def test():
# prepare base things
args = parseArgs()
cfg, cfg_file_path = getCfgByDatasetAndBackbone(
datasetname=args.datasetname, backbonename=args.backbonename)
checkDir(cfg.TEST_BACKUPDIR)
logger_handle = Logger(cfg.TEST_LOGFILE)
use_cuda = torch.cuda.is_available()
clsnames = loadclsnames(cfg.CLSNAMESPATH)
# prepare dataset
if args.datasetname == 'coco':
dataset = COCODataset(rootdir=cfg.DATASET_ROOT_DIR,
image_size_dict=cfg.IMAGESIZE_DICT,
max_num_gt_boxes=-1,
use_color_jitter=False,
img_norm_info=cfg.IMAGE_NORMALIZE_INFO,
mode='TEST',
datasettype=args.datasettype,
annfilepath=args.annfilepath)
else:
raise ValueError('Unsupport datasetname <%s> now...' %
args.datasetname)
dataloader = torch.utils.data.DataLoader(dataset,
batch_size=1,
shuffle=False,
num_workers=0)
# prepare model
if args.backbonename.find('resnet') != -1:
model = RetinanetFPNResNets(mode='TEST',
cfg=cfg,
logger_handle=logger_handle)
else:
raise ValueError('Unsupport backbonename <%s> now...' %
args.backbonename)
if use_cuda:
model = model.cuda()
# load checkpoints
checkpoints = loadCheckpoints(args.checkpointspath, logger_handle)
model.load_state_dict(checkpoints['model'])
model.eval()
# test mAP
FloatTensor = torch.cuda.FloatTensor if use_cuda else torch.FloatTensor
results = []
img_ids = []
for batch_idx, samples in enumerate(dataloader):
logger_handle.info('detect %s/%s...' %
(batch_idx + 1, len(dataloader)))
# --do detect
img_id, img, w_ori, h_ori, gt_boxes, img_info, num_gt_boxes = samples
img_id, w_ori, h_ori, scale_factor = int(
img_id.item()), w_ori.item(), h_ori.item(), img_info[0][-1].item()
img_ids.append(img_id)
with torch.no_grad():
output = model(x=img.type(FloatTensor),
gt_boxes=gt_boxes.type(FloatTensor),
img_info=img_info.type(FloatTensor),
num_gt_boxes=num_gt_boxes.type(FloatTensor))
anchors = output[0].data.view(1, -1, 4)
preds_cls = output[1].data
preds_reg = output[2].data
# --parse the results
preds_reg = preds_reg.view(-1, 4) * torch.FloatTensor(
cfg.BBOX_NORMALIZE_STDS).type(FloatTensor) + torch.FloatTensor(
cfg.BBOX_NORMALIZE_MEANS).type(FloatTensor)
preds_reg = preds_reg.view(1, -1, 4)
boxes_pred = BBoxFunctions.decodeBboxes(anchors, preds_reg)
boxes_pred = BBoxFunctions.clipBoxes(
boxes_pred,
torch.from_numpy(
np.array(
[h_ori * scale_factor, w_ori * scale_factor,
scale_factor])).unsqueeze(0).type(FloatTensor).data)
boxes_pred = boxes_pred.squeeze()
scores = preds_cls.squeeze()
thresh = 0.05
for j in range(cfg.NUM_CLASSES - 1):
idxs = torch.nonzero(scores[:, j] > thresh).view(-1)
if idxs.numel() > 0:
cls_scores = scores[:, j][idxs]
_, order = torch.sort(cls_scores, 0, True)
cls_boxes = boxes_pred[idxs, :]
cls_dets = torch.cat((cls_boxes, cls_scores.unsqueeze(1)), 1)
cls_dets = cls_dets[order]
cls_dets, _ = nms(cls_dets, args.nmsthresh)
for cls_det in cls_dets:
category_id = dataset.clsids2cococlsids_dict.get(j)
x1, y1, x2, y2, score = cls_det
x1 = x1.item() / scale_factor
x2 = x2.item() / scale_factor
y1 = y1.item() / scale_factor
y2 = y2.item() / scale_factor
bbox = [x1, y1, x2, y2]
bbox[2] = bbox[2] - bbox[0]
bbox[3] = bbox[3] - bbox[1]
image_result = {
'image_id': img_id,
'category_id': int(category_id),
'score': float(score.item()),
