def train():
dataset = Preprocessor()
dataloader = data_.DataLoader(dataset,
batch_size=1,
shuffle=True,
num_workers=4)
faster_rcnn = FasterRCNN_vgg16()
trainer = FasterRCNNTrainer(faster_rcnn).cuda()
epochs = 12
best_map = 0
lr_ = 1e-3
for epoch in range(epochs):
trainer.reset_meters()
total_loss = 0
for ii, (img, bbox_, label, scale) in enumerate(dataloader):
scale = scalar(scale)
img, bbox, label = img.cuda().float(), bbox_.cuda(), label.cuda()
loss = trainer.train_step(img, bbox, label, scale)
total_loss += loss[-1].item()
trainer.save(save_path='checkpoints/%d.pth' % epoch)
print('Epoch [%d] total loss: %.4f' %
(epoch + 1, total_loss / len(dataloader)))
def main():
faster_rcnn = FasterRCNNVGG16(mask=opt.mask)
trainer = FasterRCNNTrainer(faster_rcnn).cuda()
assert os.path.isfile(
args.load_path), f"Need valid checkpoint, {args.load_path} not found"
trainer.load(args.load_path)
'''
Check to make sure weights are dense
'''
for n, m in trainer.named_modules():
if hasattr(m, 'sparse'):
m.sparse = False
for n, m in trainer.named_modules():
if hasattr(m, 'weight'):
if m.weight.is_sparse:
print("Weights are already sparse")
return
print("\n\n=========SIZE BEFORE=============")
try:
trainer.faster_rcnn.set_pruned()
except:
print("No masks.")
get_size(trainer)
trainer.quantize(bits=args.bits, verbose=args.verbose)
print("\n\n=========SIZE AFTER==============")
get_size(trainer)
print("Saving a maskedmodel")
trainer.save(save_path=args.save_path)
print("Saving a SparseDense Model")
trainer.replace_with_sparsedense()
sd_file = args.save_path.split("/")
sd_file[-1] = "SparseDense_" + sd_file[-1]
sd_file = "/".join(sd_file)
trainer.save(save_path=sd_file)
def train(train_set,
val_set,
load_path=False,
epochs=1,
lr=1e-3,
record_every=300,
lr_decay=1e-3,
test_num=500):
'''
Uses the training set and validation set as arguments to create dataloader. Loads and trains model
'''
train_dataloader = td.DataLoader(train_set,
batch_size=1,
pin_memory=False,
shuffle=True)
test_dataloader = td.DataLoader(val_set, batch_size=1, pin_memory=True)
faster_rcnn = RFCNResnet101().cuda()
print('model construct completed')
trainer = FasterRCNNTrainer(faster_rcnn).cuda()
saved_loss = []
iterations = []
if load_path:
trainer.load(load_path)
print('load pretrained model from %s' % load_path)
state_dict = t.load(load_path)
saved_loss = state_dict['losses']
iterations = state_dict['iterations']
best_map = 0
lr_ = lr
for epoch in range(epochs):
trainer.reset_meters()
for ii, (img, bbox_, label_,
scale) in tqdm(enumerate(train_dataloader)):
scale = at.scalar(scale)
img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda()
losses = trainer.train_step(img, bbox, label, scale)
loss_info = 'Iter {}; Losses: RPN loc {}, RPN cls: {}, ROI loc {}, ROI cls {}, Total:{}'.format(
str(ii), "%.3f" % losses[0].cpu().data.numpy(),
"%.3f" % losses[1].cpu().data.numpy(),
"%.3f" % losses[2].cpu().data.numpy(),
"%.3f" % losses[3].cpu().data.numpy(),
"%.3f" % losses[4].cpu().data.numpy())
print(loss_info)
if (ii + 1) % record_every == 0:
iterations.append(ii + 1)
saved_loss.append([
losses[0].cpu().item(), losses[1].cpu().item(),
losses[2].cpu().item(), losses[3].cpu().item(),
losses[4].cpu().item()
])
kwargs = {"losses": saved_loss, "iterations": iterations}
trainer.save(saved_loss=saved_loss, iterations=iterations)
print("new model saved")
def train(**kwargs):
opt._parse(kwargs) # 解析配置参数
#
dataset = Dataset(opt) # 训练集 voc2007 5011 张
print('load data')
dataloader = data_.DataLoader(dataset, \
batch_size=1, \
shuffle=True, \
# pin_memory=True,
num_workers=opt.num_workers)
testset = TestDataset(opt, split='val') # 验证集 2500左右
test_dataloader = data_.DataLoader(testset,
batch_size=1,
num_workers=opt.test_num_workers,
shuffle=False, \
pin_memory=True
)
faster_rcnn = FasterRCNN_ResNet50() # 生成一个faster-rcnn实例
print('model construct completed')
trainer = FasterRCNNTrainer(faster_rcnn).cuda() # tocuda
if opt.load_path: # 加载与训练模型
trainer.load(opt.load_path)
print('load pretrained model from %s' % opt.load_path)
best_map = 0
lr_ = opt.lr
writer = SummaryWriter('logs', comment='faster-rcnn-vgg16')
global_step = 0
for epoch in range(opt.epoch): # 开始迭代 14轮 0-12 13个epoch
for ii, (img, bbox_, label_, scale) in tqdm(enumerate(dataloader)):
scale = at.scalar(scale)
img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda()
loss = trainer.train_step(img, bbox, label, scale)
rpn_loc_loss, rpn_cls_loss, roi_loc_loss, roi_cls_loss, total_loss = loss
writer.add_scalar('rpn_loc_loss', rpn_loc_loss.detach().cpu().numpy(), global_step)
writer.add_scalar('rpn_cls_loss', rpn_cls_loss.detach().cpu().numpy(), global_step)
writer.add_scalar('roi_loc_loss', roi_loc_loss.detach().cpu().numpy(), global_step)
writer.add_scalar('roi_cls_loss', roi_cls_loss.detach().cpu().numpy(), global_step)
writer.add_scalar('total_loss', total_loss.detach().cpu().numpy(), global_step)
global_step += 1
if (ii + 1) % opt.plot_every == 0:
pass
eval_result = eval(test_dataloader, faster_rcnn, test_num=opt.test_num)
lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr']
log_info = 'lr:{}, map:{}'.format(str(lr_), str(eval_result['map']))
print(log_info)
if eval_result['map'] > best_map:
best_map = eval_result['map']
best_path = trainer.save(best_map=best_map)
if epoch == 9:
trainer.load(best_path)
trainer.faster_rcnn.scale_lr(opt.lr_decay)
lr_ = lr_ * opt.lr_decay
if epoch == 13:
break
def main():
dataset = Dataset(opt)
dataloader = data_.DataLoader(dataset, \
batch_size=1, \
shuffle=True, \
# pin_memory=True,
num_workers=opt.num_workers)
testset = TestDataset(opt, split='val')
test_dataloader = data_.DataLoader(testset,
batch_size=1,
num_workers=opt.test_num_workers,
shuffle=False, \
pin_memory=True
)
print(f"TRAIN SET: {len(dataloader)} | TEST SET: {len(test_dataloader)}")
faster_rcnn = FasterRCNNVGG16(mask=opt.mask)
print('model construct completed')
trainer = FasterRCNNTrainer(faster_rcnn).cuda()
best_map = 0
lr_ = opt.lr
if opt.load_path:
assert os.path.isfile(opt.load_path), 'Checkpoint {} does not exist.'.format(opt.load_path)
checkpoint = torch.load(opt.load_path)['other_info']
trainer.load(opt.load_path)
print("="*30+" Checkpoint "+"="*30)
print("Loaded checkpoint '{}' (epoch {})".format(opt.load_path, 1)) #no saved epoch, put in 1 for now
if args.prune_by_std:
trainer.faster_rcnn.prune_by_std(args.sensitivity)
else:
trainer.faster_rcnn.prune_by_percentile(q=args.percentile)
prune_utils.print_nonzeros(trainer.faster_rcnn)
train(opt, faster_rcnn, dataloader, test_dataloader, trainer, lr_, best_map)
trainer.faster_rcnn.set_pruned()
trainer.save(save_path=args.save_path)
else:
print("Must specify load path to pretrained model")
def train(individual, **kwargs):
opt._parse(kwargs)
dataset = Dataset(opt)
print('load data')
dataloader = data_.DataLoader(dataset,
batch_size=1,
shuffle=True,
num_workers=opt.num_workers)
testset = TestDataset(opt)
test_dataloader = data_.DataLoader(testset,
batch_size=1,
num_workers=opt.test_num_workers,
shuffle=False,
pin_memory=True)
faster_rcnn = FasterRCNN_mine(individual)
print('model construct completed')
trainer = FasterRCNNTrainer(faster_rcnn).cuda()
best_map = 0
lr_ = opt.lr
for epoch in range(opt.epoch):
trainer.reset_meters()
for ii, (img, bbox_, label_, scale) in tqdm(enumerate(dataloader)):
scale = at.scalar(scale)
img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda()
trainer.train_step(img, bbox, label, scale)
if (ii + 1) % opt.plot_every == 0:
if os.path.exists(opt.debug_file):
ipdb.set_trace()
ori_img_ = inverse_normalize(at.tonumpy(img[0]))
_bboxes, _labels, _scores = trainer.faster_rcnn.predict(
[ori_img_], visualize=True)
eval_result = eval(test_dataloader, faster_rcnn, test_num=opt.test_num)
lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr']
best_path = None
if eval_result['map'] > best_map:
best_map = eval_result['map']
best_path = trainer.save(best_map=best_map)
if epoch == 9:
trainer.load(best_path)
trainer.faster_rcnn.scale_lr(opt.lr_decay)
lr_ = lr_ * opt.lr_decay
individual.accuracy = best_map
def train(**kwargs):
opt._parse(kwargs) # 全部的设置
dataset = Dataset(opt) # 数据集
print('load data')
dataloader = data_.DataLoader(dataset, \
batch_size=1, \
shuffle=True, \
# pin_memory=True,
num_workers=opt.num_workers)
# pin memory：锁页内存，内存为所欲为的时候为true，详情见：https://blog.csdn.net/yangwangnndd/article/details/95385628
# num worker：加载数据的线程数，默认为8。具体数值的选取由训练时间决定，当训练时间快于加载时间时则需要增加线程
# shuffle=True允许数据打乱排序
testset = TestDataset(opt)
test_dataloader = data_.DataLoader(testset,
batch_size=1,
num_workers=opt.test_num_workers,
shuffle=False, \
pin_memory=True
)
faster_rcnn = FasterRCNNVGG16()
print('model construct completed')
trainer = FasterRCNNTrainer(faster_rcnn).cuda()
if opt.load_path: #接下来判断opt.load_path是否存在，如果存在，直接从opt.load_path读取预训练模型，然后将训练数据的label进行可视化操作
trainer.load(opt.load_path)
print('load pretrained model from %s' % opt.load_path)
trainer.vis.text(dataset.db.label_names, win='labels')
best_map = 0
lr_ = opt.lr
for epoch in range(
opt.epoch): # 训练迭代的次数opt.epoch=14也在config.py文件中都预先定义好，属于超参数
trainer.reset_meters() # 首先在可视化界面重设所有数据
for ii, (img, bbox_, label_, scale) in tqdm(enumerate(dataloader)):
scale = at.scalar(scale)
img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda()
# 然后从训练数据中枚举dataloader,设置好缩放范围，将img,bbox,label,scale全部设置为可gpu加速
trainer.train_step(
img, bbox, label, scale
) # 调用trainer.py中的函数trainer.train_step(img,bbox,label,scale)进行一次参数迭代优化过程
# 判断数据读取次数是否能够整除plot_every(是否达到了画图次数)
if (ii + 1) % opt.plot_every == 0:
# 如果达到判断debug_file是否存在，用ipdb工具设置断点
if os.path.exists(opt.debug_file):
ipdb.set_trace()
# plot loss
# 调用trainer中的trainer.vis.plot_many(trainer.get_meter_data())将训练数据读取并上传完成可视化
trainer.vis.plot_many(trainer.get_meter_data())
# plot groud truth bboxes
ori_img_ = inverse_normalize(at.tonumpy(img[0]))
gt_img = visdom_bbox(ori_img_, at.tonumpy(bbox_[0]),
at.tonumpy(label_[0]))
trainer.vis.img('gt_img', gt_img)
# 将每次迭代读取的图片用dataset文件里面的inverse_normalize()函数进行预处理，将处理后的图片调用Visdom_bbox
# plot predicti bboxes
_bboxes, _labels, _scores = trainer.faster_rcnn.predict(
[ori_img_], visualize=True)
pred_img = visdom_bbox(ori_img_, at.tonumpy(_bboxes[0]),
at.tonumpy(_labels[0]).reshape(-1),
at.tonumpy(_scores[0]))
trainer.vis.img('pred_img', pred_img)
# rpn confusion matrix(meter)
# 调用 trainer.vis.text将rpn_cm也就是RPN网络的混淆矩阵在可视化工具中显示出来
trainer.vis.text(str(trainer.rpn_cm.value().tolist()),
win='rpn_cm')
# roi confusion matrix
trainer.vis.img(
'roi_cm',
at.totensor(trainer.roi_cm.conf, False).float())
eval_result = eval(test_dataloader, faster_rcnn, test_num=opt.test_num)
trainer.vis.plot('test_map', eval_result['map'])
lr_ = trainer.faster_rcnn.optimizer.param_groups[0][
'lr'] # learning rate
log_info = 'lr:{}, map:{},loss:{}'.format(
str(lr_), str(eval_result['map']), str(trainer.get_meter_data()))
trainer.vis.log(log_info) # 将损失学习率以及map等信息及时显示更新
if eval_result['map'] > best_map:
best_map = eval_result['map']
best_path = trainer.save(best_map=best_map) # 用if判断语句永远保存效果最好的map
if epoch == 9:
trainer.load(best_path)
trainer.faster_rcnn.scale_lr(opt.lr_decay)
lr_ = lr_ * opt.lr_decay # if判断语句如果学习的epoch达到了9就将学习率*0.1变成原来的十分之一
if epoch == 13:
break
def train(**kwargs):
opt._parse(kwargs)
data_set = TrainDataset()
print('load data.')
