def evaluate_one_shot(model, xloader, api, cal_mode, seed=111):
print(
"This is an old version of codes to use NAS-Bench-API, and should be modified to align with the new version. Please contact me for more details if you use this function."
)
weights = deepcopy(model.state_dict())
model.train(cal_mode)
with torch.no_grad():
logits = nn.functional.log_softmax(model.arch_parameters, dim=-1)
archs = CellStructure.gen_all(model.op_names, model.max_nodes, False)
probs, accuracies, gt_accs_10_valid, gt_accs_10_test = [], [], [], []
loader_iter = iter(xloader)
random.seed(seed)
random.shuffle(archs)
for idx, arch in enumerate(archs):
arch_index = api.query_index_by_arch(arch)
metrics = api.get_more_info(arch_index, "cifar10-valid", None,
False, False)
gt_accs_10_valid.append(metrics["valid-accuracy"])
metrics = api.get_more_info(arch_index, "cifar10", None, False,
False)
gt_accs_10_test.append(metrics["test-accuracy"])
select_logits = []
for i, node_info in enumerate(arch.nodes):
for op, xin in node_info:
node_str = "{:}<-{:}".format(i + 1, xin)
op_index = model.op_names.index(op)
select_logits.append(logits[model.edge2index[node_str],
op_index])
cur_prob = sum(select_logits).item()
probs.append(cur_prob)
cor_prob_valid = np.corrcoef(probs, gt_accs_10_valid)[0, 1]
cor_prob_test = np.corrcoef(probs, gt_accs_10_test)[0, 1]
print(
"{:} correlation for probabilities : {:.6f} on CIFAR-10 validation and {:.6f} on CIFAR-10 test"
.format(time_string(), cor_prob_valid, cor_prob_test))
for idx, arch in enumerate(archs):
model.set_cal_mode("dynamic", arch)
try:
inputs, targets = next(loader_iter)
except:
loader_iter = iter(xloader)
inputs, targets = next(loader_iter)
_, logits = model(inputs.cuda())
_, preds = torch.max(logits, dim=-1)
correct = (preds == targets.cuda()).float()
accuracies.append(correct.mean().item())
if idx != 0 and (idx % 500 == 0 or idx + 1 == len(archs)):
cor_accs_valid = np.corrcoef(accuracies,
gt_accs_10_valid[:idx + 1])[0, 1]
cor_accs_test = np.corrcoef(accuracies,
gt_accs_10_test[:idx + 1])[0, 1]
print(
"{:} {:05d}/{:05d} mode={:5s}, correlation : accs={:.5f} for CIFAR-10 valid, {:.5f} for CIFAR-10 test."
.format(time_string(), idx, len(archs),
"Train" if cal_mode else "Eval", cor_accs_valid,
cor_accs_test))
model.load_state_dict(weights)
return archs, probs, accuracies
def generate_meta_info(save_dir, max_node, divide=40):
aa_nas_bench_ss = get_search_spaces('cell', 'nas-bench-201')
archs = CellStructure.gen_all(aa_nas_bench_ss, max_node, False)
print ('There are {:} archs vs {:}.'.format(len(archs), len(aa_nas_bench_ss) ** ((max_node-1)*max_node/2)))
random.seed( 88 ) # please do not change this line for reproducibility
random.shuffle( archs )
# to test fixed-random shuffle
#print ('arch [0] : {:}\n---->>>> {:}'.format( archs[0], archs[0].tostr() ))
#print ('arch [9] : {:}\n---->>>> {:}'.format( archs[9], archs[9].tostr() ))
assert archs[0 ].tostr() == '|avg_pool_3x3~0|+|nor_conv_1x1~0|skip_connect~1|+|nor_conv_1x1~0|skip_connect~1|skip_connect~2|', 'please check the 0-th architecture : {:}'.format(archs[0])
assert archs[9 ].tostr() == '|avg_pool_3x3~0|+|none~0|none~1|+|skip_connect~0|none~1|nor_conv_3x3~2|', 'please check the 9-th architecture : {:}'.format(archs[9])
assert archs[123].tostr() == '|avg_pool_3x3~0|+|avg_pool_3x3~0|nor_conv_1x1~1|+|none~0|avg_pool_3x3~1|nor_conv_3x3~2|', 'please check the 123-th architecture : {:}'.format(archs[123])
total_arch = len(archs)
num = 50000
indexes_5W = list(range(num))
random.seed( 1021 )
random.shuffle( indexes_5W )
train_split = sorted( list(set(indexes_5W[:num//2])) )
valid_split = sorted( list(set(indexes_5W[num//2:])) )
assert len(train_split) + len(valid_split) == num
