gluoncv 训练自己的数据集，进行目标检测
跑了一晚上的模型，实在占GPU资源，这两天已经有很多小朋友说我了。我选择了其中一个参数。
https://github.com/dmlc/gluon-cv/blob/master/scripts/detection/faster_rcnn/train_faster_rcnn.py
train_faster_rcnn的修改之前就弄好了，这里贴一个完整的。
"""Train Faster-RCNN end to end."""
import argparse
import os
# disable autotune
os.environ['MXNET_CUDNN_AUTOTUNE_DEFAULT'] = ''
import logging
import time
import numpy as np
import mxnet as mx
from mxnet import nd
from mxnet import gluon
from mxnet import autograd
import gluoncv as gcv
from gluoncv import data as gdata
from gluoncv import utils as gutils
from gluoncv.model_zoo import get_model
from gluoncv.data import batchify
from gluoncv.data.transforms.presets.rcnn import FasterRCNNDefaultTrainTransform
from gluoncv.data.transforms.presets.rcnn import FasterRCNNDefaultValTransform
from gluoncv.utils.metrics.voc_detection import VOC07MApMetric
from gluoncv.utils.metrics.coco_detection import COCODetectionMetric
from gluoncv.utils.metrics.accuracy import Accuracy # add_lst
from gluoncv.data import LstDetection def parse_args():
parser = argparse.ArgumentParser(description='Train Faster-RCNN networks e2e.')
parser.add_argument('--network', type=str, default='resnet50_v1b',
help="Base network name which serves as feature extraction base.")
parser.add_argument('--dataset', type=str, default='voc',
help='Training dataset. Now support voc and coco.')
parser.add_argument('--num-workers', '-j', dest='num_workers', type=int,
default=4, help='Number of data workers, you can use larger '
'number to accelerate data loading, if you CPU and GPUs are powerful.')
parser.add_argument('--gpus', type=str, default='',
help='Training with GPUs, you can specify 1,3 for example.')
parser.add_argument('--epochs', type=str, default='',
help='Training epochs.')
parser.add_argument('--resume', type=str, default='',
help='Resume from previously saved parameters if not None. '
'For example, you can resume from ./faster_rcnn_xxx_0123.params')
parser.add_argument('--start-epoch', type=int, default=0,
help='Starting epoch for resuming, default is 0 for new training.'
'You can specify it to 100 for example to start from 100 epoch.')
parser.add_argument('--lr', type=str, default='',
help='Learning rate, default is 0.001 for voc single gpu training.')
parser.add_argument('--lr-decay', type=float, default=0.1,
help='decay rate of learning rate. default is 0.1.')
parser.add_argument('--lr-decay-epoch', type=str, default='',
help='epoches at which learning rate decays. default is 14,20 for voc.')
parser.add_argument('--lr-warmup', type=str, default='',
help='warmup iterations to adjust learning rate, default is 0 for voc.')
parser.add_argument('--momentum', type=float, default=0.9,
help='SGD momentum, default is 0.9')
parser.add_argument('--wd', type=str, default='',
help='Weight decay, default is 5e-4 for voc')
parser.add_argument('--log-interval', type=int, default=100,
help='Logging mini-batch interval. Default is 100.')
parser.add_argument('--save-prefix', type=str, default='',
help='Saving parameter prefix')
parser.add_argument('--save-interval', type=int, default=1,
help='Saving parameters epoch interval, best model will always be saved.')
parser.add_argument('--val-interval', type=int, default=1,
help='Epoch interval for validation, increase the number will reduce the '
'training time if validation is slow.')
parser.add_argument('--seed', type=int, default=233,
help='Random seed to be fixed.')
parser.add_argument('--verbose', dest='verbose', action='store_true',
help='Print helpful debugging info once set.')
parser.add_argument('--mixup', action='store_true', help='Use mixup training.')
parser.add_argument('--no-mixup-epochs', type=int, default=20,
help='Disable mixup training if enabled in the last N epochs.')