data_loader = data_.DataLoader(data_set, batch_size=1, shuffle=True)
testset = TestDataset()
test_dataloader = data_.DataLoader(testset,
batch_size=1,
shuffle=False,
pin_memory=True)
faster_rcnn = FasterRCNNVGG16()
print('model construct.')
trainer = FasterRCNNTrainer(faster_rcnn).cuda()
if opt.load_path:
trainer.load(opt.load_path)
print('load pretrained model from %s' % opt.load_path)
lr = opt.lr
best_map = 0
for epoch in range(opt.epoch):
trainer.reset_meters()
for ii, (img, bbox, label, scale) in tqdm(enumerate(data_loader)):
img = img.cuda()
trainer.train_step(img, bbox, label, scale)
if (ii + 1) % opt.plot_every == 0:
ipdb.set_trace()
"""plot loss"""
trainer.vis.plot_many(trainer.get_meter_data())
"""plot gt_bbox"""
ori_img = inverse_normalize(img[0].cpu().numpy())
gt_img = visdom_bbox(ori_img, bbox[0].numpy(),
label[0].numpy())
trainer.vis.img('gt_img', gt_img)
"""plot predicted bbox"""
pred_bbox, pred_label, pred_score = trainer.faster_rcnn.predict(
[ori_img], visualize=True)
pred_img = visdom_bbox(ori_img, pred_bbox[0], pred_label[0],
pred_score[0])
trainer.vis.img('pred_img', pred_img)
# rpn confusion matrix(meter)
trainer.vis.text(str(trainer.rpn_cm.value().tolist()),
win='rpn_cm')
# roi confusion matrix
trainer.vis.img('roi_cm', trainer.roi_cm.conf.float().cpu())
eval_result = eval(test_dataloader, faster_rcnn, test_num=opt.test_num)
if eval_result['map'] > best_map:
best_map = eval_result['map']
best_path = trainer.save(best_map=best_map)
if epoch == 9:
trainer.load(best_path)
trainer.faster_rcnn.scale_lr(opt.lr_decay)
lr = lr * opt.lr_decay
trainer.vis.plot('test_map', eval_result['map'])
log_info = 'lr:{}, map:{},loss:{}'.format(
str(lr), str(eval_result['map']), str(trainer.get_meter_data()))
trainer.vis.log(log_info)
if epoch == 13:
print('finish!')
break
def train(**kwargs):
opt._parse(kwargs)
carrada = download('Carrada')
train_set = Carrada().get('Train')
val_set = Carrada().get('Validation')
test_set = Carrada().get('Test')
train_seqs = SequenceCarradaDataset(train_set)
val_seqs = SequenceCarradaDataset(val_set)
test_seqs = SequenceCarradaDataset(test_set)
train_seqs_loader = data_.DataLoader(train_seqs, \
batch_size=1, \
shuffle=True, \
# pin_memory=True,
num_workers=opt.num_workers)
val_seqs_loader = data_.DataLoader(val_seqs,
batch_size=1,
shuffle=False,
# pin_memory=True,
num_workers=opt.num_workers)
test_seqs_loader = data_.DataLoader(test_seqs,
batch_size=1,
shuffle=False,
# pin_memory=True,
num_workers=opt.num_workers)
# faster_rcnn = FasterRCNNVGG16(n_fg_class=3)
# faster_rcnn = FasterRCNNRESNET101(n_fg_class=3)
faster_rcnn = FasterRCNNRESNET18(n_fg_class=3)
print('model construct completed')
trainer = FasterRCNNTrainer(faster_rcnn).cuda()
scheduler = ExponentialLR(trainer.faster_rcnn.optimizer, gamma=0.9)
if opt.load_path:
trainer.load(opt.load_path)
print('load pretrained model from %s' % opt.load_path)
writer_path = os.path.join(opt.logs_path, opt.model_name)
os.makedirs(writer_path, exist_ok=True)
writer = SummaryWriter(writer_path)
iteration = 0
best_map = 0
lr_ = opt.lr
for epoch in range(opt.epoch):
print('Processing epoch: {}/{}'.format(epoch, opt.epoch))
trainer.reset_meters()
for n_seq, sequence_data in tqdm(enumerate(train_seqs_loader)):
seq_name, seq = sequence_data
path_to_frames = os.path.join(carrada, seq_name[0])
train_frame_set = CarradaDataset(opt, seq, 'box', opt.signal_type,
path_to_frames)
train_frame_loader = data_.DataLoader(train_frame_set,
batch_size=1,
shuffle=False,
num_workers=opt.num_workers)
for ii, (img, bbox_, label_, scale) in tqdm(enumerate(train_frame_loader)):
iteration += 1
scale = at.scalar(scale)
img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda()
img = normalize(img)
if opt.debug_step and (iteration+1) % opt.debug_step == 0:
trainer.train_step(img, bbox, label, scale, stop=True)
else:
trainer.train_step(img, bbox, label, scale)
if (iteration + 1) % opt.plot_every == 0:
if os.path.exists(opt.debug_file):
ipdb.set_trace()
train_results = trainer.get_meter_data()
writer.add_scalar('Losses/rpn_loc', train_results['rpn_loc_loss'],
iteration)
writer.add_scalar('Losses/rpn_cls', train_results['rpn_cls_loss'],
iteration)
writer.add_scalar('Losses/roi_loc', train_results['roi_loc_loss'],
iteration)
writer.add_scalar('Losses/roi_cls', train_results['roi_cls_loss'],
iteration)
writer.add_scalar('Losses/total', train_results['total_loss'],
iteration)
if (iteration + 1) % opt.img_every == 0:
ori_img_ = at.tonumpy(img[0])
gt_img = visdom_bbox(ori_img_,
at.tonumpy(bbox_[0]),
at.tonumpy(label_[0]))
gt_img_grid = make_grid(torch.from_numpy(gt_img))
writer.add_image('Ground_truth_img', gt_img_grid, iteration)
# plot predicti bboxes
_bboxes, _labels, _scores = trainer.faster_rcnn.predict([ori_img_], opt.signal_type,
visualize=True)
# FLAG: vis
pred_img = visdom_bbox(ori_img_,
at.tonumpy(_bboxes[0]),
at.tonumpy(_labels[0]).reshape(-1),
at.tonumpy(_scores[0]))
pred_img_grid = make_grid(torch.from_numpy(pred_img))
writer.add_image('Predicted_img', pred_img_grid, iteration)
if opt.train_eval and (iteration + 1) % opt.train_eval == 0:
train_eval_result, train_best_iou = eval(train_seqs_loader, faster_rcnn,
opt.signal_type)
writer.add_scalar('Train/mAP', train_eval_result['map'],
iteration)
writer.add_scalar('Train/Best_IoU', train_best_iou,
iteration)
eval_result, best_val_iou = eval(val_seqs_loader, faster_rcnn, opt.signal_type,
test_num=opt.test_num)
writer.add_scalar('Validation/mAP', eval_result['map'],
iteration)
writer.add_scalar('Validation/Best_IoU', best_val_iou,
iteration)
lr_ = scheduler.get_lr()[0]
writer.add_scalar('learning_rate', lr_, iteration)
log_info = 'lr:{}, map:{},loss:{}'.format(str(lr_),
str(eval_result['map']),
str(trainer.get_meter_data()))
print(log_info)
if eval_result['map'] > best_map:
test_result, test_best_iou = eval(test_seqs_loader, faster_rcnn, opt.signal_type,
test_num=opt.test_num)
writer.add_scalar('Test/mAP', test_result['map'],
iteration)
writer.add_scalar('Test/Best_IoU', test_best_iou,
iteration)
best_map = eval_result['map']
best_test_map = test_result['map']
best_path = trainer.save(best_val_map=best_map, best_test_map=best_test_map)
# best_path = trainer.save(best_map=best_map)
if (epoch + 1) % opt.lr_step == 0:
scheduler.step()
def train(**kwargs):
opt._parse(kwargs)
log = SummaryWriter(log_dir=opt.log_dir)
dataset = Dataset(opt)
print('load data')
dataloader = data_.DataLoader(dataset,
batch_size=1,
shuffle=True,
pin_memory=True,
num_workers=opt.num_workers)
testset = TestDataset(opt)
test_dataloader = data_.DataLoader(testset,
batch_size=1,
num_workers=opt.test_num_workers,
shuffle=False,
pin_memory=True
)
# 配置文件
# cfg = VGConf()
# 训练数据集
# trainset = Dataset(cfg)
# valset = Dataset(cfg, valid=True)
# 加载数据
# print("load data2..")
# dataloader = DataLoader(dataloader, batch_size=1, shuffle=True,
# pin_memory=True, num_workers=opt.num_workers)
# valloader = DataLoader(test_dataloader, batch_size=1, shuffle=False,
# pin_memory=True, num_workers=opt.num_workers)
faster_rcnn = FasterRCNNVGG16()
print('model construct completed')
trainer = FasterRCNNTrainer(faster_rcnn).cuda()
if opt.load_path:
trainer.load(opt.load_path)
print('load pretrained model from %s' % opt.load_path)
# trainer.vis.text(dataset.db.label_names, win='labels')
best_map = 0
lr_ = opt.lr
idx = 0
for epoch in range(opt.epoch):
trainer.reset_meters()
for ii, (img, bbox_, label_, scale) in enumerate(dataloader):
scale = at.scalar(scale)
img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda()
trainer.train_step(img, bbox, label, scale)
# 获取损失值
losses = trainer.get_meter_data()
log.add_scalars(main_tag='Training(batch)',
tag_scalar_dict=losses,
global_step=idx)
idx = idx+1
if (ii + 1) % opt.plot_every == 0:
# if os.path.exists(opt.debug_file):
# ipdb.set_trace()
# plot loss
# trainer.vis.plot_many(trainer.get_meter_data())
print(trainer.get_meter_data())
# plot groud truth bboxes
ori_img_ = inverse_normalize(at.tonumpy(img[0]))
# gt_img = visdom_bbox(ori_img_,
# at.tonumpy(bbox_[0]),
# at.tonumpy(label_[0]))
# trainer.vis.img('gt_img', gt_img)
# plot predicti bboxes
# _bboxes, _labels, _scores = trainer.faster_rcnn.predict([ori_img_], visualize=True)
# pred_img = visdom_bbox(ori_img_,
# at.tonumpy(_bboxes[0]),
# at.tonumpy(_labels[0]).reshape(-1),
# at.tonumpy(_scores[0]))
# trainer.vis.img('pred_img', pred_img)
# rpn confusion matrix(meter)
# trainer.vis.text(str(trainer.rpn_cm.value().tolist()), win='rpn_cm')
# roi confusion matrix
# trainer.vis.img('roi_cm', at.totensor(trainer.roi_cm.conf, False).float())
eval_result = eval(test_dataloader, faster_rcnn, test_num=opt.test_num)
log.add_scalar(tag='mAP', scalar_value=eval_result['map'], global_step=epoch)
# trainer.vis.plot('test_map', eval_result['map'])
lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr']
log_info = 'lr:{}, map:{},loss:{}'.format(str(lr_),
str(eval_result['map']),
str(trainer.get_meter_data()))
print(log_info)
# trainer.vis.log(log_info)
if eval_result['map'] > best_map:
best_map = eval_result['map']
best_path = trainer.save(best_map=best_map)
if epoch == 9:
trainer.load(best_path)
trainer.faster_rcnn.scale_lr(opt.lr_decay)
lr_ = lr_ * opt.lr_decay
if epoch == 13:
break
def train(**kwargs):
opt._parse(
kwargs
) #将调用函数时候附加的参数用，config.py文件里面的opt._parse()进行解释，然后获取其数据存储的路径，之后放到Dataset里面！
dataset = Dataset(opt)
print('load data')
dataloader = data_.DataLoader(dataset,
batch_size=1,
shuffle=True,
num_workers=opt.num_workers)
testset = TestDataset(opt)
test_dataloader = data_.DataLoader(
testset,
batch_size=1,
num_workers=opt.test_num_workers,
shuffle=False,
#pin_memory=True
) #pin_memory锁页内存,开启时使用显卡的内存，速度更快
faster_rcnn = FasterRCNNVGG16()
print('model construct completed')
trainer = FasterRCNNTrainer(faster_rcnn).cuda()
#判断opt.load_path是否存在，如果存在，直接从opt.load_path读取预训练模型，然后将训练数据的label进行可视化操作
if opt.load_path:
trainer.load(opt.load_path)
print('load pretrained model from %s' % opt.load_path)
trainer.vis.text(dataset.dataset.label_names, win='labels')
best_map = 0
lr_ = opt.lr