'bbox': bbox
}
results.append(image_result)
json.dump(results, open(cfg.TEST_BBOXES_SAVE_PATH, 'w'), indent=4)
if args.datasettype in ['val2017']:
dataset.doDetectionEval(img_ids, cfg.TEST_BBOXES_SAVE_PATH)
def train():
# prepare base things
args = parseArgs()
cfg, cfg_file_path = getCfgByDatasetAndBackbone(
datasetname=args.datasetname, backbonename=args.backbonename)
checkDir(cfg.TRAIN_BACKUPDIR)
logger_handle = Logger(cfg.TRAIN_LOGFILE)
use_cuda = torch.cuda.is_available()
is_multi_gpus = cfg.IS_MULTI_GPUS
# prepare dataset
if args.datasetname == 'coco':
dataset = COCODataset(rootdir=cfg.DATASET_ROOT_DIR,
image_size_dict=cfg.IMAGESIZE_DICT,
max_num_gt_boxes=cfg.MAX_NUM_GT_BOXES,
use_color_jitter=cfg.USE_COLOR_JITTER,
img_norm_info=cfg.IMAGE_NORMALIZE_INFO,
mode='TRAIN',
datasettype='train2017')
dataloader = torch.utils.data.DataLoader(
dataset,
batch_size=cfg.BATCHSIZE,
sampler=NearestRatioRandomSampler(dataset.img_ratios,
cfg.BATCHSIZE),
num_workers=cfg.NUM_WORKERS,
collate_fn=COCODataset.paddingCollateFn,
pin_memory=cfg.PIN_MEMORY)
else:
raise ValueError('Unsupport backbonename <%s> now...' %
args.backbonename)
# prepare model
if args.backbonename.find('resnet') != -1:
model = RetinanetFPNResNets(mode='TRAIN',
cfg=cfg,
logger_handle=logger_handle)
else:
raise ValueError('Unsupport backbonename <%s> now...' %
args.backbonename)
start_epoch = 1
end_epoch = cfg.MAX_EPOCHS
if use_cuda:
model = model.cuda()
# prepare optimizer
learning_rate_idx = 0
if cfg.IS_USE_WARMUP:
learning_rate = cfg.LEARNING_RATES[learning_rate_idx] / 3
else:
learning_rate = cfg.LEARNING_RATES[learning_rate_idx]
optimizer = optim.SGD(filter(lambda p: p.requires_grad,
model.parameters()),
lr=learning_rate,
momentum=cfg.MOMENTUM,
weight_decay=cfg.WEIGHT_DECAY)
# check checkpoints path
if args.checkpointspath:
checkpoints = loadCheckpoints(args.checkpointspath, logger_handle)
model.load_state_dict(checkpoints['model'])
optimizer.load_state_dict(checkpoints['optimizer'])
start_epoch = checkpoints['epoch'] + 1
for epoch in range(1, start_epoch):
if epoch in cfg.LR_ADJUST_EPOCHS:
learning_rate_idx += 1
# data parallel
if is_multi_gpus:
model = nn.DataParallel(model)
# print config
logger_handle.info('Dataset used: %s, Number of images: %s' %
(args.datasetname, len(dataset)))
logger_handle.info('Backbone used: %s' % args.backbonename)
logger_handle.info('Checkpoints used: %s' % args.checkpointspath)
logger_handle.info('Config file used: %s' % cfg_file_path)
# train
FloatTensor = torch.cuda.FloatTensor if use_cuda else torch.FloatTensor
for epoch in range(start_epoch, end_epoch + 1):
# --set train mode
if is_multi_gpus:
model.module.setTrain()
else:
model.setTrain()
# --adjust learning rate
if epoch in cfg.LR_ADJUST_EPOCHS:
learning_rate_idx += 1
adjustLearningRate(optimizer=optimizer,
target_lr=cfg.LEARNING_RATES[learning_rate_idx],
logger_handle=logger_handle)
# --log info
logger_handle.info('Start epoch %s, learning rate is %s...' %
(epoch, cfg.LEARNING_RATES[learning_rate_idx]))
# --train epoch
for batch_idx, samples in enumerate(dataloader):
if (epoch == 1) and (cfg.IS_USE_WARMUP) and (
batch_idx == cfg.NUM_WARMUP_STEPS):
assert learning_rate_idx == 0, 'BUGS may exist...'