args = parser.parse_args()
if args.dataset == 'voc' or args.dataset == 'pedestrian':
args.epochs = int(args.epochs) if args.epochs else 20
args.lr_decay_epoch = args.lr_decay_epoch if args.lr_decay_epoch else '14,20'
args.lr = float(args.lr) if args.lr else 0.001
args.lr_warmup = args.lr_warmup if args.lr_warmup else -1
args.wd = float(args.wd) if args.wd else 5e-4
elif args.dataset == 'coco':
args.epochs = int(args.epochs) if args.epochs else 26
args.lr_decay_epoch = args.lr_decay_epoch if args.lr_decay_epoch else '17,23'
args.lr = float(args.lr) if args.lr else 0.00125
args.lr_warmup = args.lr_warmup if args.lr_warmup else 8000
args.wd = float(args.wd) if args.wd else 1e-4
num_gpus = len(args.gpus.split(','))
if num_gpus == 1:
args.lr_warmup = -1
else:
args.lr *= num_gpus
args.lr_warmup /= num_gpus
return args class RPNAccMetric(mx.metric.EvalMetric):
def __init__(self):
super(RPNAccMetric, self).__init__('RPNAcc') def update(self, labels, preds):
# label: [rpn_label, rpn_weight]
# preds: [rpn_cls_logits]
rpn_label, rpn_weight = labels
rpn_cls_logits = preds[0] # calculate num_inst (average on those fg anchors)
num_inst = mx.nd.sum(rpn_weight) # cls_logits (b, c, h, w) red_label (b, 1, h, w)
# pred_label = mx.nd.argmax(rpn_cls_logits, axis=1, keepdims=True)
pred_label = mx.nd.sigmoid(rpn_cls_logits) >= 0.5
# label (b, 1, h, w)
num_acc = mx.nd.sum((pred_label == rpn_label) * rpn_weight) self.sum_metric += num_acc.asscalar()
self.num_inst += num_inst.asscalar() class RPNL1LossMetric(mx.metric.EvalMetric):
def __init__(self):
super(RPNL1LossMetric, self).__init__('RPNL1Loss') def update(self, labels, preds):
# label = [rpn_bbox_target, rpn_bbox_weight]
# pred = [rpn_bbox_reg]
rpn_bbox_target, rpn_bbox_weight = labels
rpn_bbox_reg = preds[0] # calculate num_inst (average on those fg anchors)
num_inst = mx.nd.sum(rpn_bbox_weight) / 4 # calculate smooth_l1
loss = mx.nd.sum(rpn_bbox_weight * mx.nd.smooth_l1(rpn_bbox_reg - rpn_bbox_target, scalar=3)) self.sum_metric += loss.asscalar()
self.num_inst += num_inst.asscalar() class RCNNAccMetric(mx.metric.EvalMetric):
def __init__(self):
super(RCNNAccMetric, self).__init__('RCNNAcc') def update(self, labels, preds):
# label = [rcnn_label]
# pred = [rcnn_cls]
rcnn_label = labels[0]
rcnn_cls = preds[0] # calculate num_acc
pred_label = mx.nd.argmax(rcnn_cls, axis=-1)
num_acc = mx.nd.sum(pred_label == rcnn_label) self.sum_metric += num_acc.asscalar()
self.num_inst += rcnn_label.size class RCNNL1LossMetric(mx.metric.EvalMetric):
def __init__(self):
super(RCNNL1LossMetric, self).__init__('RCNNL1Loss') def update(self, labels, preds):
# label = [rcnn_bbox_target, rcnn_bbox_weight]
# pred = [rcnn_reg]
rcnn_bbox_target, rcnn_bbox_weight = labels
rcnn_bbox_reg = preds[0] # calculate num_inst
num_inst = mx.nd.sum(rcnn_bbox_weight) / 4 # calculate smooth_l1
loss = mx.nd.sum(rcnn_bbox_weight * mx.nd.smooth_l1(rcnn_bbox_reg - rcnn_bbox_target, scalar=1)) self.sum_metric += loss.asscalar()
self.num_inst += num_inst.asscalar() def get_dataset(dataset, args):
if dataset.lower() == 'voc':
train_dataset = gdata.VOCDetection(
splits=[(2007, 'trainval'), (2012, 'trainval')])
val_dataset = gdata.VOCDetection(
splits=[(2007, 'test')])
#print(val_dataset.classes)
#('aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus', 'car', 'cat', 'chair', 'cow', 'diningtable', 'dog', 'horse', 'motorbike', 'person', 'pottedplant', 'sheep', 'sofa', 'train', 'tvmonitor') val_metric = VOC07MApMetric(iou_thresh=0.5, class_names=val_dataset.classes)
elif dataset.lower() == 'coco':
train_dataset = gdata.COCODetection(splits='instances_train2017', use_crowd=False)
val_dataset = gdata.COCODetection(splits='instances_val2017', skip_empty=False)
val_metric = COCODetectionMetric(val_dataset, args.save_prefix + '_eval', cleanup=True)
elif dataset.lower() == 'pedestrian':
lst_dataset = LstDetection('train_val.lst',root=os.path.expanduser('.'))