# 之后用一个for循环开始训练过程，而训练迭代的次数opt.epoch=14也在config.py文件中都预先定义好，属于超参数
for epoch in range(opt.epoch):
print('epoch {}/{}'.format(epoch, opt.epoch))
trainer.reset_meters() #首先在可视化界面重设所有数据
for ii, (img, bbox_, label_, scale) in tqdm(enumerate(dataloader)):
scale = array_tool.scalar(scale)
img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda()
trainer.train_step(img, bbox, label, scale)
if (ii + 1) % opt.plot_every == 0:
if os.path.exists(opt.debug_file):
ipdb.set_trace()
#可视化画出loss
trainer.vis.plot_many(trainer.get_meter_data())
#可视化画出groudtruth bboxes
ori_img_ = inverse_normalize(array_tool.tonumpy(img[0]))
gt_img = visdom_bbox(ori_img_, array_tool.tonumpy(bbox_[0]),
array_tool.tonumpy(label_[0]))
trainer.vis.img('gt_img', gt_img)
#可视化画出预测bboxes
# 调用faster_rcnn的predict函数进行预测，预测的结果保留在以_下划线开头的对象里面
_bboxes, _labels, _scores = trainer.faster_rcnn.predict(
[ori_img_], visualize=True)
pred_img = visdom_bbox(
ori_img_, array_tool.tonumpy(_bboxes[0]),
array_tool.tonumpy(_labels[0]).reshape(-1),
array_tool.tonumpy(_scores[0]))
trainer.vis.img('pred_img', pred_img)
# 调用 trainer.vis.text将rpn_cm也就是RPN网络的混淆矩阵在可视化工具中显示出来
trainer.vis.text(str(trainer.rpn_cm.value().tolist()),
win='rpn_cm')
#将roi_cm也就是roihead网络的混淆矩阵在可视化工具中显示出来
trainer.vis.img(
'roi_cm',
array_tool.totensor(trainer.roi_cm.conf, False).float())
eval_result = eval(test_dataloader, faster_rcnn, test_num=opt.test_num)
trainer.vis.plot('test_map', eval_result['map'])
lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr']
log_info = 'lr:{}, map:{}, loss{}'.format(
str(lr_), str(eval_result['map']), str(trainer.get_meter_data()))
trainer.vis.log(log_info) #将学习率以及map等信息及时显示更新
if eval_result['map'] > best_map:
best_map = eval_result['map']
best_path = trainer.save(best_map=best_map)
if epoch == 9: #if判断语句如果学习的epoch达到了9就将学习率*0.1变成原来的十分之一
trainer.load(best_path)
trainer.faster_rcnn.scale_lr(opt.lr_decay)
lr_ = lr_ * opt.lr_decay
if epoch == 13:
break
def train(**kwargs):
opt._parse(kwargs) #获得config设置信息
dataset = Dataset(opt) #传入opt，利用设置的数据集参数来创建训练数据集
print('load data')
dataloader = data_.DataLoader(dataset, \ #用创建的训练数据集创建训练DataLoader,代码仅支持batch_size=1
batch_size=1, \
shuffle=True, \
# pin_memory=True,
num_workers=opt.num_workers)
testset = TestDataset(opt) #传入opt，利用设置的数据集参数来加载测试数据集
test_dataloader = data_.DataLoader(testset, #用创建的测试数据集创建训练DataLoader,代码仅支持batch_size=1
batch_size=1,
num_workers=opt.test_num_workers,
shuffle=False, \
pin_memory=True
)
faster_rcnn = FasterRCNNVGG16() #创建以vgg为backbone的FasterRCNN网络
print('model construct completed')
trainer = FasterRCNNTrainer(faster_rcnn).cuda() #把创建好的FasterRCNN网络放入训练器
if opt.load_path: #若有FasterRCNN网络的预训练加载，则加载load_path权重
trainer.load(opt.load_path) #训练器加载权重
print('load pretrained model from %s' % opt.load_path)
trainer.vis.text(dataset.db.label_names, win='labels')
best_map = 0 #初始化best_map，训练时用于判断是否需要保存模型，类似打擂台后面用
lr_ = opt.lr #得到预设的学习率
for epoch in range(opt.epoch): #开始训练，训练次数为opt.epoch
trainer.reset_meters()
for ii, (img, bbox_, label_, scale) in tqdm(enumerate(dataloader)):
scale = at.scalar(scale) #进行类别处理得到scale（待定）
#bbox是gt_box坐标(ymin, xmin, ymax, xmax)
#label是类别的下标VOC_BBOX_LABEL_NAMES
#img是图片，代码仅支持batch_size=1的训练
img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda() #使用gpu训练
trainer.train_step(img, bbox, label, scale) #预处理完毕，进入模型
if (ii + 1) % opt.plot_every == 0: #可视化内容，（跳过）
if os.path.exists(opt.debug_file):
ipdb.set_trace()
# plot loss
trainer.vis.plot_many(trainer.get_meter_data())
# plot groud truth bboxes
ori_img_ = inverse_normalize(at.tonumpy(img[0]))
gt_img = visdom_bbox(ori_img_,
at.tonumpy(bbox_[0]),
at.tonumpy(label_[0]))
trainer.vis.img('gt_img', gt_img)
# plot predicti bboxes
_bboxes, _labels, _scores = trainer.faster_rcnn.predict([ori_img_], visualize=True)
pred_img = visdom_bbox(ori_img_,
at.tonumpy(_bboxes[0]),
at.tonumpy(_labels[0]).reshape(-1),
at.tonumpy(_scores[0]))
trainer.vis.img('pred_img', pred_img)
# rpn confusion matrix(meter)
trainer.vis.text(str(trainer.rpn_cm.value().tolist()), win='rpn_cm')
# roi confusion matrix
trainer.vis.img('roi_cm', at.totensor(trainer.roi_cm.conf, False).float())
eval_result = eval(test_dataloader, faster_rcnn, test_num=opt.test_num) #训练一个epoch评估一次
trainer.vis.plot('test_map', eval_result['map']) #可视化内容，（跳过）
lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr'] #获得当前的学习率
log_info = 'lr:{}, map:{},loss:{}'.format(str(lr_), #日志输出学习率，map，loss
str(eval_result['map']),
str(trainer.get_meter_data()))
trainer.vis.log(log_info) #可视化内容，（跳过）
if eval_result['map'] > best_map: #若这次评估的map大于之前最大的map则保存模型
best_map = eval_result['map'] #保存模型的map信息
best_path = trainer.save(best_map=best_map) #调用保存模型函数
if epoch == 9: #若训练到第9个epoch则加载之前最好的模型并且减低学习率继续训练
trainer.load(best_path) #加载模型
trainer.faster_rcnn.scale_lr(opt.lr_decay) #降低学习率
lr_ = lr_ * opt.lr_decay #获得当前学习率
if epoch == 13: #13个epoch停止训练
break
def train(**kwargs):
# opt._parse(kwargs)
print('load data')
dataloader = get_train_loader(opt.root_dir,
batch_size=opt.batch_size,
shuffle=opt.shuffle,
num_workers=opt.num_workers,
pin_memory=opt.pin_memory)
faster_rcnn = FasterRCNNVGG16()
print('model construct completed')
trainer = FasterRCNNTrainer(faster_rcnn).cuda()
# if opt.load_path:
# trainer.load(opt.load_path)
# print('load pretrained model from %s' % opt.load_path)
# trainer.vis.text(dataset.db.label_names, win='labels')
best_map = 0
lr_ = opt.lr
for epoch in range(opt.epoch):
trainer.reset_meters()
for ii, sample in tqdm(enumerate(dataloader)):
if len(sample.keys()) == 5:
img_id, img, bbox_, scale, label_ = sample['img_id'], sample['image'], sample['bbox'], sample['scale'], \
sample['label']
img, bbox, label = img.cuda().float(), bbox_.cuda(
), label_.cuda()
img, bbox, label = Variable(img), Variable(bbox), Variable(
label)
else:
img_id, img, bbox, scale, label = sample['img_id'], sample['image'], np.zeros((1, 0, 4)), \
sample['scale'], np.zeros((1, 0, 1))
img = img.cuda().float()
img = Variable(img)
# if label.size == 0:
# continue
scale = at.scalar(scale)
trainer.train_step(img_id, img, bbox, label, scale)
if (ii + 1) % opt.plot_every == 0:
if os.path.exists(opt.debug_file):
ipdb.set_trace()
# plot loss
trainer.vis.plot_many(trainer.get_meter_data())
# plot ground truth bboxes
ori_img_ = inverse_normalize(at.tonumpy(img[0]))
gt_img = visdom_bbox(ori_img_, at.tonumpy(bbox_[0]),
at.tonumpy(label_[0]))
trainer.vis.img('gt_img', gt_img)
# plot predicted bboxes
_bboxes, _labels, _scores = trainer.faster_rcnn.predict(
[ori_img_], visualize=True)
pred_img = visdom_bbox(ori_img_, at.tonumpy(_bboxes[0]),
at.tonumpy(_labels[0]).reshape(-1),
at.tonumpy(_scores[0]))
trainer.vis.img('pred_img', pred_img)
# rpn confusion matrix(meter)
trainer.vis.text(str(trainer.rpn_cm.value().tolist()),
win='rpn_cm')
# roi confusion matrix
trainer.vis.img(
'roi_cm',
at.totensor(trainer.roi_cm.conf, False).float())
if epoch % 10 == 0:
best_path = trainer.save(best_map=best_map)
def train(**kwargs):
opt._parse(kwargs)
dataset = Dataset(opt)
print('load data')
dataloader = data_.DataLoader(dataset,
batch_size=1,
shuffle=True,
# pin_memory=True,
num_workers=opt.num_workers)
testset = TestDataset(opt)
test_dataloader = data_.DataLoader(testset,
batch_size=1,
num_workers=opt.test_num_workers,
shuffle=False,
pin_memory=True
)
testset_all = TestDataset_all(opt, 'test2')
test_all_dataloader = data_.DataLoader(testset_all,
batch_size=1,
num_workers=opt.test_num_workers,
shuffle=False,
pin_memory=True
)
tsf = Transform(opt.min_size, opt.max_size)
faster_rcnn = FasterRCNNVGG16()
trainer = FasterRCNNTrainer(faster_rcnn).cuda()
print('model construct completed')
# 加载训练过的模型，在config配置路径就可以了
if opt.load_path:
trainer.load(opt.load_path)
print('load pretrained model from %s' % opt.load_path)
#提取蒸馏知识所需要的软标签
if opt.is_distillation == True:
opt.predict_socre = 0.3
for ii, (imgs, sizes, gt_bboxes_, gt_labels_, scale, id_) in tqdm(enumerate(dataloader)):
if len(gt_bboxes_) == 0:
continue
sizes = [sizes[0][0].item(), sizes[1][0].item()]
pred_bboxes_, pred_labels_, pred_scores_, features_ = trainer.faster_rcnn.predict(imgs, [
sizes])
img_file = os.path.join(
opt.voc_data_dir, 'JPEGImages', id_[0] + '.jpg')
ori_img = read_image(img_file, color=True)
img, pred_bboxes_, pred_labels_, scale_ = tsf(
(ori_img, pred_bboxes_[0], pred_labels_[0]))
#去除软标签和真值标签重叠过多的部分，去除错误的软标签
pred_bboxes_, pred_labels_, pred_scores_ = py_cpu_nms(
gt_bboxes_[0], gt_labels_[0], pred_bboxes_, pred_labels_, pred_scores_[0])
#存储软标签，这样存储不会使得GPU占用过多
np.save('label/' + str(id_[0]) + '.npy', pred_labels_)
np.save('bbox/' + str(id_[0]) + '.npy', pred_bboxes_)
np.save('feature/' + str(id_[0]) + '.npy', features_)
np.save('score/' + str(id_[0]) + '.npy', pred_scores_)
opt.predict_socre = 0.05
t.cuda.empty_cache()
# visdom 显示所有类别标签名
trainer.vis.text(dataset.db.label_names, win='labels')
best_map = 0
lr_ = opt.lr
for epoch in range(opt.epoch):
print('epoch=%d' % epoch)
# 重置混淆矩阵
trainer.reset_meters()
# tqdm可以在长循环中添加一个进度提示信息，用户只需要封装任意的迭代器 tqdm(iterator)，
# 是一个快速、扩展性强
for ii, (img, sizes, bbox_, label_, scale, id_) in tqdm(enumerate(dataloader)):
if len(bbox_) == 0:
continue
scale = at.scalar(scale)
img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda()
# 训练的就这一步 下面的都是打印的信息
# 转化成pytorch能够计算的格式，转tensor格式
if opt.is_distillation == True:
#读取软标签
teacher_pred_labels = np.load(
'label/' + str(id_[0]) + '.npy')
teacher_pred_bboxes = np.load(
'bbox/' + str(id_[0]) + '.npy')
teacher_pred_features_ = np.load(
'feature/' + str(id_[0]) + '.npy')
teacher_pred_scores = np.load(
'score/' + str(id_[0]) + '.npy')
#格式转换
teacher_pred_bboxes = teacher_pred_bboxes.astype(np.float32)
teacher_pred_labels = teacher_pred_labels.astype(np.int32)
teacher_pred_scores = teacher_pred_scores.astype(np.float32)
#转成pytorch格式
teacher_pred_bboxes_ = at.totensor(teacher_pred_bboxes)
teacher_pred_labels_ = at.totensor(teacher_pred_labels)
teacher_pred_scores_ = at.totensor(teacher_pred_scores)
teacher_pred_features_ = at.totensor(teacher_pred_features_)
#使用GPU
teacher_pred_bboxes_ = teacher_pred_bboxes_.cuda()
