File size: 5,836 Bytes
83d8d3c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 |
import logging
import os
import time
from typing import List
import torch
from eval import verification
from torch import distributed
from torch.utils.tensorboard import SummaryWriter
from utils.utils_logging import AverageMeter
class CallBackVerification(object):
def __init__(self, val_targets, rec_prefix, summary_writer=None, image_size=(112, 112), wandb_logger=None):
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
self.wandb_logger = wandb_logger
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 self.wandb_logger:
import wandb
self.wandb_logger.log(
{
f"Acc/val-Acc1 {self.ver_name_list[i]}": acc1,
f"Acc/val-Acc2 {self.ver_name_list[i]}": acc2,
# f'Acc/val-std1 {self.ver_name_list[i]}': std1,
# f'Acc/val-std2 {self.ver_name_list[i]}': acc2,
}
)
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, start_step=0, 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.start_step: int = start_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
time_now = time.time()
time_sec = int(time_now - self.time_start)
time_sec_avg = time_sec / (global_step - self.start_step + 1)
eta_sec = time_sec_avg * (self.total_step - global_step - 1)
time_for_end = eta_sec / 3600
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 %.6f 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 %.6f 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()
|