print(len(lst_dataset))
first_img = lst_dataset[0][0] print(first_img.shape)
print(lst_dataset[0][1]) train_dataset = LstDetection('train.lst',root=os.path.expanduser('.'))
val_dataset = LstDetection('val.lst',root=os.path.expanduser('.'))
classs = ('pedestrian',)
val_metric = VOC07MApMetric(iou_thresh=0.5,class_names=classs) else:
raise NotImplementedError('Dataset: {} not implemented.'.format(dataset))
if args.mixup:
from gluoncv.data.mixup import MixupDetection
train_dataset = MixupDetection(train_dataset)
return train_dataset, val_dataset, val_metric def get_dataloader(net, train_dataset, val_dataset, batch_size, num_workers):
"""Get dataloader."""
train_bfn = batchify.Tuple(*[batchify.Append() for _ in range(5)])
train_loader = mx.gluon.data.DataLoader(
train_dataset.transform(FasterRCNNDefaultTrainTransform(net.short, net.max_size, net)),
batch_size, True, batchify_fn=train_bfn, last_batch='rollover', num_workers=num_workers)
val_bfn = batchify.Tuple(*[batchify.Append() for _ in range(3)])
val_loader = mx.gluon.data.DataLoader(
val_dataset.transform(FasterRCNNDefaultValTransform(net.short, net.max_size)),
batch_size, False, batchify_fn=val_bfn, last_batch='keep', num_workers=num_workers)
return train_loader, val_loader def save_params(net, logger, best_map, current_map, epoch, save_interval, prefix):
current_map = float(current_map)
if current_map > best_map[0]:
logger.info('[Epoch {}] mAP {} higher than current best {} saving to {}'.format(
epoch, current_map, best_map, '{:s}_best.params'.format(prefix)))
best_map[0] = current_map
net.save_parameters('{:s}_best.params'.format(prefix))
with open(prefix+'_best_map.log', 'a') as f:
f.write('{:04d}:\t{:.4f}\n'.format(epoch, current_map))
if save_interval and (epoch + 1) % save_interval == 0:
logger.info('[Epoch {}] Saving parameters to {}'.format(
epoch, '{:s}_{:04d}_{:.4f}.params'.format(prefix, epoch, current_map)))
net.save_parameters('{:s}_{:04d}_{:.4f}.params'.format(prefix, epoch, current_map)) def split_and_load(batch, ctx_list):
"""Split data to 1 batch each device."""
num_ctx = len(ctx_list)
new_batch = []
for i, data in enumerate(batch):
new_data = [x.as_in_context(ctx) for x, ctx in zip(data, ctx_list)]
new_batch.append(new_data)
return new_batch def validate(net, val_data, ctx, eval_metric):
"""Test on validation dataset."""