teacher_pred_labels_ = teacher_pred_labels_.cuda()
teacher_pred_scores_ = teacher_pred_scores_.cuda()
teacher_pred_features_ = teacher_pred_features_.cuda()
# 如果dataset.py 中的Transform 设置了图像翻转,就要使用这个判读软标签是否一起翻转
if(teacher_pred_bboxes_[0][1] != bbox[0][0][1]):
_, o_C, o_H, o_W = img.shape
teacher_pred_bboxes_ = flip_bbox(
teacher_pred_bboxes_, (o_H, o_W), x_flip=True)
losses = trainer.train_step(img, bbox, label, scale, epoch,
teacher_pred_bboxes_, teacher_pred_labels_, teacher_pred_features_, teacher_pred_scores)
else:
trainer.train_step(img, bbox, label, scale, epoch)
# visdom显示的信息
if (ii + 1) % opt.plot_every == 0:
if os.path.exists(opt.debug_file):
ipdb.set_trace()
# plot loss
trainer.vis.plot_many(trainer.get_meter_data())
# plot groud truth bboxes
ori_img_ = inverse_normalize(at.tonumpy(img[0]))
gt_img = visdom_bbox(ori_img_,
at.tonumpy(bbox_[0]),
at.tonumpy(label_[0]))
trainer.vis.img('gt_img', gt_img)
gt_img = visdom_bbox(ori_img_,
at.tonumpy(teacher_pred_bboxes_),
at.tonumpy(teacher_pred_labels_),
at.tonumpy(teacher_pred_scores_))
trainer.vis.img('gt_img_all', gt_img)
# plot predicti bboxes
_bboxes, _labels, _scores, _ = trainer.faster_rcnn.predict(
[ori_img_], visualize=True)
pred_img = visdom_bbox(ori_img_,
at.tonumpy(_bboxes[0]),
at.tonumpy(_labels[0]).reshape(-1),
at.tonumpy(_scores[0]))
trainer.vis.img('pred_img', pred_img)
# 混淆矩阵
# rpn confusion matrix(meter)
trainer.vis.text(
str(trainer.rpn_cm.value().tolist()), win='rpn_cm')
# roi confusion matrix
trainer.vis.text(
str(trainer.roi_cm.value().tolist()), win='roi_cm')
# trainer.vis.img('roi_cm', at.totensor(
# trainer.roi_cm.value(), False).float())
eval_result = eval(test_dataloader, faster_rcnn, test_num=opt.test_num)
trainer.vis.plot('test_map', eval_result['map'])
lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr']
log_info = 'lr:{},ap:{}, map:{},loss:{}'.format(str(lr_),
str(eval_result['ap']),
str(eval_result['map']),
str(trainer.get_meter_data()))
trainer.vis.log(log_info)
# 保存最好结果并记住路径
if eval_result['map'] > best_map:
best_map = eval_result['map']
best_path = trainer.save(best_map=best_map)
if epoch == 20:
trainer.save(best_map='20')
result = eval(test_all_dataloader,
trainer.faster_rcnn, test_num=5000)
print('20result={}'.format(str(result)))
# trainer.load(best_path)
# result=eval(test_all_dataloader,trainer.faster_rcnn,test_num=5000)
# print('bestmapresult={}'.format(str(result)))
break
# 每10轮加载前面最好权重，并且减少学习率
if epoch % 20 == 15:
trainer.load(best_path)
trainer.faster_rcnn.scale_lr(opt.lr_decay)
lr_ = lr_ * opt.lr_decay
def train(**kwargs):
opt._parse(kwargs)
dataset = Dataset(opt)
print('load data')
dataloader = data_.DataLoader(dataset, \
batch_size=1, \
shuffle=True, \
# pin_memory=True,
num_workers=opt.num_workers)
testset = TestDataset(opt)
test_dataloader = data_.DataLoader(testset,
batch_size=1,
num_workers=opt.test_num_workers,
shuffle=False, \
pin_memory=True
)
faster_rcnn = FasterRCNNVGG16()
print('model construct completed')
trainer = FasterRCNNTrainer(faster_rcnn).cuda()
if opt.load_path:
trainer.load(opt.load_path)
print('load pretrained model from %s' % opt.load_path)
trainer.vis.text(dataset.db.label_names, win='labels')
best_map = 0
for epoch in range(opt.epoch):
trainer.reset_meters()
for ii, (img, bbox_, label_, scale) in tqdm(enumerate(dataloader)):
scale = at.scalar(scale)
img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda()
img, bbox, label = Variable(img), Variable(bbox), Variable(label)
trainer.train_step(img, bbox, label, scale)
if (ii + 1) % opt.plot_every == 0:
if os.path.exists(opt.debug_file):
ipdb.set_trace()
# plot loss
trainer.vis.plot_many(trainer.get_meter_data())
# plot groud truth bboxes
ori_img_ = inverse_normalize(at.tonumpy(img[0]))
gt_img = visdom_bbox(ori_img_,
at.tonumpy(bbox_[0]),
at.tonumpy(label_[0]))
trainer.vis.img('gt_img', gt_img)
# plot predicti bboxes
_bboxes, _labels, _scores = trainer.faster_rcnn.predict([ori_img_], visualize=True)
pred_img = visdom_bbox(ori_img_,
at.tonumpy(_bboxes[0]),
at.tonumpy(_labels[0]).reshape(-1),
at.tonumpy(_scores[0]))
trainer.vis.img('pred_img', pred_img)
# rpn confusion matrix(meter)
trainer.vis.text(str(trainer.rpn_cm.value().tolist()), win='rpn_cm')
# roi confusion matrix
trainer.vis.img('roi_cm', at.totensor(trainer.roi_cm.conf, False).float())
eval_result = eval(test_dataloader, faster_rcnn, test_num=opt.test_num)
if eval_result['map'] > best_map:
best_map = eval_result['map']
best_path = trainer.save(best_map=best_map)
if epoch == 9:
trainer.load(best_path)
trainer.faster_rcnn.scale_lr(opt.lr_decay)
trainer.vis.plot('test_map', eval_result['map'])
lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr']
log_info = 'lr:{}, map:{},loss:{}'.format(str(lr_),
str(eval_result['map']),
str(trainer.get_meter_data()))
trainer.vis.log(log_info)
if epoch == 13:
break
def train(**kwargs):
opt._parse(kwargs)
#dataset = Polypcoco_anchorfree('/data2/dechunwang/dataset', split='train')
#print("dataset length: ", len(dataset))
dataset = Dataset(opt)
print('load data')
dataloader = data_.DataLoader(dataset, \
batch_size=1, \
shuffle=True, \
# pin_memory=True,
num_workers=opt.num_workers)
#print(dataloader)
# for i, sample_image in enumerate(dataloader):
# print("data loader output: ", sample_image)
testset = TestDataset(opt)
#testset = Polypcoco_anchorfree('/data2/dechunwang/dataset', split='test')
test_dataloader = data_.DataLoader(testset,
batch_size=1,
num_workers=opt.test_num_workers,
shuffle=False, \
pin_memory=True
)
#print("test dataloader", test_dataloader)
faster_rcnn = FasterRCNNVGG16()
print('model construct completed')
trainer = FasterRCNNTrainer(faster_rcnn).cuda()
if opt.load_path:
trainer.load(opt.load_path)
print('load pretrained model from %s' % opt.load_path)
#trainer.vis.text(dataset.db.label_names, win='labels')
best_map = 0
lr_ = opt.lr
for epoch in range(opt.epoch):
trainer.reset_meters()
for ii, (img, bbox_, label_, scale) in enumerate(dataloader):
#print("loader:", img.shape, bbox_.shape, label_.shape, scale.shape)
scale = at.scalar(scale)
# img = torch.FloatTensor(img).unsqueeze(0)
# bbox_ = torch.FloatTensor(bbox_)
# print("bbox_ shape: ", bbox_.shape)
# label_ = torch.FloatTensor(label_)
# print("*" * 100)
# print("bbox before tocuda: ", bbox_, bbox_.shape)
# print("*" * 100)
img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda()
# print("*" * 100)
# print("bbox before trainer.step: ", bbox, bbox.shape)
# print("*" * 100)
#print(img.shape)
trainer.train_step(img, bbox, label, scale)
if (ii + 1) % opt.plot_every == 0:
if os.path.exists(opt.debug_file):
ipdb.set_trace()
# plot loss
#trainer.vis.plot_many(trainer.get_meter_data())
# plot groud truth bboxes
ori_img_ = inverse_normalize(at.tonumpy(img[0]))
# gt_img = visdom_bbox(ori_img_,
# at.tonumpy(bbox_[0]),
# at.tonumpy(label_[0]))
#trainer.vis.img('gt_img', gt_img)
# plot predicti bboxes
_bboxes, _labels, _scores = trainer.faster_rcnn.predict(
[ori_img_], visualize=True)
# pred_img = visdom_bbox(ori_img_,
# at.tonumpy(_bboxes[0]),
# at.tonumpy(_labels[0]).reshape(-1),
# at.tonumpy(_scores[0]))
#trainer.vis.img('pred_img', pred_img)
# rpn confusion matrix(meter)
#trainer.vis.text(str(trainer.rpn_cm.value().tolist()), win='rpn_cm')
# roi confusion matrix
#trainer.vis.img('roi_cm', at.totensor(trainer.roi_cm.conf, False).float())
eval_result = eval(test_dataloader, faster_rcnn, test_num=len(testset))
print("result: ", eval_result)
#trainer.vis.plot('test_map', eval_result['map'])
lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr']
log_info = 'lr:{}, map:{},loss:{}'.format(
str(lr_), str(eval_result['map']), str(trainer.get_meter_data()))
#trainer.vis.log(log_info)
print("log info: ", log_info)
if eval_result['map'] > best_map:
best_map = eval_result['map']
best_path = trainer.save(best_map=best_map)
print("best: ", best_map)
if epoch == 9:
trainer.load(best_path)
trainer.faster_rcnn.scale_lr(opt.lr_decay)
lr_ = lr_ * opt.lr_decay
if epoch == 13:
break
# plt.figure(figsize=(8, 8))
# plt.imshow(imgs.transpose(1, 2, 0))
# if not isinstance(bboxes, np.ndarray) and not isinstance(bboxes, torch.Tensor):
# input_bboxes = np.array(input_bboxes)
# input_bboxes = bboxes.reshape(-1, 4)
# w = input_bboxes[:, 3] - input_bboxes[:, 1]
# h = input_bboxes[:, 2] - input_bboxes[:, 0]
# for i in range(input_bboxes.shape[0]):
# plt.gca().add_patch(Rectangle(input_bboxes[i][[1, 0]],w[i], h[i], fill=False,edgecolor='r'))
# plt.text(input_bboxes[i][1], input_bboxes[i][0], dv.VOC_BBOX_LABEL_NAMES[labels.reshape(-1, len(input_bboxes))[0][i]])
# plt.axis("off")
# plt.show()
# break
lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr']
logging.info(
f"[Batch: {epoch}] training loss: {np.mean(loss_history):.2f} lr: {lr_}"
)
if (epoch + 1) % 1 == 0:
eval_result = eval(test_dataloader, faster_rcnn, test_num=opt.test_num)
logging.info(f"[Batch: {epoch}] eval loss: {eval_result['map']:.4f}")
if eval_result['map'] > best_map:
best_map = eval_result['map']
if best_map > 0.68:
best_path = trainer.save(best_map=best_map)
if epoch == 9:
# pass
trainer.faster_rcnn.scale_lr(opt.lr_decay)
lr_ = lr_ * opt.lr_decay
def train(**kwargs):
opt._parse(kwargs)
# device_num = 6
data_root = "/home/lsm/TrainSet/"
train_file = "train.txt"
test_file = "test.txt"
trainset = MyDataset(data_root, train_file, opt)
testset = TestDataset(data_root, test_file, opt)
print('load data')
dataloader = data_.DataLoader(trainset, \
batch_size=1, \
shuffle=True, \
# pin_memory=True,
num_workers=opt.num_workers)
test_dataloader = data_.DataLoader(testset,
batch_size=1,
num_workers=opt.test_num_workers,
shuffle=False, \
pin_memory=True
)
faster_rcnn = FasterRCNNVGG16()
print('model construct completed')
trainer = FasterRCNNTrainer(faster_rcnn).cuda()
if opt.load_path:
trainer.load(opt.load_path)
print('load pretrained model from %s' % opt.load_path)
# trainer.vis.text(dataset.db.label_names, win='labels')
best_map = 0
lr_ = opt.lr
f = open('log.txt', 'w')
for epoch in range(opt.epoch):
trainer.reset_meters()
print("epoch " + str(epoch) + " ...")