assert train_split[0] == 0 and train_split[10] == 26 and train_split[111] == 203 and valid_split[0] == 1 and valid_split[10] == 18 and valid_split[111] == 242, '{:} {:} {:} - {:} {:} {:}'.format(train_split[0], train_split[10], train_split[111], valid_split[0], valid_split[10], valid_split[111])
splits = {num: {'train': train_split, 'valid': valid_split} }
info = {'archs' : [x.tostr() for x in archs],
'total' : total_arch,
'max_node' : max_node,
'splits': splits}
save_dir = Path(save_dir)
save_dir.mkdir(parents=True, exist_ok=True)
save_name = save_dir / 'meta-node-{:}.pth'.format(max_node)
assert not save_name.exists(), '{:} already exist'.format(save_name)
torch.save(info, save_name)
print ('save the meta file into {:}'.format(save_name))
script_name_full = save_dir / 'BENCH-201-N{:}.opt-full.script'.format(max_node)
script_name_less = save_dir / 'BENCH-201-N{:}.opt-less.script'.format(max_node)
full_file = open(str(script_name_full), 'w')
less_file = open(str(script_name_less), 'w')
gaps = total_arch // divide
for start in range(0, total_arch, gaps):
xend = min(start+gaps, total_arch)
full_file.write('bash ./scripts-search/NAS-Bench-201/train-models.sh 0 {:5d} {:5d} -1 \'777 888 999\'\n'.format(start, xend-1))
less_file.write('bash ./scripts-search/NAS-Bench-201/train-models.sh 1 {:5d} {:5d} -1 \'777 888 999\'\n'.format(start, xend-1))
print ('save the training script into {:} and {:}'.format(script_name_full, script_name_less))
full_file.close()
less_file.close()
script_name = save_dir / 'meta-node-{:}.cal-script.txt'.format(max_node)
macro = 'OMP_NUM_THREADS=6 CUDA_VISIBLE_DEVICES=0'
with open(str(script_name), 'w') as cfile:
for start in range(0, total_arch, gaps):
xend = min(start+gaps, total_arch)
cfile.write('{:} python exps/NAS-Bench-201/statistics.py --mode cal --target_dir {:06d}-{:06d}-C16-N5\n'.format(macro, start, xend-1))
print ('save the post-processing script into {:}'.format(script_name))
def evaluate_one_shot(model, xloader, api, cal_mode, seed=111):
weights = deepcopy(model.state_dict())
model.train(cal_mode)
with torch.no_grad():
logits = nn.functional.log_softmax(model.arch_parameters, dim=-1)
archs = CellStructure.gen_all(model.op_names, model.max_nodes, False)
probs, accuracies, gt_accs_10_valid, gt_accs_10_test = [], [], [], []
loader_iter = iter(xloader)
random.seed(seed)
random.shuffle(archs)
for idx, arch in enumerate(archs):
arch_index = api.query_index_by_arch(arch)
metrics = api.get_more_info(arch_index, 'cifar10-valid', None,
False, False)
gt_accs_10_valid.append(metrics['valid-accuracy'])
metrics = api.get_more_info(arch_index, 'cifar10', None, False,
False)
gt_accs_10_test.append(metrics['test-accuracy'])
select_logits = []
for i, node_info in enumerate(arch.nodes):
for op, xin in node_info:
node_str = '{:}<-{:}'.format(i + 1, xin)
op_index = model.op_names.index(op)
select_logits.append(logits[model.edge2index[node_str],
op_index])
cur_prob = sum(select_logits).item()
probs.append(cur_prob)
cor_prob_valid = np.corrcoef(probs, gt_accs_10_valid)[0, 1]
cor_prob_test = np.corrcoef(probs, gt_accs_10_test)[0, 1]
print(
'{:} correlation for probabilities : {:.6f} on CIFAR-10 validation and {:.6f} on CIFAR-10 test'
.format(time_string(), cor_prob_valid, cor_prob_test))
for idx, arch in enumerate(archs):
model.set_cal_mode('dynamic', arch)
try:
inputs, targets = next(loader_iter)
except:
loader_iter = iter(xloader)
inputs, targets = next(loader_iter)
_, logits = model(inputs.cuda())
_, preds = torch.max(logits, dim=-1)
correct = (preds == targets.cuda()).float()
accuracies.append(correct.mean().item())
if idx != 0 and (idx % 500 == 0 or idx + 1 == len(archs)):
cor_accs_valid = np.corrcoef(accuracies,
gt_accs_10_valid[:idx + 1])[0, 1]
cor_accs_test = np.corrcoef(accuracies,
gt_accs_10_test[:idx + 1])[0, 1]
print(
'{:} {:05d}/{:05d} mode={:5s}, correlation : accs={:.5f} for CIFAR-10 valid, {:.5f} for CIFAR-10 test.'