clipper = gcv.nn.bbox.BBoxClipToImage()
eval_metric.reset()
net.hybridize(static_alloc=True)
for batch in val_data:
batch = split_and_load(batch, ctx_list=ctx)
det_bboxes = []
det_ids = []
det_scores = []
gt_bboxes = []
gt_ids = []
gt_difficults = []
for x, y, im_scale in zip(*batch):
# get prediction results
ids, scores, bboxes = net(x)
det_ids.append(ids)
det_scores.append(scores)
# clip to image size
det_bboxes.append(clipper(bboxes, x))
# rescale to original resolution
im_scale = im_scale.reshape((-1)).asscalar()
det_bboxes[-1] *= im_scale
# split ground truths
gt_ids.append(y.slice_axis(axis=-1, begin=4, end=5))
gt_bboxes.append(y.slice_axis(axis=-1, begin=0, end=4))
gt_bboxes[-1] *= im_scale
gt_difficults.append(y.slice_axis(axis=-1, begin=5, end=6) if y.shape[-1] > 5 else None) # update metric
for det_bbox, det_id, det_score, gt_bbox, gt_id, gt_diff in zip(det_bboxes, det_ids, det_scores, gt_bboxes, gt_ids, gt_difficults):
eval_metric.update(det_bbox, det_id, det_score, gt_bbox, gt_id, gt_diff)
return eval_metric.get() def get_lr_at_iter(alpha):
return 1. / 3. * (1 - alpha) + alpha def train(net, train_data, val_data, eval_metric, ctx, args):
"""Training pipeline"""
net.collect_params().setattr('grad_req', 'null')
net.collect_train_params().setattr('grad_req', 'write')
trainer = gluon.Trainer(
net.collect_train_params(), # fix batchnorm, fix first stage, etc...
'sgd',
{'learning_rate': args.lr,
'wd': args.wd,
'momentum': args.momentum,
'clip_gradient': 5}) # lr decay policy
lr_decay = float(args.lr_decay)
lr_steps = sorted([float(ls) for ls in args.lr_decay_epoch.split(',') if ls.strip()])
lr_warmup = float(args.lr_warmup) # avoid int division # TODO(zhreshold) losses?
rpn_cls_loss = mx.gluon.loss.SigmoidBinaryCrossEntropyLoss(from_sigmoid=False)
rpn_box_loss = mx.gluon.loss.HuberLoss(rho=1/9.) # == smoothl1
rcnn_cls_loss = mx.gluon.loss.SoftmaxCrossEntropyLoss()
rcnn_box_loss = mx.gluon.loss.HuberLoss() # == smoothl1
metrics = [mx.metric.Loss('RPN_Conf'),
mx.metric.Loss('RPN_SmoothL1'),
mx.metric.Loss('RCNN_CrossEntropy'),
mx.metric.Loss('RCNN_SmoothL1'),] rpn_acc_metric = RPNAccMetric()
rpn_bbox_metric = RPNL1LossMetric()
rcnn_acc_metric = RCNNAccMetric()
rcnn_bbox_metric = RCNNL1LossMetric()
metrics2 = [rpn_acc_metric, rpn_bbox_metric, rcnn_acc_metric, rcnn_bbox_metric] # set up logger
logging.basicConfig()
logger = logging.getLogger()
logger.setLevel(logging.INFO)
log_file_path = args.save_prefix + '_train.log'
log_dir = os.path.dirname(log_file_path)
if log_dir and not os.path.exists(log_dir):
os.makedirs(log_dir)
fh = logging.FileHandler(log_file_path)
logger.addHandler(fh)
logger.info(args)
if args.verbose:
logger.info('Trainable parameters:')
logger.info(net.collect_train_params().keys())
logger.info('Start training from [Epoch {}]'.format(args.start_epoch))
best_map = [0]
for epoch in range(args.start_epoch, args.epochs):
mix_ratio = 1.0
if args.mixup:
# TODO(zhreshold) only support evenly mixup now, target generator needs to be modified otherwise
train_data._dataset.set_mixup(np.random.uniform, 0.5, 0.5)
mix_ratio = 0.5
if epoch >= args.epochs - args.no_mixup_epochs:
train_data._dataset.set_mixup(None)
mix_ratio = 1.0
while lr_steps and epoch >= lr_steps[0]:
new_lr = trainer.learning_rate * lr_decay
lr_steps.pop(0)
trainer.set_learning_rate(new_lr)
logger.info("[Epoch {}] Set learning rate to {}".format(epoch, new_lr))