for ii, (img, bbox_, label_, scale) in tqdm(enumerate(dataloader)):
# break
# for ii, (img, bbox_, label_, scale) in enumerate(dataloader):
# print(ii)
scale = at.scalar(scale)
img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda()
trainer.train_step(img, bbox, label, scale)
# if (ii + 1) % opt.plot_every == 0:
# if os.path.exists(opt.debug_file):
# ipdb.set_trace()
#
# # plot loss
# # trainer.vis.plot_many(trainer.get_meter_data())
#
# # plot groud truth bboxes
# ori_img_ = inverse_normalize(at.tonumpy(img[0]))
# # gt_img = visdom_bbox(ori_img_,
# # at.tonumpy(bbox_[0]),
# # at.tonumpy(label_[0]))
# # trainer.vis.img('gt_img', gt_img)
#
# # plot predicti bboxes
# _bboxes, _labels, _scores = trainer.faster_rcnn.predict([ori_img_], visualize=True)
eval_result = eval(test_dataloader, faster_rcnn, test_num=opt.test_num)
lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr']
log_info = 'lr:{}, map:{},loss:{}'.format(
str(lr_), str(eval_result['map']), str(trainer.get_meter_data()))
print(log_info)
# trainer.vis.log(log_info)
# print(str(lr_)+": loss = "+str(trainer.get_meter_data()))
f.write(log_info)
if eval_result['map'] > best_map:
best_map = eval_result['map']
best_path = trainer.save(best_map=best_map)
if epoch == 9:
trainer.load(best_path)
trainer.faster_rcnn.scale_lr(opt.lr_decay)
lr_ = lr_ * opt.lr_decay
if epoch == 19:
trainer.load(best_path)
trainer.faster_rcnn.scale_lr(opt.lr_decay)
lr_ = lr_ * opt.lr_decay
if epoch == 50:
break
f.close()
def train(**kwargs):
# 将调用函数时候附加的参数用，config.py的opt._parse()解析，获取存储路径，放入dataset
opt._parse(kwargs)
dataset = Dataset(opt)
print('load data')
# VOCBboxDataset作为数据读取库，读取图片，并调整和随机反转
dataloader = data_.DataLoader(dataset, \
batch_size=1, \
shuffle=True, \
# pin_memory=True,
num_workers=opt.num_workers)
testset = TestDataset(opt)
# 数据装载到dataloader中，shuffle=True允许数据打乱，num_workers设置分批处理
test_dataloader = data_.DataLoader(testset,
batch_size=1,
num_workers=opt.test_num_workers,
shuffle=False, \
pin_memory=True
)
faster_rcnn = FasterRCNNVGG16() # 定义模型
print('model construct completed')
# 将FasterRCNNVGG16作为fasterrcnn的模型送入到FasterRCNNTrainer中
# 并设置好GPU加速
trainer = FasterRCNNTrainer(faster_rcnn).cuda()
if opt.load_path: # 判断路径存在
trainer.load(opt.load_path) # 读取与训练模型
print('load pretrained model from %s' % opt.load_path)
trainer.vis.text(dataset.db.label_names, win='labels')
best_map = 0
lr_ = opt.lr
# 开始训练，迭代次数在config.py预先定义，超参
for epoch in range(opt.epoch):
print ("---------------", epoch, " in ", opt.epoch, "-------------")
trainer.reset_meters() # 可视化界面初始化数据
for ii, (img, bbox_, label_, scale) in tqdm(enumerate(dataloader)):
scale = at.scalar(scale)
# 从训练数据中枚举dataloader，设置缩放范围，设置gpu加速
img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda()
# 调用trainer.py中的函数trainer.train_step(img, bbox, label, scale) 进行一次参数优化过程
trainer.train_step(img, bbox, label, scale)
if (ii + 1) % opt.plot_every == 0:
# 判断数据读取次数是否能够整除plot_every，
# 如果达到判断debug_file是否存在，用ipdb工具设置断点，
if os.path.exists(opt.debug_file):
ipdb.set_trace()
# plot loss将训练数据读取并上传完成可视化
trainer.vis.plot_many(trainer.get_meter_data())
# 绘制Ground truth包围盒
ori_img_ = inverse_normalize(at.tonumpy(img[0]))
gt_img = visdom_bbox(ori_img_,
at.tonumpy(bbox_[0]),
at.tonumpy(label_[0]))
# 将每次迭代读取的图片用dataset文件里面的inverse_normalize()
# 函数进行预处理，将处理后的图片调用visdom_bbox
trainer.vis.img('ground_truth_img', gt_img)
# plot predict bboxes
# 显示原始图片和预测结果（边框+类别）
_bboxes, _labels, _scores = trainer.faster_rcnn.predict([ori_img_], visualize=True)
pred_img = visdom_bbox(ori_img_,
at.tonumpy(_bboxes[0]),
at.tonumpy(_labels[0]).reshape(-1),
at.tonumpy(_scores[0]))
trainer.vis.img('predict_img', pred_img)
# rpn confusion matrix(meter)
# 调用trainer.vis.text将rpn_cm也就是RPN网络的混淆矩阵在可视化工具中显示
trainer.vis.text(str(trainer.rpn_cm.value().tolist()), win='rpn_cm')
# roi confusion matrix
trainer.vis.img('roi_cm', at.totensor(trainer.roi_cm.conf, False).float())
eval_result = eval(test_dataloader, faster_rcnn, test_num=opt.test_num)
# 调用Trainer.vis.img将Roi_cm将roi的可视化矩阵以图片的形式显示
trainer.vis.plot('test_map', eval_result['map'])
# 设置学习率
lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr']
log_info = 'lr:{}, map:{},loss:{}'.format(str(lr_),
str(eval_result['map']),
str(trainer.get_meter_data()))
# 将损失学习率以及map等信息及时显示更新
trainer.vis.log(log_info)
# 保存效果最好的map
if eval_result['map'] > best_map:
best_map = eval_result['map']
best_path = trainer.save(best_map=best_map)
# if判断句如果学习的epoch达到了9就将学习率*0.1变成原来的十分之一
if epoch == 9:
trainer.load(best_path)
trainer.faster_rcnn.scale_lr(opt.lr_decay)
lr_ = lr_ * opt.lr_decay
if epoch == 13:
break # 结束训练过程
def train(**kwargs):
opt._parse(kwargs)
print('load data')
dataset = Dataset(opt)
dataloader = data_.DataLoader(dataset, \
batch_size=1, \
shuffle=True, \
# pin_memory=True,
num_workers=opt.num_workers)
testset = TestDataset(opt)
test_dataloader = data_.DataLoader(testset,
batch_size=1,
num_workers=opt.test_num_workers,
shuffle=False, \
pin_memory=True
)
faster_rcnn = FasterRCNNVGG16(n_fg_class=dataset.get_class_count(),
ratios=[1],
anchor_scales=[1])
print('model construct completed')
trainer = FasterRCNNTrainer(faster_rcnn,
n_fg_class=dataset.get_class_count())
if opt.use_cuda:
trainer = trainer.cuda()
if opt.load_path:
old_state = trainer.load(opt.load_path)
print('load pretrained model from %s' % opt.load_path)
if opt.validate_only:
num_eval_images = len(testset)
eval_result = eval(test_dataloader,
faster_rcnn,
trainer,
testset,
test_num=num_eval_images)
print('Evaluation finished, obtained {} using {} out of {} images'.
format(eval_result, num_eval_images, len(testset)))
return
if opt.load_path and 'epoch' in old_state.keys():
starting_epoch = old_state['epoch'] + 1
print('Model was trained until epoch {}, continuing with epoch {}'.
format(old_state['epoch'], starting_epoch))
else:
starting_epoch = 0
#trainer.vis.text(dataset.db.label_names, win='labels')
best_map = 0
lr_ = opt.lr
global_step = 0
for epoch in range(starting_epoch, opt.num_epochs):
lr_ = opt.lr * (opt.lr_decay**(epoch // opt.epoch_decay))
trainer.faster_rcnn.set_lr(lr_)
print('Starting epoch {} with learning rate {}'.format(epoch, lr_))
trainer.reset_meters()
for ii, (img, bbox_, label_, scale) in tqdm(enumerate(dataloader),
total=len(dataset)):
global_step = global_step + 1
scale = at.scalar(scale)
if opt.use_cuda:
img, bbox, label = img.cuda().float(), bbox_.float().cuda(
), label_.float().cuda()
else:
img, bbox, label = img.float(), bbox_.float(), label_.float()
img, bbox, label = Variable(img), Variable(bbox), Variable(label)
losses = trainer.train_step(img, bbox, label, scale)
if (ii + 1) % opt.plot_every == 0:
if os.path.exists(opt.debug_file):
ipdb.set_trace()
# plot loss
#trainer.vis.plot_many(trainer.get_meter_data())
"""
# plot groud truth bboxes
ori_img_ = inverse_normalize(at.tonumpy(img[0]))
gt_img = visdom_bbox(ori_img_,
at.tonumpy(bbox_[0]),
at.tonumpy(label_[0]),
label_names=dataset.get_class_names()+['BG'])
trainer.vis.img('gt_img', gt_img)
# plot predicti bboxes
_bboxes, _labels, _scores = trainer.faster_rcnn.predict([ori_img_], visualize=True)
pred_img = visdom_bbox(ori_img_,
at.tonumpy(_bboxes[0]),
at.tonumpy(_labels[0]).reshape(-1),
at.tonumpy(_scores[0]),
label_names=dataset.get_class_names()+['BG'])
trainer.vis.img('pred_img', pred_img)
"""
# rpn confusion matrix(meter)
#trainer.vis.text(str(trainer.rpn_cm.value().tolist()), win='rpn_cm')
# roi confusion matrix
#trainer.vis.img('roi_cm', at.totensor(trainer.roi_cm.conf, False).float())
#print('Current total loss {}'.format(losses[-1].tolist()))
trainer.vis.plot('train_total_loss', losses[-1].tolist())
if (global_step) % opt.snapshot_every == 0:
snapshot_path = trainer.save(epoch=epoch)
print("Snapshotted to {}".format(snapshot_path))
#snapshot_path = trainer.save(epoch=epoch)
#print("After epoch {}: snapshotted to {}".format(epoch,snapshot_path))
for lo in losses:
del lo
del img, bbox_, label_, scale
torch.cuda.empty_cache()
eval_result = eval(test_dataloader,
faster_rcnn,
trainer,
testset,
test_num=min(opt.test_num, len(testset)))
print(eval_result)
# TODO: this definitely is not good and will bias evaluation
if eval_result['map'] > best_map:
best_map = eval_result['map']
best_path = trainer.save(best_map=eval_result['map'], epoch=epoch)
print("After epoch {}: snapshotted to {}".format(epoch, best_path))
trainer.vis.plot('test_map', eval_result['map'])
del eval_result
torch.cuda.empty_cache()
def train(**kwargs):
opt._parse(kwargs)
faster_rcnn = FasterRCNNVGG16()
print('model construct completed')
trainer = FasterRCNNTrainer(faster_rcnn).cuda()
if opt.is_distilltion == False:
iteration_number = 10
path = opt.voc_data_dir + '/ImageSets/Main/trainval.txt'
datatxt = 0
f = open(path, "r")
for i in range(5000):
if i % 500 == 0:
datatxt = datatxt + 1
f2 = open(
opt.voc_data_dir + '/ImageSets/Main/' + str(datatxt) +
'.txt', "w")
f2.write(f.readline())
else:
iteration_number = 1
if opt.load_path:
trainer.load(opt.load_path)
print('load pretrained model from %s' % opt.load_path)
for jj in range(iteration_number):
t.cuda.empty_cache()
if jj > 0:
opt.datatxt = str(int(opt.datatxt) + 1)
opt.load_path = best_path
# 样本挖掘
print(opt.datatxt)
if opt.is_example_mining == True and opt.load_path != None:
if opt.example_type == 'mAP':
