File size: 3,620 Bytes
483de47 |
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 |
# ------------------------------------------------------------------------
# Copyright (c) 2022 megvii-research. All Rights Reserved.
# ------------------------------------------------------------------------
# Modified from Deformable DETR (https://github.com/fundamentalvision/Deformable-DETR)
# Copyright (c) 2020 SenseTime. All Rights Reserved.
# ------------------------------------------------------------------------
# Modified from DETR (https://github.com/facebookresearch/detr)
# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
# ------------------------------------------------------------------------
"""
Train and eval functions used in main.py
"""
import math
import os
import sys
from typing import Iterable
import torch
import util.misc as utils
from datasets.data_prefetcher import data_dict_to_cuda
def train_one_epoch_mot(model: torch.nn.Module, criterion: torch.nn.Module,
data_loader: Iterable, optimizer: torch.optim.Optimizer,
device: torch.device, epoch: int, max_norm: float = 0):
model.train()
criterion.train()
metric_logger = utils.MetricLogger(delimiter=" ")
metric_logger.add_meter('lr', utils.SmoothedValue(window_size=1, fmt='{value:.6f}'))
# metric_logger.add_meter('class_error', utils.SmoothedValue(window_size=1, fmt='{value:.2f}'))
metric_logger.add_meter('grad_norm', utils.SmoothedValue(window_size=1, fmt='{value:.2f}'))
header = 'Epoch: [{}]'.format(epoch)
print_freq = 10
# for samples, targets in metric_logger.log_every(data_loader, print_freq, header):
for data_dict in metric_logger.log_every(data_loader, print_freq, header):
data_dict = data_dict_to_cuda(data_dict, device)
outputs = model(data_dict)
loss_dict = criterion(outputs, data_dict)
# print("iter {} after model".format(cnt-1))
weight_dict = criterion.weight_dict
losses = sum(loss_dict[k] * weight_dict[k] for k in loss_dict.keys() if k in weight_dict)
# reduce losses over all GPUs for logging purposes
loss_dict_reduced = utils.reduce_dict(loss_dict)
# loss_dict_reduced_unscaled = {f'{k}_unscaled': v
# for k, v in loss_dict_reduced.items()}
loss_dict_reduced_scaled = {k: v * weight_dict[k]
for k, v in loss_dict_reduced.items() if k in weight_dict}
losses_reduced_scaled = sum(loss_dict_reduced_scaled.values())
loss_value = losses_reduced_scaled.item()
if not math.isfinite(loss_value):
print("Loss is {}, stopping training".format(loss_value))
print(loss_dict_reduced)
sys.exit(1)
optimizer.zero_grad()
losses.backward()
if max_norm > 0:
grad_total_norm = torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm)
else:
grad_total_norm = utils.get_total_grad_norm(model.parameters(), max_norm)
optimizer.step()
# metric_logger.update(loss=loss_value, **loss_dict_reduced_scaled, **loss_dict_reduced_unscaled)
metric_logger.update(loss=loss_value, **loss_dict_reduced_scaled)
# metric_logger.update(class_error=loss_dict_reduced['class_error'])
metric_logger.update(lr=optimizer.param_groups[0]["lr"])
metric_logger.update(grad_norm=grad_total_norm)
# gather the stats from all processes
metric_logger.synchronize_between_processes()
print("Averaged stats:", metric_logger)
return {k: meter.global_avg for k, meter in metric_logger.meters.items()}
|