for metric in metrics:
metric.reset()
tic = time.time()
btic = time.time()
net.hybridize(static_alloc=True)
base_lr = trainer.learning_rate
for i, batch in enumerate(train_data):
if epoch == 0 and i <= lr_warmup:
# adjust based on real percentage
new_lr = base_lr * get_lr_at_iter(i / lr_warmup)
if new_lr != trainer.learning_rate:
if i % args.log_interval == 0:
logger.info('[Epoch 0 Iteration {}] Set learning rate to {}'.format(i, new_lr))
trainer.set_learning_rate(new_lr)
batch = split_and_load(batch, ctx_list=ctx)
batch_size = len(batch[0])
losses = []
metric_losses = [[] for _ in metrics]
add_losses = [[] for _ in metrics2]
with autograd.record():
for data, label, rpn_cls_targets, rpn_box_targets, rpn_box_masks in zip(*batch):
gt_label = label[:, :, 4:5]
gt_box = label[:, :, :4]
cls_pred, box_pred, roi, samples, matches, rpn_score, rpn_box, anchors = net(data, gt_box)
# losses of rpn
rpn_score = rpn_score.squeeze(axis=-1)
num_rpn_pos = (rpn_cls_targets >= 0).sum()
rpn_loss1 = rpn_cls_loss(rpn_score, rpn_cls_targets, rpn_cls_targets >= 0) * rpn_cls_targets.size / num_rpn_pos
rpn_loss2 = rpn_box_loss(rpn_box, rpn_box_targets, rpn_box_masks) * rpn_box.size / num_rpn_pos
# rpn overall loss, use sum rather than average
rpn_loss = rpn_loss1 + rpn_loss2
# generate targets for rcnn
cls_targets, box_targets, box_masks = net.target_generator(roi, samples, matches, gt_label, gt_box)
# losses of rcnn
num_rcnn_pos = (cls_targets >= 0).sum()
rcnn_loss1 = rcnn_cls_loss(cls_pred, cls_targets, cls_targets >= 0) * cls_targets.size / cls_targets.shape[0] / num_rcnn_pos
rcnn_loss2 = rcnn_box_loss(box_pred, box_targets, box_masks) * box_pred.size / box_pred.shape[0] / num_rcnn_pos
rcnn_loss = rcnn_loss1 + rcnn_loss2
# overall losses
losses.append(rpn_loss.sum() * mix_ratio + rcnn_loss.sum() * mix_ratio)
metric_losses[0].append(rpn_loss1.sum() * mix_ratio)
metric_losses[1].append(rpn_loss2.sum() * mix_ratio)
metric_losses[2].append(rcnn_loss1.sum() * mix_ratio)
metric_losses[3].append(rcnn_loss2.sum() * mix_ratio)
add_losses[0].append([[rpn_cls_targets, rpn_cls_targets>=0], [rpn_score]])
add_losses[1].append([[rpn_box_targets, rpn_box_masks], [rpn_box]])
add_losses[2].append([[cls_targets], [cls_pred]])
add_losses[3].append([[box_targets, box_masks], [box_pred]])
autograd.backward(losses)
for metric, record in zip(metrics, metric_losses):
metric.update(0, record)
for metric, records in zip(metrics2, add_losses):
for pred in records:
metric.update(pred[0], pred[1])
trainer.step(batch_size)
# update metrics
if args.log_interval and not (i + 1) % args.log_interval:
# msg = ','.join(['{}={:.3f}'.format(*metric.get()) for metric in metrics])
msg = ','.join(['{}={:.3f}'.format(*metric.get()) for metric in metrics + metrics2])
logger.info('[Epoch {}][Batch {}], Speed: {:.3f} samples/sec, {}'.format(
epoch, i, args.log_interval * batch_size/(time.time()-btic), msg))
btic = time.time() msg = ','.join(['{}={:.3f}'.format(*metric.get()) for metric in metrics])
logger.info('[Epoch {}] Training cost: {:.3f}, {}'.format(
epoch, (time.time()-tic), msg))
# if not (epoch + 1) % args.val_interval: # # consider reduce the frequency of validation to save time
# map_name, mean_ap = validate(net, val_data, ctx, eval_metric)
# val_msg = '\n'.join(['{}={}'.format(k, v) for k, v in zip(map_name, mean_ap)]) # logger.info('[Epoch {}] Validation: \n{}'.format(epoch, val_msg))