example_mining_map(trainer, opt.datatxt)
elif opt.example_type == 'loss':
example_mining_loss(opt.datatxt)
elif opt.example_type == 'diversity':
example_mining_diversity(trainer, opt.datatxt)
elif opt.example_type == 'mAP_diversity':
example_mining_map_diversity(trainer, opt.datatxt)
else:
example_mining_map_loss(trainer, opt.datatxt)
print('example mining completed')
print('load data')
dataset = Dataset(opt)
dataloader = data_.DataLoader(
dataset,
batch_size=1,
shuffle=True,
# pin_memory=True,
num_workers=opt.num_workers)
testset = TestDataset(opt)
test_dataloader = data_.DataLoader(testset,
batch_size=1,
num_workers=opt.test_num_workers,
shuffle=False,
pin_memory=True)
testset_all = TestDataset(opt, 'test')
test_all_dataloader = data_.DataLoader(
testset_all,
batch_size=1,
num_workers=opt.test_num_workers,
shuffle=False,
pin_memory=True)
# visdom 显示所有类别标签名
trainer.vis.text(dataset.db.label_names, win='labels')
best_map = 0
lr_ = opt.lr
# print(lr_)
t.cuda.empty_cache()
for epoch in range(opt.epoch):
t.cuda.empty_cache()
print('epoch=%d' % epoch)
if opt.example_type != 'mAP':
# 计算loss的数组初始化
loss = np.zeros(10000)
ID = list()
# 重置混淆矩阵
trainer.reset_meters()
# tqdm可以在长循环中添加一个进度提示信息，用户只需要封装任意的迭代器 tqdm(iterator)，
# 是一个快速、扩展性强
for ii, (img, sizes, bbox_, label_, scale,
id_) in enumerate(dataloader):
if len(bbox_) == 0:
continue
t.cuda.empty_cache()
scale = at.scalar(scale)
img, bbox, label = img.cuda().float(), bbox_.cuda(
), label_.cuda()
# 训练的就这一步 下面的都是打印的信息
# 转化成pytorch能够计算的格式，转tensor格式
if opt.is_distilltion == True:
# inx = str(id_[0])
# inx = int(inx[-5:])
# teacher_pred_bboxes = pred_bboxes[int(index[inx])]
# teacher_pred_labels = pred_labels[int(index[inx])]
# teacher_pred_features_ = pred_features[int(index[inx])]
teacher_pred_labels = np.load('label/' + str(id_[0]) +
'.npy')
teacher_pred_bboxes = np.load('bbox/' + str(id_[0]) +
'.npy')
teacher_pred_features_ = np.load('feature/' + str(id_[0]) +
'.npy')
teacher_pred_bboxes = teacher_pred_bboxes.astype(
np.float32)
teacher_pred_labels = teacher_pred_labels.astype(np.int32)
teacher_pred_bboxes_ = at.totensor(teacher_pred_bboxes)
teacher_pred_labels_ = at.totensor(teacher_pred_labels)
teacher_pred_bboxes_ = teacher_pred_bboxes_.cuda()
teacher_pred_labels_ = teacher_pred_labels_.cuda()
teacher_pred_features_ = teacher_pred_features_.cuda()
losses = trainer.train_step(img, bbox, label, scale, epoch,
teacher_pred_bboxes_,
teacher_pred_labels_,
teacher_pred_features_)
else:
losses = trainer.train_step(img, bbox, label, scale, epoch)
# 保存每一个样本的损失
if opt.example_type != 'mAP':
ID += list(id_)
loss[ii] = losses.total_loss
# visdom显示的信息
if (ii + 1) % opt.plot_every == 0:
if os.path.exists(opt.debug_file):
ipdb.set_trace()
# plot loss
trainer.vis.plot_many(trainer.get_meter_data())
# plot groud truth bboxes
ori_img_ = inverse_normalize(at.tonumpy(img[0]))
gt_img = visdom_bbox(ori_img_, at.tonumpy(bbox_[0]),
at.tonumpy(label_[0]))
trainer.vis.img('gt_img', gt_img)
# plot predicti bboxes
_bboxes, _labels, _scores, _ = trainer.faster_rcnn.predict(
[ori_img_], visualize=True)
print(at.tonumpy(_bboxes[0]).reshape(-1).shape)
print(at.tonumpy(_labels[0]).shape)
pred_img = visdom_bbox(ori_img_, at.tonumpy(_bboxes[0]),
at.tonumpy(_labels[0]).reshape(-1),
at.tonumpy(_scores[0]))
trainer.vis.img('pred_img', pred_img)
# 混淆矩阵
# rpn confusion matrix(meter)
trainer.vis.text(str(trainer.rpn_cm.value().tolist()),
win='rpn_cm')
# roi confusion matrix
trainer.vis.text(str(trainer.roi_cm.value().tolist()),
win='roi_cm')
# trainer.vis.img('roi_cm', at.totensor(
# trainer.roi_cm.value(), False).float())
eval_result = eval(test_dataloader,
faster_rcnn,
test_num=opt.test_num)
trainer.vis.plot('test_map', eval_result['map'])
lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr']
log_info = 'lr:{},ap:{}, map:{},loss:{}'.format(
str(lr_), str(eval_result['ap']), str(eval_result['map']),
str(trainer.get_meter_data()))
trainer.vis.log(log_info)
# 保存最好结果并记住路径
if eval_result['map'] > best_map:
best_map = eval_result['map']
best_path = trainer.save(best_map=best_map)
if opt.example_type != 'mAP':
order = loss.argsort()[::-1]
f = open('loss.txt', "w")
for i in range(len(ID)):
f.write(ID[order[i]] + ' ' + str(loss[order[i]]) +
'\n')
f.close()
if epoch == 20:
#draw(test_dataloader, faster_rcnn, test_num=opt.test_num)
save_name = trainer.save(best_map='20')
f = open('result.txt', "a")
result = eval(test_all_dataloader,
trainer.faster_rcnn,
test_num=5000)
f.write(opt.datatxt + '\n')
f.write(save_name + '\n')
f.write(result + '\n')
f.close
print(result)
trainer.faster_rcnn.scale_lr(10)
lr_ = lr_ * 10
break
# 每10轮加载前面最好权重，并且减少学习率
if epoch % 20 == 15:
trainer.save(best_map='15')
trainer.load(best_path)
trainer.faster_rcnn.scale_lr(opt.lr_decay)
lr_ = lr_ * opt.lr_decay
def train(**kwargs): # *变量名, 表示任何多个无名参数, 它是一个tuple；**变量名, 表示关键字参数, 它是一个dict
opt._parse(kwargs) # 识别参数,传递过来的是一个字典,用parse来解析
dataset = Dataset(opt) # 作者自定义的Dataset类
print('读取数据中...')
# Dataloader 定义了一次获取批次数据的方法
dataloader = data_.DataLoader(dataset, \
batch_size=1, \
shuffle=True, \
# pin_memory=True,
num_workers=opt.num_workers) # PyTorch自带的DataLoader类,生成一个多线程迭代器来迭代dataset, 以供读取一个batch的数据
testset = TestDataset(opt, split='trainval')
# 测试集loader
test_dataloader = data_.DataLoader(testset,
batch_size=1,
num_workers=opt.test_num_workers,
shuffle=False, \
pin_memory=True
)
faster_rcnn = FasterRCNNVGG16() # 网络定义
print('模型构建完毕!')
trainer = FasterRCNNTrainer(
faster_rcnn).cuda() # 定义一个训练器,返回loss, .cuda()表示把返回的Tensor存入GPU
if opt.load_path: # 如果要加载预训练模型
trainer.load(opt.load_path)
print('已加载预训练参数 %s' % opt.load_path)
else:
print("未引入预训练参数, 随机初始化网络参数")
trainer.vis.text(dataset.db.label_names, win='labels') # 显示labels标题
best_map = 0 # 定义一个best_map
for epoch in range(opt.epoch): # 对于每一个epoch
trainer.reset_meters() # 重置测各种测量仪
# 对每一个数据
for ii, (img, bbox_, label_, scale) in tqdm(enumerate(dataloader)):
scale = at.scalar(scale) # 转化为标量
img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda(
) # 存入GPU
img, bbox, label = Variable(img), Variable(bbox), Variable(
label) # 转换成变量以供自动微分器使用
# TODO
trainer.train_step(img, bbox, label, scale) # 训练一步
if (ii + 1) % opt.plot_every == 0: # 如果到达"每多少次显示"
if os.path.exists(opt.debug_file):
ipdb.set_trace()
# plot loss
trainer.vis.plot_many(trainer.get_meter_data())
# plot groud truth bboxes
ori_img_ = inverse_normalize(at.tonumpy(img[0]))
gt_img = visdom_bbox(ori_img_, at.tonumpy(bbox_[0]),
at.tonumpy(label_[0]))
trainer.vis.img('gt_img', gt_img)
# plot predicti bboxes
_bboxes, _labels, _scores = trainer.faster_rcnn.predict(
[ori_img_], visualize=True)
pred_img = visdom_bbox(ori_img_, at.tonumpy(_bboxes[0]),
at.tonumpy(_labels[0]).reshape(-1),
at.tonumpy(_scores[0]))
trainer.vis.img('pred_img', pred_img)
# rpn confusion matrix(meter)
trainer.vis.text(str(trainer.rpn_cm.value().tolist()),
win='rpn_cm')
# roi confusion matrix
trainer.vis.img(
'roi_cm',
at.totensor(trainer.roi_cm.conf, False).float())
# 使用测试数据集来评价模型(此步里面包含预测信息)
eval_result = eval(test_dataloader, faster_rcnn, test_num=opt.test_num)
if eval_result['map'] > best_map:
best_map = eval_result['map']
best_path = trainer.save(
best_map=best_map) # 好到一定程度就存储模型, 存储在checkpoint文件夹内
if epoch == 9: # 到第9轮的时候读取模型, 并调整学习率
trainer.load(best_path)
trainer.faster_rcnn.scale_lr(opt.lr_decay)
trainer.vis.plot('test_map', eval_result['map'])
lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr']
log_info = 'lr:{}, map:{},loss:{}'.format(
str(lr_), str(eval_result['map']), str(trainer.get_meter_data()))
trainer.vis.log(log_info)
# if epoch == 13: # 到第14轮的时候停止训练
# break
trainer.save(best_map=best_map)
def train(**kwargs):
# opt._parse(kwargs)#将调用函数时候附加的参数用，
# config.py文件里面的opt._parse()进行解释，然后
# 获取其数据存储的路径，之后放到Dataset里面！
opt._parse(kwargs)
dataset = Dataset(opt)
print('load data')
# #Dataset完成的任务见第二次推文数据预处理部分，
# 这里简单解释一下，就是用VOCBboxDataset作为数据
# 集，然后依次从样例数据库中读取图片出来，还调用了
# Transform(object)函数，完成图像的调整和随机翻转工作
dataloader = data_.DataLoader(dataset, \
batch_size=1, \
shuffle=True, \
# pin_memory=True,
num_workers=opt.num_workers)
testset = TestDataset(opt)
# 将数据装载到dataloader中，shuffle=True允许数据打乱排序，
# num_workers是设置数据分为几批处理，同样的将测试数据集也
# 进行同样的处理，然后装载到test_dataloader中
test_dataloader = data_.DataLoader(testset,
batch_size=1,
num_workers=opt.test_num_workers,
shuffle=False, \
pin_memory=True
)
# 定义faster_rcnn=FasterRCNNVGG16()训练模型
faster_rcnn = FasterRCNNVGG16()
print('model construct completed')
# 设置trainer = FasterRCNNTrainer(faster_rcnn).cuda()将
# FasterRCNNVGG16作为fasterrcnn的模型送入到FasterRCNNTrainer
# 中并设置好GPU加速
trainer = FasterRCNNTrainer(faster_rcnn).cuda()
if opt.load_path:
trainer.load(opt.load_path)
print('load pretrained model from %s' % opt.load_path)
trainer.vis.text(dataset.db.label_names, win='labels')
best_map = 0
lr_ = opt.lr
# 用一个for循环开始训练过程，而训练迭代的次数
# opt.epoch=14也在config.py文件中预先定义好，属于超参数
for epoch in range(opt.epoch):
# 首先在可视化界面重设所有数据
trainer.reset_meters()
for ii, (img, bbox_, label_, scale) in tqdm(enumerate(dataloader)):
scale = at.scalar(scale)
# 然后从训练数据中枚举dataloader,设置好缩放范围，
# 将img,bbox,label,scale全部设置为可gpu加速
img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda()
# 调用trainer.py中的函数trainer.train_step
# (img,bbox,label,scale)进行一次参数迭代优化过程
trainer.train_step(img, bbox, label, scale)