adjustLearningRate(
optimizer=optimizer,
target_lr=cfg.LEARNING_RATES[learning_rate_idx],
logger_handle=logger_handle)
optimizer.zero_grad()
img_ids, imgs, gt_boxes, img_info, num_gt_boxes = samples
output = model(x=imgs.type(FloatTensor),
gt_boxes=gt_boxes.type(FloatTensor),
img_info=img_info.type(FloatTensor),
num_gt_boxes=num_gt_boxes.type(FloatTensor))
anchors, preds_cls, preds_reg, loss_cls, loss_reg = output
loss = loss_cls.mean() + loss_reg.mean()
logger_handle.info('[EPOCH]: %s/%s, [BATCH]: %s/%s, [LEARNING_RATE]: %s, [DATASET]: %s \n\t [LOSS]: loss_cls %.4f, loss_reg %.4f, total %.4f' % \
(epoch, end_epoch, (batch_idx+1), len(dataloader), cfg.LEARNING_RATES[learning_rate_idx], args.datasetname, loss_cls.mean().item(), loss_reg.mean().item(), loss.mean().item()))
loss.backward()
clipGradients(model.parameters(), cfg.GRAD_CLIP_MAX_NORM,
cfg.GRAD_CLIP_NORM_TYPE)
optimizer.step()
# --save model
if (epoch % cfg.SAVE_INTERVAL == 0) or (epoch == end_epoch):
state_dict = {
'epoch':
epoch,
'model':
model.module.state_dict()
if is_multi_gpus else model.state_dict(),
'optimizer':
optimizer.state_dict()
}
savepath = os.path.join(cfg.TRAIN_BACKUPDIR,
'epoch_%s.pth' % epoch)
saveCheckpoints(state_dict, savepath, logger_handle)
def demo():
# prepare base things
args = parseArgs()
cfg, cfg_file_path = getCfgByDatasetAndBackbone(datasetname=args.datasetname, backbonename=args.backbonename)
checkDir(cfg.TEST_BACKUPDIR)
logger_handle = Logger(cfg.TEST_LOGFILE)
use_cuda = torch.cuda.is_available()
clsnames = loadclsnames(cfg.CLSNAMESPATH)
# prepare model
if args.backbonename.find('resnet') != -1:
model = FasterRCNNResNets(mode='TEST', cfg=cfg, logger_handle=logger_handle)
else:
raise ValueError('Unsupport backbonename <%s> now...' % args.backbonename)
if use_cuda:
model = model.cuda()
# load checkpoints
checkpoints = loadCheckpoints(args.checkpointspath, logger_handle)
model.load_state_dict(checkpoints['model'])
model.eval()
# do detect
FloatTensor = torch.cuda.FloatTensor if use_cuda else torch.FloatTensor
img = Image.open(args.imagepath)
if args.datasetname == 'coco':
input_img, scale_factor, target_size = COCODataset.preprocessImage(img, use_color_jitter=False, image_size_dict=cfg.IMAGESIZE_DICT, img_norm_info=cfg.IMAGE_NORMALIZE_INFO, use_caffe_pretrained_model=cfg.USE_CAFFE_PRETRAINED_MODEL)
else:
raise ValueError('Unsupport datasetname <%s> now...' % args.datasetname)
input_img = input_img.unsqueeze(0).type(FloatTensor)
gt_boxes = torch.FloatTensor([1, 1, 1, 1, 0]).unsqueeze(0).type(FloatTensor)
img_info = torch.from_numpy(np.array([target_size[0], target_size[1], scale_factor])).unsqueeze(0).type(FloatTensor)
num_gt_boxes = torch.FloatTensor([0]).unsqueeze(0).type(FloatTensor)
with torch.no_grad():
output = model(x=input_img, gt_boxes=gt_boxes, img_info=img_info, num_gt_boxes=num_gt_boxes)
rois = output[0].data[..., 1:5]
cls_probs = output[1].data
bbox_preds = output[2].data
# parse the results
if cfg.IS_CLASS_AGNOSTIC:
box_deltas = bbox_preds.view(-1, 4) * torch.FloatTensor(cfg.TEST_BBOX_NORMALIZE_STDS).type(FloatTensor) + torch.FloatTensor(cfg.TEST_BBOX_NORMALIZE_MEANS).type(FloatTensor)
box_deltas = box_deltas.view(1, -1, 4)
else:
box_deltas = bbox_preds.view(-1, 4) * torch.FloatTensor(cfg.TEST_BBOX_NORMALIZE_STDS).type(FloatTensor) + torch.FloatTensor(cfg.TEST_BBOX_NORMALIZE_MEANS).type(FloatTensor)
box_deltas = box_deltas.view(1, -1, 4*cfg.NUM_CLASSES)
boxes_pred = BBoxFunctions.decodeBboxes(rois, box_deltas)
boxes_pred = BBoxFunctions.clipBoxes(boxes_pred, img_info.data)
boxes_pred = boxes_pred.squeeze()
scores = cls_probs.squeeze()
thresh = 0.05
for j in range(1, cfg.NUM_CLASSES):
idxs = torch.nonzero(scores[:, j] > thresh).view(-1)
if idxs.numel() > 0:
cls_scores = scores[:, j][idxs]
_, order = torch.sort(cls_scores, 0, True)
if cfg.IS_CLASS_AGNOSTIC:
cls_boxes = boxes_pred[idxs, :]
else:
cls_boxes = boxes_pred[idxs][:, j*4: (j+1)*4]
cls_dets = torch.cat((cls_boxes, cls_scores.unsqueeze(1)), 1)
cls_dets = cls_dets[order]
_, keep_idxs = nms(cls_dets, args.nmsthresh)
cls_dets = cls_dets[keep_idxs.view(-1).long()]
for cls_det in cls_dets:
if cls_det[-1] > args.confthresh:
x1, y1, x2, y2 = cls_det[:4]
x1 = x1.item() / scale_factor
x2 = x2.item() / scale_factor
y1 = y1.item() / scale_factor
y2 = y2.item() / scale_factor
label = clsnames[j-1]
logger_handle.info('Detect a %s in confidence %.4f...' % (label, cls_det[-1].item()))
color = (0, 255, 0)
draw = ImageDraw.Draw(img)
draw.line([(x1, y1), (x2, y1), (x2, y2), (x1, y2), (x1, y1)], width=2, fill=color)
font = ImageFont.truetype('libs/font.TTF', 25)
draw.text((x1+5, y1), label, fill=color, font=font)
img.save(os.path.join(cfg.TEST_BACKUPDIR, 'demo_output.jpg'))