# current_map = float(mean_ap[-1])
# else:
# current_map = 0.
current_map = 0
save_params(net, logger, best_map, current_map, epoch, args.save_interval, args.save_prefix) if __name__ == '__main__':
args = parse_args()
# fix seed for mxnet, numpy and python builtin random generator.
gutils.random.seed(args.seed) # training contexts
ctx = [mx.gpu(int(i)) for i in args.gpus.split(',') if i.strip()]
ctx = ctx if ctx else [mx.cpu()]
args.batch_size = len(ctx) # 1 batch per device # network
net_name = '_'.join(('faster_rcnn', args.network, args.dataset))
args.save_prefix += net_name
net = get_model(net_name, pretrained_base=True)
if args.resume.strip():
net.load_parameters(args.resume.strip())
else:
for param in net.collect_params().values():
if param._data is not None:
continue
param.initialize()
net.collect_params().reset_ctx(ctx) # training data
train_dataset, val_dataset, eval_metric = get_dataset(args.dataset, args)
train_data, val_data = get_dataloader(
net, train_dataset, val_dataset, args.batch_size, args.num_workers) # training
train(net, train_data, val_data, eval_metric, ctx, args)
检测部分，是在demo 下修改的，填了几个参数，可以用lst文件遍历了，用cv2画图，不用那个matplotlib了
"""Faster RCNN Demo script."""
import os
import argparse
import mxnet as mx
import gluoncv as gcv
from gluoncv.data.transforms import presets
from matplotlib import pyplot as plt
import cv2 font = cv2.FONT_HERSHEY_SIMPLEX def parse_args():
parser = argparse.ArgumentParser(description='Test with Faster RCNN networks.')
parser.add_argument('--network', type=str, default='faster_rcnn_resnet50_v1b_coco',
help="Faster RCNN full network name")
parser.add_argument('--images', type=str, default='',
help='Test images, use comma to split multiple.')
parser.add_argument('--gpus', type=str, default='',
help='Training with GPUs, you can specify 1,3 for example.')
parser.add_argument('--pretrained', type=str, default='True',
help='Load weights from previously saved parameters. You can specify parameter file name.')
parser.add_argument('--thresh', type=float, default=0.5,
help='Threshold of object score when visualize the bboxes.')
# add_lst
parser.add_argument('--lst', type=str,default='',help="predict's lst file")
args = parser.parse_args()
return args if __name__ == '__main__':
args = parse_args()
# context list
ctx = [mx.gpu(int(i)) for i in args.gpus.split(',') if i.strip()]
ctx = [mx.cpu()] if not ctx else ctx # grab some image if not specified
if not args.images.strip() and args.lst=='':
gcv.utils.download('https://github.com/dmlc/web-data/blob/master/' +
'gluoncv/detection/biking.jpg?raw=true', 'biking.jpg')
image_list = ['biking.jpg']
else:
image_list = [x.strip() for x in args.images.split(',') if x.strip()] cnt = 0
if args.lst!='':
print(args.lst)
file = open('val_front_0913.lst')
image_list = []
for line in file:
line = line.split('\t')
print('/mnt/hdfs-data-4/data/jian.yin/val_front_0913/'+line[-1][:-1])