# 判断数据读取次数是否能够整除plot_every
# (是否达到了画图次数)，如果达到判断debug_file是否存在，
# 用ipdb工具设置断点，调用trainer中的trainer.vis.
# plot_many(trainer.get_meter_data())将训练数据读取并
# 上传完成可视化
if (ii + 1) % opt.plot_every == 0:
if os.path.exists(opt.debug_file):
ipdb.set_trace()
# plot loss
trainer.vis.plot_many(trainer.get_meter_data())
# plot groud truth bboxes
ori_img_ = inverse_normalize(at.tonumpy(img[0]))
gt_img = visdom_bbox(ori_img_,
at.tonumpy(bbox_[0]),
at.tonumpy(label_[0]))
# 将每次迭代读取的图片用dataset文件里面的inverse_normalize()
# 函数进行预处理，将处理后的图片调用Visdom_bbox可视化
trainer.vis.img('gt_img', gt_img)
# plot predicti bboxes
# 调用faster_rcnn的predict函数进行预测，
# 预测的结果保留在以_下划线开头的对象里面
_bboxes, _labels, _scores = trainer.faster_rcnn.predict([ori_img_], visualize=True)
pred_img = visdom_bbox(ori_img_,
at.tonumpy(_bboxes[0]),
at.tonumpy(_labels[0]).reshape(-1),
at.tonumpy(_scores[0]))
# 利用同样的方法将原始图片以及边框类别的
# 预测结果同样在可视化工具中显示出来
trainer.vis.img('pred_img', pred_img)
# rpn confusion matrix(meter)
# 调用trainer.vis.text将rpn_cm也就是
# RPN网络的混淆矩阵在可视化工具中显示出来
trainer.vis.text(str(trainer.rpn_cm.value().tolist()), win='rpn_cm')
# roi confusion matrix
# 可视化ROI head的混淆矩阵
trainer.vis.img('roi_cm', at.totensor(trainer.roi_cm.conf, False).float())
# 调用eval函数计算map等指标
eval_result = eval(test_dataloader, faster_rcnn, test_num=opt.test_num)
# 可视化map
trainer.vis.plot('test_map', eval_result['map'])
# 设置学习的learning rate
lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr']
log_info = 'lr:{}, map:{},loss:{}'.format(str(lr_),
str(eval_result['map']),
str(trainer.get_meter_data()))
# 将损失学习率以及map等信息及时显示更新
trainer.vis.log(log_info)
# 用if判断语句永远保存效果最好的map
if eval_result['map'] > best_map:
best_map = eval_result['map']
best_path = trainer.save(best_map=best_map)
if epoch == 9:
# if判断语句如果学习的epoch达到了9就将学习率*0.1
# 变成原来的十分之一
trainer.load(best_path)
trainer.faster_rcnn.scale_lr(opt.lr_decay)
lr_ = lr_ * opt.lr_decay
# 判断epoch==13结束训练验证过程
if epoch == 13:
break
def train_val():
print('load data')
train_loader, val_loader = get_train_val_loader(
opt.root_dir,
batch_size=opt.batch_size,
val_ratio=0.1,
shuffle=opt.shuffle,
num_workers=opt.num_workers,
pin_memory=opt.pin_memory)
faster_rcnn = FasterRCNNVGG16()
# faster_rcnn = FasterRCNNResNet50()
print('model construct completed')
trainer = FasterRCNNTrainer(faster_rcnn).cuda()
# if opt.load_path:
# trainer.load(opt.load_path)
# print('load pretrained model from %s' % opt.load_path)
# trainer.vis.text(dataset.db.label_names, win='labels')
best_map = 0
lr_ = opt.lr
for epoch in range(opt.epoch):
trainer.reset_meters()
tqdm.monitor_interval = 0
for ii, sample in tqdm(enumerate(train_loader)):
if len(sample.keys()) == 5:
img_id, img, bbox, scale, label = sample['img_id'], sample['image'], sample['bbox'], sample['scale'], \
sample['label']
img, bbox, label = img.cuda().float(), bbox.cuda(), label.cuda(
)
img, bbox, label = Variable(img), Variable(bbox), Variable(
label)
else:
img_id, img, bbox, scale, label = sample['img_id'], sample['image'], np.zeros((1, 0, 4)), \
sample['scale'], np.zeros((1, 0, 1))
img = img.cuda().float()
img = Variable(img)
if bbox.size == 0:
continue
scale = at.scalar(scale)
trainer.train_step(img_id, img, bbox, label, scale)
if (ii + 1) % opt.plot_every == 0:
# plot loss
trainer.vis.plot_many(trainer.get_meter_data())
# plot ground truth bboxes
ori_img_ = inverse_normalize(at.tonumpy(img[0]))
gt_img = visdom_bbox(ori_img_, img_id[0], at.tonumpy(bbox[0]),
at.tonumpy(label[0]))
trainer.vis.img('gt_img', gt_img)
# plot predicted bboxes
_bboxes, _labels, _scores = trainer.faster_rcnn.predict(
[ori_img_], visualize=True)
pred_img = visdom_bbox(ori_img_, img_id[0],
at.tonumpy(_bboxes[0]),
at.tonumpy(_labels[0]).reshape(-1),
at.tonumpy(_scores[0]))
trainer.vis.img('pred_img', pred_img)
# rpn confusion matrix(meter)
trainer.vis.text(str(trainer.rpn_cm.value().tolist()),
win='rpn_cm')
# roi confusion matrix
trainer.vis.img(
'roi_cm',
at.totensor(trainer.roi_cm.conf, False).float())
mAP = eval_mAP(trainer, val_loader)
trainer.vis.plot('val_mAP', mAP)
lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr']
log_info = 'lr:{}, map:{},loss:{}'.format(
str(lr_), str(mAP), str(trainer.get_meter_data()))
trainer.vis.log(log_info)
if mAP > best_map:
best_map = mAP
best_path = trainer.save(best_map=best_map)
if epoch == opt.epoch - 1:
best_path = trainer.save()
if (epoch + 1) % 10 == 0:
trainer.load(best_path)
trainer.faster_rcnn.scale_lr(opt.lr_decay)
lr_ = lr_ * opt.lr_decay
def train(**kwargs):
opt.parse(kwargs)
print('loading data...')
trainset = TrainDataset(opt)
train_dataloader = torch.utils.data.DataLoader(trainset,
batch_size=1,
shuffle=True,
num_workers=opt.num_workers)
testset = TestDataset(opt)
test_dataloader = torch.utils.data.DataLoader(
testset,
batch_size=1,
num_workers=opt.test_num_workers,
shuffle=False,
pin_memory=True)
print('constructing model...')
if opt.model == 'vgg16':
faster_rcnn = FasterRCNNVGG16()
elif opt.model == 'resnet101':
faster_rcnn = FasterRCNNResNet101()
trainer = FasterRCNNTrainer(faster_rcnn).cuda()
print('loading model...')
if opt.load_path:
trainer.load(opt.load_path)
print('load pretrained model from %s' % opt.load_path)
else:
print('no pretrained model found')
trainer.vis.text('<br/>'.join(trainset.db.label_names), win='labels')
print('start training...')
best_map = 0.0
lr_ = opt.lr
for epoch in range(opt.epoch):
print("epoch : %d training ..." % epoch)
trainer.reset_meters()
for ii, (imgs_, bboxes_, labels_,
scales_) in tqdm(enumerate(train_dataloader)):
scales = at.scalar(scales_)
imgs, bboxes, labels = imgs_.cuda().float(), bboxes_.cuda(
), labels_.cuda()
trainer.train_step(imgs, bboxes, labels, scales)
if (ii + 1) % opt.plot_every == 0:
# plot loss
trainer.vis.plot_many(trainer.losses_data())
# generate plotted image
img = inverse_normalize(at.tonumpy(imgs_[0]))
# plot groud truth bboxes
bbox = at.tonumpy(bboxes_[0])
label = at.tonumpy(labels_[0])
img_gt = visdom_bbox(img, bbox, label)
trainer.vis.img('ground truth', img_gt)
bboxes__, labels__, scores__ = trainer.faster_rcnn.predict(
[img], visualize=True)
# plot prediction bboxes
bbox = at.tonumpy(bboxes__[0])
label = at.tonumpy(labels__[0]).reshape(-1)
score = at.tonumpy(scores__[0])
img_pred = visdom_bbox(img, bbox, label, score)
trainer.vis.img('prediction', img_pred)
# rpn confusion matrix(meter)
trainer.vis.text(str(trainer.rpn_cm.value().tolist()),
win='rpn_cm')
# roi confusion matrix
trainer.vis.img(
'roi_cm',
at.totensor(trainer.roi_cm.conf, False).float())
if ii + 1 == opt.train_num:
break
print("epoch : %d evaluating ..." % epoch)
eval_result = eval(test_dataloader, faster_rcnn, test_num=opt.test_num)
trainer.vis.plot('test_map', eval_result['map'])
lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr']
log_info = vis_dict(
{
'epoch': '%s/%s' % (str(epoch), str(opt.epoch)),
'lr': lr_,
'map': float(eval_result['map']),
}, trainer.losses_data())
trainer.vis.log(log_info)
if eval_result['map'] > best_map:
best_map = eval_result['map']
best_path = trainer.save(best_map="%.4f" % best_map)
if epoch == 9:
trainer.load(best_path)
trainer.faster_rcnn.scale_lr(opt.lr_decay)
lr_ = lr_ * opt.lr_decay
def train(**kwargs):
opt._parse(kwargs)
log_dir = os.path.join("logs", "faster_rcnn_train_onGray")
os.makedirs(log_dir, exist_ok=True)
log_path = os.path.join(
log_dir, time.strftime("%Y-%m-%d-%H%M.log", time.localtime(time.time()))
)
logging.basicConfig(
level=logging.INFO,
format="%(asctime)s - %(levelname)s - %(message)s",
handlers=[logging.FileHandler(log_path), logging.StreamHandler()],
)
logger = logging.getLogger()
dataset = Dataset(opt)
print("load data")
dataloader = data_.DataLoader(
dataset,
batch_size=1,
shuffle=True, # pin_memory=True,
num_workers=opt.num_workers,
)
testset = TestDataset(opt)
test_dataloader = data_.DataLoader(
testset,
batch_size=1,
num_workers=opt.test_num_workers,
shuffle=False,
pin_memory=True,
)
faster_rcnn = FasterRCNNVGG16()
print("model construct completed")
logger.info(faster_rcnn)
logger.info("-" * 50)
trainer = FasterRCNNTrainer(faster_rcnn, logger).cuda()
if opt.load_path:
trainer.load(opt.load_path)
print("load pretrained model from %s" % opt.load_path)
trainer.vis.text(dataset.db.label_names, win="labels")
best_map = 0
lr_ = opt.lr
for epoch in range(opt.epoch):
trainer.reset_meters()
trainer.reset_ave()
for ii, (img, bbox_, label_, scale) in enumerate(dataloader):
scale = at.scalar(scale)
img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda()
if (ii + 1) % opt.print_freq == 0:
logger.info(
"[Train] Epoch:{} [{:03d}/{:03d}]({:.0f}%)\t".format(
epoch, ii + 1, len(dataloader), (ii + 1) / len(dataloader) * 100
)
)
trainer.train_step(
img, bbox, label, scale, print_epoch=epoch, print_info=True
)
else:
trainer.train_step(
img, bbox, label, scale, print_epoch=epoch, print_info=False
)
# if (ii + 1) % opt.plot_every == 0:
# if os.path.exists(opt.debug_file):
# ipdb.set_trace()
#
# # plot loss
# trainer.vis.plot_many(trainer.get_meter_data())
#
# # plot groud truth bboxes
# ori_img_ = inverse_normalize(at.tonumpy(img[0]))
# gt_img = visdom_bbox(
# ori_img_, at.tonumpy(bbox_[0]), at.tonumpy(label_[0])
# )
# trainer.vis.img("gt_img", gt_img)
# if (ii + 1) % opt.plot_every == 0:
# if os.path.exists(opt.debug_file):
# ipdb.set_trace()
#
# # plot loss
# trainer.vis.plot_many(trainer.get_meter_data())
#
# # plot groud truth bboxes
# ori_img_ = inverse_normalize(at.tonumpy(img[0]))
# gt_img = visdom_bbox(
# ori_img_, at.tonumpy(bbox_[0]), at.tonumpy(label_[0])
# )
# trainer.vis.img("gt_img", gt_img)
#
# # plot predicti bboxes
# _bboxes, _labels, _scores = trainer.faster_rcnn.predict(
# [ori_img_], visualize=True
# )
# pred_img = visdom_bbox(
# ori_img_,
# at.tonumpy(_bboxes[0]),
# at.tonumpy(_labels[0]).reshape(-1),
# at.tonumpy(_scores[0]),
# )
# trainer.vis.img("pred_img", pred_img)
#
# # rpn confusion matrix(meter)
# trainer.vis.text(str(trainer.rpn_cm.value().tolist()), win="rpn_cm")
# # roi confusion matrix
# trainer.vis.img(
# "roi_cm", at.totensor(trainer.roi_cm.conf, False).float()
# )
eval_result = eval(test_dataloader, faster_rcnn, test_num=opt.test_num)
# trainer.vis.plot("test_map", eval_result["map"])
lr_ = trainer.faster_rcnn.optimizer.param_groups[0]["lr"]
log_info = "lr:{}, map:{},loss:{}".format(
str(lr_), str(eval_result["map"]), str(trainer.get_meter_data())
)
logger.info(log_info)
# trainer.vis.log(log_info)
if eval_result["map"] > best_map:
best_map = eval_result["map"]
best_path = trainer.save(
best_map=best_map,
save_path="checkpoints/trainedOnGray/fasterrcnn_%s"
% time.strftime("%m%d%H%M"),
)
if epoch == 9:
trainer.load(best_path)
trainer.faster_rcnn.scale_lr(opt.lr_decay)
lr_ = lr_ * opt.lr_decay
def train(**kwargs):
"""
训练
"""
#解析命令行参数，设置配置文件参数
opt._parse(kwargs)
#初始化Dataset参数
dataset = Dataset(opt)
print('load data')
#data_ 数据加载器（被重命名，pytorch方法）
dataloader = data_.DataLoader(dataset, \
batch_size=1, \
shuffle=True, \
# pin_memory=True,
num_workers=opt.num_workers)
#初始化TestDataset参数
testset = TestDataset(opt)
test_dataloader = data_.DataLoader(testset,
batch_size=1,
num_workers=opt.test_num_workers,
shuffle=False, \
pin_memory=True
)
#新建一个FasterRCNNVGG16
faster_rcnn = FasterRCNNVGG16()
print('model construct completed')
