir)
return outdir
def _merge_a_into_b(a, b):
"""Merge config dictionary a into config dictionary b, clobbering the
options in b whenever they are also specified in a.
"""
if type(a) is not edict:
return
for k, v in a.iteritems():
# a must specify keys that are in b
if not b.has_key(k):
raise KeyError('{} is not a valid config key'.format(k))
# the types must match, too
old_type = type(b[k])
if old_type is not type(v):
if isinstance(b[k], np.ndarray):
v = np.array(v, dtype=b[k].dtype)
else:
raise ValueError(('Type mismatch ({} vs. {}) '
'for config key: {}').format(type(b[k]),
type(v), k))
# recursively merge dicts
if type(v) is edict:
try:
_merge_a_into_b(a[k], b[k])
except:
print('Error under config key: {}'.format(k))
raise
else:
b[k] = v
def cfg_from_file(filename):
"""Load a config file and merge it into the default options."""
import yaml
with open(filename, 'r') as f:
yaml_cfg = edict(yaml.load(f))
_merge_a_into_b(yaml_cfg, __C)
def cfg_from_list(cfg_list):
"""Set config keys via list (e.g., from command line)."""
from ast import literal_eval
assert len(cfg_list) % 2 == 0
for k, v in zip(cfg_list[0::2], cfg_list[1::2]):
key_list = k.split('.')
d = __C
for subkey in key_list[:-1]:
assert d.has_key(subkey)
d = d[subkey]
subkey = key_list[-1]
assert d.has_key(subkey)
try:
value = literal_eval(v)
except:
# handle the case when v is a string literal
value = v
assert type(value) == type(d[subkey]), \
'type {} does not match original type {}'.format(
type(value), type(d[subkey]))
d[subkey] = value
Jedes Mal, wenn ich das laufen Code mit einem ZF-Netz, bekomme ich die Ausgabebilder mit der Bounding Box.
Das Terminal Ausgang wird hier für ZF gegeben: http://txt.do/5bqsf
Allerdings, wenn ich den Code mit dem VGG_CNN_M_1024 Netz laufen, es keine Ausgabebilder angezeigt ist, auch wenn der Code erfolgreich ausgeführt wird.
Das Terminal Ausgang wird für VGG_CNN_M_1024 hier gegeben: http://txt.do/5bqsf
Was im Code kann ich ändern?