image_list.append('/mnt/hdfs-data-4/data/jian.yin/val_front_0913/'+line[-1][:-1])
cnt+=1
print 'sum of pic ',cnt if args.pretrained.lower() in ['true', '', 'yes', 't']:
net = gcv.model_zoo.get_model(args.network, pretrained=True)
else:
net = gcv.model_zoo.get_model(args.network, pretrained=False, pretrained_base=False)
net.load_parameters(args.pretrained)
net.set_nms(0.3, 200)
net.collect_params().reset_ctx(ctx = ctx) ax = None # write plt.txt
fw = open('draw/plt.txt','w')
dict = {}
cnt1 = 0
for image in image_list:
dict['url'] = image
bbox_list = []
x, img = presets.rcnn.load_test(image, short=net.short, max_size=net.max_size)
img_h = img.shape[0]
img_w = img.shape[1] x = x.as_in_context(ctx[0])
ids, scores, bboxes = [xx[0].asnumpy() for xx in net(x)] original_img = cv2.imread(image)
original_img_h = original_img.shape[0]
original_img_w = original_img.shape[1] for i in range(scores.shape[0]):
if scores[i] > args.thresh:
x1 = int(bboxes[i][0]*original_img_h/img_h)
y1 = int(bboxes[i][1]*original_img_w/img_w)
x2 = int(bboxes[i][2]*original_img_h/img_h)
y2 = int(bboxes[i][3]*original_img_w/img_w) bbox_list.append((float(scores[i]),x1,y1,x2,y2))
dict['bbox'] = bbox_list
fw.write(str(dict)+'\n')
cnt1+=1
print 'The last ',cnt-cnt1
fw.close()
# cv2.rectangle(original_img, (x1, y1), (x2, y2), (255,0,0), 3)
# cv2.putText(original_img,'person '+str(scores[i]),(x1,y1),font,0.5,(255,0,0),2)
# cv2.imwrite('draw/'+str(cnt)+'.jpg', original_img) # print(bboxes)
# ax = gcv.utils.viz.plot_bbox(img, bboxes, scores, ids, thresh=args.thresh,
# class_names=net.classes, ax=ax)
# plt.savefig(str(cnt)+'predict.jpg')
# cnt+=1
# plt.show()
把得分情况，锚框位置都写在文件里了，不用每次跑模型来得到，想怎么都可以了。plt.py
import cv2
import os
font = cv2.FONT_HERSHEY_SIMPLEX file = open('plt.txt')
cnt = 1
for line in file:
dict = eval(line)
url = dict['url']
bbox = dict['bbox']
img = cv2.imread(url)
for i in range(len(bbox)):
score = bbox[i][0]
score = '%.2f' % score
x1 = bbox[i][1]
y1 = bbox[i][2]
x2 = bbox[i][3]
y2 = bbox[i][4]
cv2.rectangle(img, (x1, y1), (x2, y2), (255,0,0), 3)
cv2.putText(img,'person '+str(score),(x1,y1),font,0.5,(255,0,0),2)
url = url.split('/')
x_url = url[5]+'/'+url[6]+'/'+url[7]+'/'+url[8]
if not os.path.exists(url[5]+'/'+url[6]+'/'+url[7]+'/'):
os.makedirs(url[5]+'/'+url[6]+'/'+url[7]+'/')
cv2.imwrite(x_url, img)
print('The last ',6137-cnt)
cnt+=1
gluoncv 训练自己的数据集，进行目标检测的更多相关文章
- 目标检测之YOLO V2 V3
YOLO V2 YOLO V2是在YOLO的基础上,融合了其他一些网络结构的特性(比如:Faster R-CNN的Anchor,GooLeNet的\(1\times1\)卷积核等),进行的升级.其目的 ...
- AI佳作解读系列(五) － 目标检测二十年技术综述
计算机视觉中的目标检测,因其在真实世界的大量应用需求,比如自动驾驶.视频监控.机器人视觉等,而被研究学者广泛关注. 上周四,arXiv新出一篇目标检测文献<Object Detection ...
- 目标检测：yolo-v3与faster-rcnn
一. 算法背景 1. 机器视觉实际应用往往涉及包含多个物体的复杂场景,基于深度卷积神经网络的特征提取器,需要结合其他算法来准确定位多个目标,并进行识别. 2. 工业领域,目标检测算法在安防和质检系统都 ...
- Notebook交互式完成目标检测任务
摘要:本文将介绍一种在Notebook中进行算法开发的新方式,新手也能够快速训练自己的模型. 目标检测是计算机视觉中非常常用且基础的任务,但是由于目标检测任务的复杂性,往往令新手望而却步.本文将介绍一 ...