#新建一个trainer，并将网络模型转移到GPU上
#将FasterRCNNVGG16模型传入
trainer = FasterRCNNTrainer(faster_rcnn).cuda()
#如果存在，加载训练好的模型
if opt.load_path:
trainer.load(opt.load_path)
print('load pretrained model from %s' % opt.load_path)
#可视化类别 vis为visdom加载器
trainer.vis.text(dataset.db.label_names, win='labels')
#best_map存放的是 最优的mAP的网络参数
best_map = 0
lr_ = opt.lr
for epoch in range(opt.epoch):
#trainer方法 将平均精度的元组 和 混淆矩阵的值置0
trainer.reset_meters()
for ii, (img, bbox_, label_, scale) in tqdm(enumerate(dataloader)):
#调整数据的形状 scale：缩放倍数（输入图片尺寸 比上 输出数据的尺寸）
#1.6左右 供模型训练之前将模型规范化
scale = at.scalar(scale)
#将数据集转入到GPU上
#img 1x3x800x600 一张图片 三通道 大小800x600（不确定）
#bbox 1x1x4
#label 1x1
img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda()
#将数据转为V 变量，以便进行自动反向传播
img, bbox, label = Variable(img), Variable(bbox), Variable(label)
#训练并更新可学习参数（重点*****） 前向+反向，返回losses
trainer.train_step(img, bbox, label, scale)
#进行多个数据的可视化
if (ii + 1) % opt.plot_every == 0:
#进入调试模式
if os.path.exists(opt.debug_file):
ipdb.set_trace()
# plot loss 画五个损失
trainer.vis.plot_many(trainer.get_meter_data())
# plot groud truth bboxes img[0]，是压缩0位，形状变为[3x800x600]
#反向归一化，将img反向还原为原始图像，以便用于显示
ori_img_ = inverse_normalize(at.tonumpy(img[0]))
#通过原始图像，真实bbox，真实类别 进行显示
gt_img = visdom_bbox(ori_img_,
at.tonumpy(bbox_[0]),
at.tonumpy(label_[0]))
trainer.vis.img('gt_img', gt_img)
# plot predicti bboxes
#对原图进行预测，得到预测的bbox label scores
_bboxes, _labels, _scores = trainer.faster_rcnn.predict([ori_img_], visualize=True)
#通过原始图像、预测的bbox，预测的类别 以及概率 进行显示
pred_img = visdom_bbox(ori_img_,
at.tonumpy(_bboxes[0]),
at.tonumpy(_labels[0]).reshape(-1),
at.tonumpy(_scores[0]))
trainer.vis.img('pred_img', pred_img)
# rpn confusion matrix(meter)
#rpn混淆矩阵
trainer.vis.text(str(trainer.rpn_cm.value().tolist()), win='rpn_cm')
# roi confusion matrix
#roi混淆矩阵
trainer.vis.img('roi_cm', at.totensor(trainer.roi_cm.conf, False).float())
#使用验证集对当前的网络进行验证，返回一个字典，key值有AP,mAP
eval_result = eval(test_dataloader, faster_rcnn, test_num=opt.test_num)
#如果当前的map值优于best_map，则将当前值赋给best_map。将当前模型保留
if eval_result['map'] > best_map:
best_map = eval_result['map']
best_path = trainer.save(best_map=best_map)
#如果epoch到达9时，加载 当前的最优模型，并将学习率按lr_decay衰减调低
if epoch == 9:
trainer.load(best_path)
trainer.faster_rcnn.scale_lr(opt.lr_decay)
lr_ = lr_ * opt.lr_decay
#可视化验证集的test_map 和log信息
trainer.vis.plot('test_map', eval_result['map'])
log_info = 'lr:{}, map:{},loss:{}'.format(str(lr_),
str(eval_result['map']),
str(trainer.get_meter_data()))
trainer.vis.log(log_info)
if epoch == 13:
break
def train(**kwargs):
opt._parse(kwargs)
dataset = Dataset(opt)
print('load data')
dataloader = data_.DataLoader(dataset, \
batch_size=1, \
shuffle=True, \
# pin_memory=True,
num_workers=opt.num_workers)
testset = TestDataset(opt)
test_dataloader = data_.DataLoader(testset,
batch_size=1,
num_workers=opt.test_num_workers,
shuffle=False, \
pin_memory=True
)
faster_rcnn = FasterRCNNVGG16()
print('model construct completed')
trainer = FasterRCNNTrainer(faster_rcnn).cuda()
if opt.load_path:
trainer.load(opt.load_path)
print('load pretrained model from %s' % opt.load_path)
trainer.vis.text(dataset.db.label_names, win='labels')
best_map = 0
lr_ = opt.lr
for epoch in range(opt.epoch):
trainer.reset_meters()
for ii, (img, bbox_, label_, scale) in tqdm(enumerate(dataloader)):
scale = at.scalar(scale)
img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda()
trainer.train_step(img, bbox, label, scale)
if (ii + 1) % opt.plot_every == 0:
if os.path.exists(opt.debug_file):
ipdb.set_trace()
# plot loss
trainer.vis.plot_many(trainer.get_meter_data())
# plot groud truth bboxes
ori_img_ = inverse_normalize(at.tonumpy(img[0]))
gt_img = visdom_bbox(ori_img_, at.tonumpy(bbox_[0]),
at.tonumpy(label_[0]))
trainer.vis.img('gt_img', gt_img)
# plot predicti bboxes
_bboxes, _labels, _scores = trainer.faster_rcnn.predict(
[ori_img_], visualize=True)
pred_img = visdom_bbox(ori_img_, at.tonumpy(_bboxes[0]),
at.tonumpy(_labels[0]).reshape(-1),
at.tonumpy(_scores[0]))
trainer.vis.img('pred_img', pred_img)
# rpn confusion matrix(meter)
trainer.vis.text(str(trainer.rpn_cm.value().tolist()),
win='rpn_cm')
# roi confusion matrix
trainer.vis.img(
'roi_cm',
at.totensor(trainer.roi_cm.conf, False).float())
eval_result = eval(test_dataloader, faster_rcnn, test_num=opt.test_num)
trainer.vis.plot('test_map', eval_result['map'])
lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr']
log_info = 'lr:{}, map:{},loss:{}'.format(
str(lr_), str(eval_result['map']), str(trainer.get_meter_data()))
trainer.vis.log(log_info)
if eval_result['map'] > best_map:
best_map = eval_result['map']
best_path = trainer.save(best_map=best_map)
if epoch == 9:
trainer.load(best_path)
trainer.faster_rcnn.scale_lr(opt.lr_decay)
lr_ = lr_ * opt.lr_decay
if epoch == 13:
break
def train(**kwargs):
opt._parse(kwargs)
dataset = Dataset(opt)
print('load data')
dataloader = data_.DataLoader(dataset,
batch_size=1,
shuffle=True, \
# pin_memory=True,
num_workers=opt.num_workers)
testset = TestDataset(opt)
test_dataloader = data_.DataLoader(testset,
batch_size=1,
num_workers=opt.test_num_workers,
shuffle=False,
pin_memory=True)
faster_rcnn = FasterRCNNVGG16()
print('model construct completed')
trainer = FasterRCNNTrainer(faster_rcnn).cuda()
if opt.load_path:
trainer.load(opt.load_path)
print('load pretrained model from %s' % opt.load_path)
trainer.vis.text(dataset.db.label_names, win='labels')
best_map = 0
best_ap = np.array([0.] * opt.label_number)
lr_ = opt.lr
vis = trainer.vis
starttime = datetime.datetime.now()
for epoch in range(opt.epoch):
trainer.reset_meters()
for ii, (img, bbox_, label_, scale) in tqdm(enumerate(dataloader)):
scale = at.scalar(scale)
img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda()
trainer.train_step(img, bbox, label, scale)
if (ii + 1) % opt.plot_every == 0:
if os.path.exists(opt.debug_file):
ipdb.set_trace()
# plot loss
trainer.vis.plot_many(trainer.get_meter_data())
# plot groud truth bboxes
ori_img_ = inverse_normalize(at.tonumpy(img[0]))
gt_img = visdom_bbox(ori_img_, at.tonumpy(bbox_[0]),
at.tonumpy(label_[0]))
trainer.vis.img('gt_img', gt_img)
# plot predicti bboxes
_bboxes, _labels, _scores = trainer.faster_rcnn.predict(
[ori_img_], visualize=True)
pred_img = visdom_bbox(ori_img_, at.tonumpy(_bboxes[0]),
at.tonumpy(_labels[0]).reshape(-1),
at.tonumpy(_scores[0]))
trainer.vis.img('pred_img', pred_img)
# rpn confusion matrix(meter)
trainer.vis.text(str(trainer.rpn_cm.value().tolist()),
win='rpn_cm')
# roi confusion matrix
roi_cm = at.totensor(trainer.roi_cm.conf, False).float()
trainer.vis.img('roi_cm', roi_cm)
eval_result = eval(test_dataloader,
faster_rcnn,
vis=vis,
test_num=opt.test_num)
best_ap = dict(zip(opt.VOC_BBOX_LABEL_NAMES, eval_result['ap']))
trainer.vis.plot('test_map', eval_result['map'])
lr_ = trainer.faster_rcnn.optimizer.param_groups[0]['lr']
log_info = 'lr:{}, map:{},loss:{}'.format(
str(lr_), str(eval_result['map']), str(trainer.get_meter_data()))
trainer.vis.log(log_info)
if eval_result['map'] > best_map:
print('roi_cm=\n', trainer.roi_cm.value())
plot_confusion_matrix(trainer.roi_cm.value(),
classes=('animal', 'plant', 'rock',
'background'),
normalize=False,
title='Normalized Confusion Matrix')
best_map = eval_result['map']
best_path = trainer.save(best_map=best_map, best_ap=best_ap)
if epoch == 9:
trainer.load(best_path)
trainer.faster_rcnn.scale_lr(opt.lr_decay)
lr_ = lr_ * opt.lr_decay
# if epoch == 13:
# break
endtime = datetime.datetime.now()
train_consum = (endtime - starttime).seconds
print("train_consum=", train_consum)
def train(**kwargs):
opt._parse(kwargs)
dataset = Dataset(opt)
print("load data")
dataloader = data_.DataLoader(
dataset,
batch_size=1,
shuffle=True, # pin_memory=True,
num_workers=opt.num_workers,
)
testset = TestDataset(opt)
test_dataloader = data_.DataLoader(
testset,
batch_size=1,
num_workers=2,
shuffle=False, # pin_memory=True
)
faster_rcnn = FasterRCNNVGG16()
print("model construct completed")
trainer = FasterRCNNTrainer(faster_rcnn).cuda()
if opt.load_path:
trainer.load(opt.load_path)
print("load pretrained model from %s" % opt.load_path)
trainer.vis.text(dataset.db.label_names, win="labels")
best_map = 0
for epoch in range(7):
trainer.reset_meters()
for ii, (img, bbox_, label_, scale,
ori_img) in tqdm(enumerate(dataloader)):
scale = at.scalar(scale)
img, bbox, label = img.cuda().float(), bbox_.cuda(), label_.cuda()
losses = trainer.train_step(img, bbox, label, scale)
if (ii + 1) % opt.plot_every == 0:
if os.path.exists(opt.debug_file):
ipdb.set_trace()
# plot loss
trainer.vis.plot_many(trainer.get_meter_data())
# plot groud truth bboxes
ori_img_ = (img * 0.225 + 0.45).clamp(min=0, max=1) * 255
gt_img = visdom_bbox(
at.tonumpy(ori_img_)[0],
at.tonumpy(bbox_)[0], label_[0].numpy())
trainer.vis.img("gt_img", gt_img)
# plot predicti bboxes
_bboxes, _labels, _scores = trainer.faster_rcnn.predict(
ori_img, visualize=True)
pred_img = visdom_bbox(
at.tonumpy(ori_img[0]),
at.tonumpy(_bboxes[0]),
at.tonumpy(_labels[0]).reshape(-1),
at.tonumpy(_scores[0]),
)
trainer.vis.img("pred_img", pred_img)
# rpn confusion matrix(meter)
trainer.vis.text(str(trainer.rpn_cm.value().tolist()),
win="rpn_cm")
# roi confusion matrix
trainer.vis.img(
"roi_cm",
at.totensor(trainer.roi_cm.conf, False).float())
if epoch == 4:
trainer.faster_rcnn.scale_lr(opt.lr_decay)
eval_result = eval(test_dataloader, faster_rcnn, test_num=1e100)
print("eval_result")
trainer.save(mAP=eval_result["map"])
def train(epochs,
img_box_dict,
pretrained_model=None,
save_path=None,
rpn_rois=None,
train_rpn=True,
train_rcnn=True,
validate=False,
lock_grad_for_rpn=False,
lock_grad_for_rcnn=False):
fpn_resnet = FPNResNet().cuda()
# lock gradient
if lock_grad_for_rcnn:
for param in fpn_resnet.parameters():
param.requires_grad = False
for param in fpn_resnet.head.parameters():
param.requires_grad = True
if lock_grad_for_rpn:
for param in fpn_resnet.parameters():
param.requires_grad = False
for param in fpn_resnet.rpn.parameters():
param.requires_grad = True
fpn_resnet.get_optimizer(Config.lr)
trainer = FasterRCNNTrainer(fpn_resnet).cuda()
print('model constructed')
if pretrained_model is not None:
trainer.load(pretrained_model, load_optimizer=False)
if validate:
dict_train, dict_val = generate_train_val_data(img_box_dict,
p_train=0.95)
else:
dict_train = img_box_dict
dict_val = None
for epoch in range(epochs):
print('epoch: ', epoch)
for i, [img_dir, img_info] in tqdm(enumerate(dict_train.items())):
img, img_info, flipped = rescale_image(img_dir,
img_info,
flip=True)
img_size = list(img_info['img_size'])
img_tensor = create_img_tensor(img)
if rpn_rois:
img_rois = rpn_rois[img_dir]
if flipped:
max = img_size[1] - img_rois[:, 1]
min = img_size[1] - img_rois[:, 3]
img_rois[:, 1] = min
img_rois[:, 3] = max
img_rois = torch.from_numpy(img_rois).cuda()
trainer.train_step(img_tensor, img_info, img_rois, train_rpn,
train_rcnn)
else:
trainer.train_step(img_tensor, img_info, None, train_rpn,
train_rcnn)
trainer.save(save_path, save_optimizer=False)
if validate:
map = evaluation(dict_val, trainer.fpn_resnet)
print('mAP: ', map)
# lr decay
if epoch == int(epochs * 0.7):
trainer.scale_lr(Config.lr_decay)
