def prefetch_test(opt):
os.environ['CUDA_VISIBLE_DEVICES'] = str(opt.gpus)
opt = opts().update_dataset_info_and_set_heads(opt, COCO)
print(opt)
Logger(opt)
split = 'val' if not opt.trainval else 'test'
dataset = COCO(opt, split)
detector = CtdetDetector(opt)
data_loader = torch.utils.data.DataLoader(PrefetchDataset(opt, dataset, pre_process),
batch_size=1,
shuffle=False,
num_workers=1,
pin_memory=True)
results = {}
num_iters = len(dataset)
bar = Bar(f'{opt.exp_id}', max=num_iters)
time_stats = ['tot', 'net', 'dec', 'post', 'merge']
avg_time_stats = {t: AverageMeter() for t in time_stats}
for i, (img_id, images) in enumerate(data_loader):
ret = detector.run(images)
results[img_id.numpy().astype(np.int32)[0]] = ret['results']
bar.suffix = f'{i}/{num_iters}|Elapsed: {bar.elapsed_td} |ETA: {bar.eta_td} '
for t in avg_time_stats:
avg_time_stats[t].update(ret[t])
bar.suffix = bar.suffix + '|{} {tm.val:.3f} ({tm.avg:.3f}) '.format(t, tm=avg_time_stats[t])
bar.next()
bar.finish()
dataset.run_eval(results, opt.save_dir)
def main(opt):
wandb.init(project="centernet_easy_tf")
TF_ctdet_temp = TF_ctdet()
opt = opts().update_dataset_info_and_set_heads(opt, TF_ctdet_temp)
print(opt)
os.environ['CUDA_VISIBLE_DEVICES'] = opt.gpus_str
opt.device = 'cuda'
print('Creating model...')
TF_dataloader_ = TF_dataloader(
'./data/coco/images/train2017',
'./data/coco/annotations/instances_train2017.json', 1, opt)
model = create_model(opt.backbone, opt.heads, opt.head_conv)
optimizer = tf.keras.optimizers.Adam(learning_rate=5e-4)
Custom_loss = CtdetLoss(opt)
model.compile(loss=Custom_loss, optimizer=optimizer)
for epoch in range(1, 100):
while (1):
temp = TF_dataloader_.get_coco_data('train')
losse = model.fit(temp['input'], temp['hm'])
print(1)
wandb.watch(model)
def prefetch_test(opt):
os.environ['CUDA_VISIBLE_DEVICES'] = opt.gpus_str
opt = opts().update_dataset_info_and_set_heads(opt, CTDetDataset)
print(opt)
split = 'val'
dataset = CTDetDataset(opt, split)
detector = CtdetDetector(opt)
result = {}
if not os.path.exists(os.path.join(opt.save_dir, 'result.json')):
data_loader = torch.utils.data.DataLoader(PrefetchDataset(
opt, dataset, detector.pre_process),
batch_size=1,
shuffle=False,
pin_memory=True)
for ind, (img_id, pre_processes_images) in enumerate(data_loader):
ret = detector.run(pre_processes_images)
result[img_id.numpy().astype(np.int32)[0]] = ret['results']
print(ind)
dataset.run_eval(result, os.path.join(opt.save_dir, 'result.json'))
cv2.imshow('input', img)
ret = detector.run(img)
time_str = ''
for stat in time_stats:
time_str = time_str + '{} {:.3f}s |'.format(stat, ret[stat])
print(time_str)
if cv2.waitKey(1) == 27:
return # esc to quit
else:
if os.path.isdir(opt.demo):
image_names = []
ls = os.listdir(opt.demo)
for file_name in sorted(ls):
ext = file_name[file_name.rfind('.') + 1:].lower()
if ext in image_ext:
image_names.append(os.path.join(opt.demo, file_name))
else:
image_names = [opt.demo]
for (image_name) in image_names:
ret = detector.run(image_name)
time_str = ''
for stat in time_stats:
time_str = time_str + '{} {:.3f}s |'.format(stat, ret[stat])
print(time_str)
if __name__ == '__main__':
opt = opts().init()
demo(opt)
data_loader = torch.utils.data.DataLoader(PrefetchDataset(opt, dataset, pre_process),
batch_size=1,