.format(time_string(), idx, len(archs),
'Train' if cal_mode else 'Eval', cor_accs_valid,
cor_accs_test))
model.load_state_dict(weights)
return archs, probs, accuracies
def traverse_net(max_node):
aa_nas_bench_ss = get_search_spaces('cell', 'nats-bench')
archs = CellStructure.gen_all(aa_nas_bench_ss, max_node, False)
print ('There are {:} archs vs {:}.'.format(len(archs), len(aa_nas_bench_ss) ** ((max_node-1)*max_node/2)))
random.seed( 88 ) # please do not change this line for reproducibility
random.shuffle( archs )
assert archs[0 ].tostr() == '|avg_pool_3x3~0|+|nor_conv_1x1~0|skip_connect~1|+|nor_conv_1x1~0|skip_connect~1|skip_connect~2|', 'please check the 0-th architecture : {:}'.format(archs[0])
assert archs[9 ].tostr() == '|avg_pool_3x3~0|+|none~0|none~1|+|skip_connect~0|none~1|nor_conv_3x3~2|', 'please check the 9-th architecture : {:}'.format(archs[9])
assert archs[123].tostr() == '|avg_pool_3x3~0|+|avg_pool_3x3~0|nor_conv_1x1~1|+|none~0|avg_pool_3x3~1|nor_conv_3x3~2|', 'please check the 123-th architecture : {:}'.format(archs[123])
return [x.tostr() for x in archs]
def generate_meta_info(save_dir, max_node, divide=40):
aa_nas_bench_ss = get_search_spaces('cell', 'nas-bench-201')
archs = CellStructure.gen_all(aa_nas_bench_ss, max_node, False)
print('There are {:} archs vs {:}.'.format(
len(archs),
len(aa_nas_bench_ss)**((max_node - 1) * max_node / 2)))
random.seed(88) # please do not change this line for reproducibility
random.shuffle(archs)
# to test fixed-random shuffle
#print ('arch [0] : {:}\n---->>>> {:}'.format( archs[0], archs[0].tostr() ))
#print ('arch [9] : {:}\n---->>>> {:}'.format( archs[9], archs[9].tostr() ))
assert archs[0].tostr(
) == '|avg_pool_3x3~0|+|nor_conv_1x1~0|skip_connect~1|+|nor_conv_1x1~0|skip_connect~1|skip_connect~2|', 'please check the 0-th architecture : {:}'.format(
archs[0])
assert archs[9].tostr(
) == '|avg_pool_3x3~0|+|none~0|none~1|+|skip_connect~0|none~1|nor_conv_3x3~2|', 'please check the 9-th architecture : {:}'.format(
archs[9])
assert archs[123].tostr(
) == '|avg_pool_3x3~0|+|avg_pool_3x3~0|nor_conv_1x1~1|+|none~0|avg_pool_3x3~1|nor_conv_3x3~2|', 'please check the 123-th architecture : {:}'.format(
archs[123])
total_arch = len(archs)
num = 50000
indexes_5W = list(range(num))
random.seed(1021)
random.shuffle(indexes_5W)
train_split = sorted(list(set(indexes_5W[:num // 2])))
valid_split = sorted(list(set(indexes_5W[num // 2:])))
assert len(train_split) + len(valid_split) == num
assert train_split[0] == 0 and train_split[10] == 26 and train_split[
111] == 203 and valid_split[0] == 1 and valid_split[
10] == 18 and valid_split[
111] == 242, '{:} {:} {:} - {:} {:} {:}'.format(
train_split[0], train_split[10], train_split[111],
valid_split[0], valid_split[10], valid_split[111])
splits = {num: {'train': train_split, 'valid': valid_split}}
info = {
'archs': [x.tostr() for x in archs],
'total': total_arch,
'max_node': max_node,
'splits': splits
}
save_dir = Path(save_dir)
save_dir.mkdir(parents=True, exist_ok=True)
save_name = save_dir / 'meta-node-{:}.pth'.format(max_node)
assert not save_name.exists(), '{:} already exist'.format(save_name)
torch.save(info, save_name)
print('save the meta file into {:}'.format(save_name))