- 【神经网络与深度学习】【计算机视觉】RCNN- 将CNN引入目标检测的开山之作
转自:https://zhuanlan.zhihu.com/p/23006190?refer=xiaoleimlnote 前面一直在写传统机器学习.从本篇开始写一写 深度学习的内容. 可能需要一定的神 ...
- 第三十二节，使用谷歌Object Detection API进行目标检测、训练新的模型(使用VOC 2012数据集)
前面已经介绍了几种经典的目标检测算法,光学习理论不实践的效果并不大,这里我们使用谷歌的开源框架来实现目标检测.至于为什么不去自己实现呢?主要是因为自己实现比较麻烦,而且调参比较麻烦,我们直接利用别人的 ...
- 目标检测算法SSD之训练自己的数据集
目标检测算法SSD之训练自己的数据集 prerequesties 预备知识/前提条件 下载和配置了最新SSD代码 git clone https://github.com/weiliu89/caffe ...
- 目标检测算法SSD在window环境下GPU配置训练自己的数据集
由于最近想试一下牛掰的目标检测算法SSD.于是乎,自己做了几千张数据(实际只有几百张,利用数据扩充算法比如镜像,噪声,切割,旋转等扩充到了几千张,其实还是很不够).于是在网上找了相关的介绍,自己处理数 ...
- tensorflow目标检测API之训练自己的数据集
1.训练文件的配置 将生成的csv和record文件都放在新建的mydata文件夹下,并打开object_detection文件夹下的data文件夹,复制一个后缀为.pbtxt的文件到mtdata文件 ...
随机推荐
- Apache mod_rewrite
mod_rewrite是Apache的一个非常强大的功能,它可以实现伪静态页面.下面我详细说说它的使用方法!对初学者很有用的哦! 1.检测Apache是否支持mod_rewrite phpinfo() ...
- 三、cent OS安装配置nginx
简介Tengine是淘宝发起的web服务器项目,简单的讲就是对nginx进行了二次开发并提供了更丰富的功能,官网地址:http://tengine.taobao.org/ 下载nginx这里使用淘宝二 ...
- 撩课-Python-每天5道面试题-第1天
一. 尽可能详细的描述出一个应用软件, 比如QQ, 在计算机中运行时涉及的软硬件, 以及说明我们编程的侧重点? 电脑开机, 从硬盘中(外部存储设备)加载操作系统(系统软件)到内存(内部存储设备), 并 ...
- InfluxDB 的用户
InfluxDB 的用户有三种: cluster admin 集群admin database admin 数据库admin database user 数据库用户 cluster admin ...
- Redis-概述
Redis支持的类型: String,List,Map,Set,Sorted set Redis的持久化: 1.Redis DataBase (RDB): RDB是在某个时间点将数据写入一个临时文件, ...
- 《JavaWeb从入门到改行》分页功能的实现
@目录 什么是分页 ? 两个子模块功能的问题分析 和 解决方案 有条件查和无条件查询的影响 和 解决方案 项目案例: mysql + commons-dbutils+itcast-tools+Base ...
- N次剩余和二次剩余
N次剩余 给定 \(N,a,P\),且 \(P\) 最好为质数 可以算出 \(x^N\equiv a(mod~p)\) 的解 首先可以算出 \(P\) 的原根 \(g\) 解方程 \(g^y\equi ...
- JS实现图片放大镜
将一个小图放置在一个小盒子里,当鼠标在小盒子里移动时,出现一个移动块,右侧出现一个大盒子,显示出小盒子中移动块所在区域的等比例放大的图片内容.需要实现的效果如下: 基本实现思路为:右侧大盒子为一个可视 ...
- iView定制主题报错问题的解决方法
按照iView官网来是这样的: 1. 在main.js当前目录下新建themes文件夹,里面新建一个叫blue.less的文件 2. 在mian.js里面引入blue.less文件 3. blue.l ...
- layui-open-上传文件
<!--选择文件上传--> <script id="upload_file_dialog" type="text/html"> < ...