shuffle=False,
num_workers=1,
pin_memory=True)
results = {}
num_iters = len(dataset)
bar = Bar(f'{opt.exp_id}', max=num_iters)
time_stats = ['tot', 'net', 'dec', 'post', 'merge']
avg_time_stats = {t: AverageMeter() for t in time_stats}
for i, (img_id, images) in enumerate(data_loader):
ret = detector.run(images)
results[img_id.numpy().astype(np.int32)[0]] = ret['results']
bar.suffix = f'{i}/{num_iters}|Elapsed: {bar.elapsed_td} |ETA: {bar.eta_td} '
for t in avg_time_stats:
avg_time_stats[t].update(ret[t])
bar.suffix = bar.suffix + '|{} {tm.val:.3f} ({tm.avg:.3f}) '.format(t, tm=avg_time_stats[t])
bar.next()
bar.finish()
dataset.run_eval(results, opt.save_dir)
if __name__ == '__main__':
opt = opts().parse()
prefetch_test(opt)
def main(opt):
wandb.init(project="centernet_easy")
torch.manual_seed(opt.seed)
torch.backends.cudnn.benchmark = True
opt = opts().update_dataset_info_and_set_heads(opt, CTDetDataset)
print(opt)
os.environ['CUDA_VISIBLE_DEVICES'] = opt.gpus_str
opt.device = 'cuda'
print('Creating model...')
model = create_model(opt.backbone, opt.heads, opt.head_conv, opt.tensorrt)
wandb.watch(model)
optimizer = torch.optim.Adam(model.parameters(), lr=opt.lr)
start_epoch = 0
if opt.load_model != '':
model, optimizer, start_epoch = load_model(model, opt.load_model, optimizer, opt.resume, opt.lr, opt.lr_step)
Trainer = CtdetTrainer
trainer = Trainer(opt, model, optimizer)
trainer.set_device(opt.gpus, opt.chunk_sizes, opt.device)
print('Setting up data...')
val_loader = torch.utils.data.DataLoader(
CTDetDataset(opt, 'val'),
batch_size=1,
shuffle=False,
num_workers=1,
pin_memory=True
)
if opt.test:
_, preds = trainer.val(0, val_loader)
val_loader.dataset.run_eval(preds, opt.save_dir)
return
train_loader = torch.utils.data.DataLoader(
CTDetDataset(opt, 'train'),
batch_size=opt.batch_size,
shuffle=True,
num_workers=opt.num_workers,
pin_memory=True,
drop_last=True
)
print('Starting training...')
best = 1e10
if not os.path.exists(os.path.join(opt.root_dir, 'exp')):
os.mkdir(os.path.join(opt.root_dir, 'exp'))
if not os.path.exists(opt.exp_dir):
os.mkdir(opt.exp_dir)
if not os.path.exists(opt.save_dir):
os.mkdir(opt.save_dir)
for epoch in range(start_epoch + 1, opt.num_epochs + 1):
mark = epoch if opt.save_all else 'last'
log_dict_train, _ = trainer.train(epoch, train_loader, wandb)
if wandb != None:
wandb.log({"{} loss".format('train'): log_dict_train[opt.metric]})
#print('epoch: {}, loss: {} |'.format(epoch, avg_loss))
if opt.val_intervals > 0 and epoch % opt.val_intervals == 0:
save_model(os.path.join(opt.save_dir, 'model_{}.pth'.format(mark)),
epoch, model, optimizer)
with torch.no_grad():
log_dict_val, preds = trainer.val(epoch, val_loader, wandb)
if wandb != None:
wandb.log({"{} loss".format('val'): log_dict_val[opt.metric]})
if log_dict_val[opt.metric] < best:
best = log_dict_val[opt.metric]
save_model(os.path.join(opt.save_dir, 'model_best.pth'),
epoch, model)
else:
save_model(os.path.join(opt.save_dir, 'model_last.pth'),
epoch, model, optimizer)
if epoch in opt.lr_step:
save_model(os.path.join(opt.save_dir, 'model_{}.pth'.format(epoch)),
epoch, model, optimizer)
lr = opt.lr * (0.1 ** (opt.lr_step.index(epoch) + 1))
print('Drop LR to', lr)
for param_group in optimizer.param_groups:
param_group['lr'] = lr