arcface
This commit is contained in:
chenxuanhong
@@ -0,0 +1,71 @@
|
||||
import os
|
||||
import sys
|
||||
|
||||
import matplotlib.pyplot as plt
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
from menpo.visualize.viewmatplotlib import sample_colours_from_colourmap
|
||||
from prettytable import PrettyTable
|
||||
from sklearn.metrics import roc_curve, auc
|
||||
|
||||
with open(sys.argv[1], "r") as f:
|
||||
files = f.readlines()
|
||||
|
||||
files = [x.strip() for x in files]
|
||||
image_path = "/train_tmp/IJB_release/IJBC"
|
||||
|
||||
|
||||
def read_template_pair_list(path):
|
||||
pairs = pd.read_csv(path, sep=' ', header=None).values
|
||||
t1 = pairs[:, 0].astype(np.int)
|
||||
t2 = pairs[:, 1].astype(np.int)
|
||||
label = pairs[:, 2].astype(np.int)
|
||||
return t1, t2, label
|
||||
|
||||
|
||||
p1, p2, label = read_template_pair_list(
|
||||
os.path.join('%s/meta' % image_path,
|
||||
'%s_template_pair_label.txt' % 'ijbc'))
|
||||
|
||||
methods = []
|
||||
scores = []
|
||||
for file in files:
|
||||
methods.append(file)
|
||||
scores.append(np.load(file))
|
||||
|
||||
methods = np.array(methods)
|
||||
scores = dict(zip(methods, scores))
|
||||
colours = dict(
|
||||
zip(methods, sample_colours_from_colourmap(methods.shape[0], 'Set2')))
|
||||
x_labels = [10 ** -6, 10 ** -5, 10 ** -4, 10 ** -3, 10 ** -2, 10 ** -1]
|
||||
tpr_fpr_table = PrettyTable(['Methods'] + [str(x) for x in x_labels])
|
||||
fig = plt.figure()
|
||||
for method in methods:
|
||||
fpr, tpr, _ = roc_curve(label, scores[method])
|
||||
roc_auc = auc(fpr, tpr)
|
||||
fpr = np.flipud(fpr)
|
||||
tpr = np.flipud(tpr) # select largest tpr at same fpr
|
||||
plt.plot(fpr,
|
||||
tpr,
|
||||
color=colours[method],
|
||||
lw=1,
|
||||
label=('[%s (AUC = %0.4f %%)]' %
|
||||
(method.split('-')[-1], roc_auc * 100)))
|
||||
tpr_fpr_row = []
|
||||
tpr_fpr_row.append(method)
|
||||
for fpr_iter in np.arange(len(x_labels)):
|
||||
_, min_index = min(
|
||||
list(zip(abs(fpr - x_labels[fpr_iter]), range(len(fpr)))))
|
||||
tpr_fpr_row.append('%.2f' % (tpr[min_index] * 100))
|
||||
tpr_fpr_table.add_row(tpr_fpr_row)
|
||||
plt.xlim([10 ** -6, 0.1])
|
||||
plt.ylim([0.3, 1.0])
|
||||
plt.grid(linestyle='--', linewidth=1)
|
||||
plt.xticks(x_labels)
|
||||
plt.yticks(np.linspace(0.3, 1.0, 8, endpoint=True))
|
||||
plt.xscale('log')
|
||||
plt.xlabel('False Positive Rate')
|
||||
plt.ylabel('True Positive Rate')
|
||||
plt.title('ROC on IJB')
|
||||
plt.legend(loc="lower right")
|
||||
print(tpr_fpr_table)
|
||||
@@ -0,0 +1,110 @@
|
||||
import logging
|
||||
import os
|
||||
import time
|
||||
from typing import List
|
||||
|
||||
import torch
|
||||
|
||||
from eval import verification
|
||||
from utils.utils_logging import AverageMeter
|
||||
from torch.utils.tensorboard import SummaryWriter
|
||||
from torch import distributed
|
||||
|
||||
|
||||
class CallBackVerification(object):
|
||||
|
||||
def __init__(self, val_targets, rec_prefix, summary_writer=None, image_size=(112, 112)):
|
||||
self.rank: int = distributed.get_rank()
|
||||
self.highest_acc: float = 0.0
|
||||
self.highest_acc_list: List[float] = [0.0] * len(val_targets)
|
||||
self.ver_list: List[object] = []
|
||||
self.ver_name_list: List[str] = []
|
||||
if self.rank is 0:
|
||||
self.init_dataset(val_targets=val_targets, data_dir=rec_prefix, image_size=image_size)
|
||||
|
||||
self.summary_writer = summary_writer
|
||||
|
||||
def ver_test(self, backbone: torch.nn.Module, global_step: int):
|
||||
results = []
|
||||
for i in range(len(self.ver_list)):
|
||||
acc1, std1, acc2, std2, xnorm, embeddings_list = verification.test(
|
||||
self.ver_list[i], backbone, 10, 10)
|
||||
logging.info('[%s][%d]XNorm: %f' % (self.ver_name_list[i], global_step, xnorm))
|
||||
logging.info('[%s][%d]Accuracy-Flip: %1.5f+-%1.5f' % (self.ver_name_list[i], global_step, acc2, std2))
|
||||
|
||||
self.summary_writer: SummaryWriter
|
||||
self.summary_writer.add_scalar(tag=self.ver_name_list[i], scalar_value=acc2, global_step=global_step, )
|
||||
|
||||
if acc2 > self.highest_acc_list[i]:
|
||||
self.highest_acc_list[i] = acc2
|
||||
logging.info(
|
||||
'[%s][%d]Accuracy-Highest: %1.5f' % (self.ver_name_list[i], global_step, self.highest_acc_list[i]))
|
||||
results.append(acc2)
|
||||
|
||||
def init_dataset(self, val_targets, data_dir, image_size):
|
||||
for name in val_targets:
|
||||
path = os.path.join(data_dir, name + ".bin")
|
||||
if os.path.exists(path):
|
||||
data_set = verification.load_bin(path, image_size)
|
||||
self.ver_list.append(data_set)
|
||||
self.ver_name_list.append(name)
|
||||
|
||||
def __call__(self, num_update, backbone: torch.nn.Module):
|
||||
if self.rank is 0 and num_update > 0:
|
||||
backbone.eval()
|
||||
self.ver_test(backbone, num_update)
|
||||
backbone.train()
|
||||
|
||||
|
||||
class CallBackLogging(object):
|
||||
def __init__(self, frequent, total_step, batch_size, writer=None):
|
||||
self.frequent: int = frequent
|
||||
self.rank: int = distributed.get_rank()
|
||||
self.world_size: int = distributed.get_world_size()
|
||||
self.time_start = time.time()
|
||||
self.total_step: int = total_step
|
||||
self.batch_size: int = batch_size
|
||||
self.writer = writer
|
||||
|
||||
self.init = False
|
||||
self.tic = 0
|
||||
|
||||
def __call__(self,
|
||||
global_step: int,
|
||||
loss: AverageMeter,
|
||||
epoch: int,
|
||||
fp16: bool,
|
||||
learning_rate: float,
|
||||
grad_scaler: torch.cuda.amp.GradScaler):
|
||||
if self.rank == 0 and global_step > 0 and global_step % self.frequent == 0:
|
||||
if self.init:
|
||||
try:
|
||||
speed: float = self.frequent * self.batch_size / (time.time() - self.tic)
|
||||
speed_total = speed * self.world_size
|
||||
except ZeroDivisionError:
|
||||
speed_total = float('inf')
|
||||
|
||||
time_now = (time.time() - self.time_start) / 3600
|
||||
time_total = time_now / ((global_step + 1) / self.total_step)
|
||||
time_for_end = time_total - time_now
|
||||
if self.writer is not None:
|
||||
self.writer.add_scalar('time_for_end', time_for_end, global_step)
|
||||
self.writer.add_scalar('learning_rate', learning_rate, global_step)
|
||||
self.writer.add_scalar('loss', loss.avg, global_step)
|
||||
if fp16:
|
||||
msg = "Speed %.2f samples/sec Loss %.4f LearningRate %.4f Epoch: %d Global Step: %d " \
|
||||
"Fp16 Grad Scale: %2.f Required: %1.f hours" % (
|
||||
speed_total, loss.avg, learning_rate, epoch, global_step,
|
||||
grad_scaler.get_scale(), time_for_end
|
||||
)
|
||||
else:
|
||||
msg = "Speed %.2f samples/sec Loss %.4f LearningRate %.4f Epoch: %d Global Step: %d " \
|
||||
"Required: %1.f hours" % (
|
||||
speed_total, loss.avg, learning_rate, epoch, global_step, time_for_end
|
||||
)
|
||||
logging.info(msg)
|
||||
loss.reset()
|
||||
self.tic = time.time()
|
||||
else:
|
||||
self.init = True
|
||||
self.tic = time.time()
|
||||
@@ -0,0 +1,16 @@
|
||||
import importlib
|
||||
import os.path as osp
|
||||
|
||||
|
||||
def get_config(config_file):
|
||||
assert config_file.startswith('configs/'), 'config file setting must start with configs/'
|
||||
temp_config_name = osp.basename(config_file)
|
||||
temp_module_name = osp.splitext(temp_config_name)[0]
|
||||
config = importlib.import_module("configs.base")
|
||||
cfg = config.config
|
||||
config = importlib.import_module("configs.%s" % temp_module_name)
|
||||
job_cfg = config.config
|
||||
cfg.update(job_cfg)
|
||||
if cfg.output is None:
|
||||
cfg.output = osp.join('work_dirs', temp_module_name)
|
||||
return cfg
|
||||
@@ -0,0 +1,41 @@
|
||||
import logging
|
||||
import os
|
||||
import sys
|
||||
|
||||
|
||||
class AverageMeter(object):
|
||||
"""Computes and stores the average and current value
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
self.val = None
|
||||
self.avg = None
|
||||
self.sum = None
|
||||
self.count = None
|
||||
self.reset()
|
||||
|
||||
def reset(self):
|
||||
self.val = 0
|
||||
self.avg = 0
|
||||
self.sum = 0
|
||||
self.count = 0
|
||||
|
||||
def update(self, val, n=1):
|
||||
self.val = val
|
||||
self.sum += val * n
|
||||
self.count += n
|
||||
self.avg = self.sum / self.count
|
||||
|
||||
|
||||
def init_logging(rank, models_root):
|
||||
if rank == 0:
|
||||
log_root = logging.getLogger()
|
||||
log_root.setLevel(logging.INFO)
|
||||
formatter = logging.Formatter("Training: %(asctime)s-%(message)s")
|
||||
handler_file = logging.FileHandler(os.path.join(models_root, "training.log"))
|
||||
handler_stream = logging.StreamHandler(sys.stdout)
|
||||
handler_file.setFormatter(formatter)
|
||||
handler_stream.setFormatter(formatter)
|
||||
log_root.addHandler(handler_file)
|
||||
log_root.addHandler(handler_stream)
|
||||
log_root.info('rank_id: %d' % rank)
|
||||
Reference in New Issue
Block a user