except Exception as e:
print(e)
sys.exit()
average_elapsed_time = np.sum(elapsed_times) / (TEST_TRIAL *
batch_num)
result[lr][node] = average_elapsed_time
print(
'[Resolution: Size ({}x{}), OutputNode: {}] / Inference time per frame(sec) {} / Max-Min(sec) {}'
.format(
t_w, t_h, node, round(average_elapsed_time, 4),
round(
np.max(elapsed_times) - np.min(elapsed_times), 4)))
for node in self.output_nodes:
log = ''
log += '{}\t'.format(node)
for lr in self.node2res[node]:
log += '{}\t'.format(round(result[lr][node], 4))
summary_logger.info(log)
if __name__ == "__main__":
model = MultiNetwork(template.get_nas_config(opt.quality))
dataset = DatasetForDASH(opt)
evaluator = Tester(opt, model, dataset)
#evaluator.evaluate_quality()
evaluator.evaluate_runtime()
for i in range(idx):
res = self.body[i](res)
res = self.body_end(res)
res += x
if self.scale > 1:
x = self.upscale(res)
else:
x = res
x = self.tail(x)
return x
if __name__ == "__main__":
"""Simple test code for model"""
model = MultiNetwork(template.get_nas_config('low')).to('cuda:0')
model.setTargetScale(4)
dataset = DatasetForDASH(opt)
dataset.setTargetLR(240)
dataset.setDatasetType('train')
#print(len(dataset))
#print(model.getOutputNodes(4))
dataloader = data.DataLoader(dataset=dataset, num_workers=opt.num_thread, batch_size=opt.num_batch, pin_memory=True, shuffle=True)
for iteration, batch in enumerate(dataloader):
batch[0] = batch[0].cuda()
output = model(batch[0])
print(batch[0].size(), output.size())
break