dtennant/reid_baseline_with_syncbn

Reimplementation of Bag of Tricks and A Strong Baseline for Deep Person Re-identification

A Modified reid_baseline supporting Multi-GPU and SyncBN training

Original repo here

However, the original repo uses ignite for training and saving the model, which is incompatible with model using SyncBN, So I reimplement the baseline without the use of ignite.(???)

Some code in this repo is borrowed from the original one.

Usage

1. Clone the repo using git clone
2. Compile the code for Cython accelerated evaluation code cd evaluate/eval_cylib && make
3. the SyncBN module is pure pytorch implementation, so no need to compile once you have pytorch.
4. Modify the training config in configs folder.
5. Start training:

# training with only one GPU
CUDA_VISIBLE_DEVICES=1 python main.py -c configs/debug.yml
# testing with one GPU
CUDA_VISIBLE_DEVICES=1 python main.py -t -c configs/debug.yml TEST.WEIGHT /path/to/saved/weights

# training with multi-GPU
CUDA_VISIBLE_DEVICES=1,2 python main.py -c configs/debug_multi-gpu.yml
# testing with multi-GPU
CUDA_VISIBLE_DEVICES=1,2 python main.py -t -c configs/debug_multi-gpu.yml TEST.WEIGHT /path/to/saved/weights

# fp16 training
CUDA_VISIBLE_DEVICES=1 python main.py -c configs/debug.yml SOLVER.FP16 True

Result

I only trained the model with 30 epoch, so the model may not be fully converged.

Note that the Resnet50 model is trained with Warmup, Random erasing augmentation, Last stride=1 and BNNeck.

Result training with one GPU

2019-07-06 13:43:29,884 reid_baseline.eval INFO: Validation Result:
2019-07-06 13:43:29,885 reid_baseline.eval INFO: CMC Rank-1: 89.55%
2019-07-06 13:43:29,885 reid_baseline.eval INFO: CMC Rank-5: 96.76%
2019-07-06 13:43:29,885 reid_baseline.eval INFO: CMC Rank-10: 98.28%
2019-07-06 13:43:29,885 reid_baseline.eval INFO: mAP: 74.50%
2019-07-06 13:43:29,885 reid_baseline.eval INFO: --------------------
2019-07-06 13:45:40,783 reid_baseline.eval INFO: ReRanking Result:
2019-07-06 13:45:40,783 reid_baseline.eval INFO: CMC Rank-1: 92.67%
2019-07-06 13:45:40,783 reid_baseline.eval INFO: CMC Rank-5: 96.41%
2019-07-06 13:45:40,784 reid_baseline.eval INFO: CMC Rank-10: 97.48%
2019-07-06 13:45:40,784 reid_baseline.eval INFO: mAP: 90.00%
2019-07-06 13:45:40,784 reid_baseline.eval INFO: --------------------

Result training with multi-GPU

2019-07-06 14:24:32,171 reid_baseline.eval INFO: Use multi gpu to inference
2019-07-06 14:25:41,053 reid_baseline.eval INFO: Validation Result:
2019-07-06 14:25:41,054 reid_baseline.eval INFO: CMC Rank-1: 87.44%
2019-07-06 14:25:41,054 reid_baseline.eval INFO: CMC Rank-5: 96.17%
2019-07-06 14:25:41,054 reid_baseline.eval INFO: CMC Rank-10: 97.54%
2019-07-06 14:25:41,054 reid_baseline.eval INFO: mAP: 72.13%
2019-07-06 14:25:41,054 reid_baseline.eval INFO: --------------------
2019-07-06 14:27:23,449 reid_baseline.eval INFO: ReRanking Result:
2019-07-06 14:27:23,450 reid_baseline.eval INFO: CMC Rank-1: 91.30%
2019-07-06 14:27:23,450 reid_baseline.eval INFO: CMC Rank-5: 95.64%
2019-07-06 14:27:23,450 reid_baseline.eval INFO: CMC Rank-10: 96.79%
2019-07-06 14:27:23,450 reid_baseline.eval INFO: mAP: 88.92%
2019-07-06 14:27:23,450 reid_baseline.eval INFO: --------------------

Result training with FP16

2019-07-07 12:29:20,649 reid_baseline.eval INFO: Validation Result:
2019-07-07 12:29:20,650 reid_baseline.eval INFO: CMC Rank-1: 90.44%
2019-07-07 12:29:20,650 reid_baseline.eval INFO: CMC Rank-5: 96.47%
2019-07-07 12:29:20,650 reid_baseline.eval INFO: CMC Rank-10: 98.13%
2019-07-07 12:29:20,650 reid_baseline.eval INFO: mAP: 75.88%
2019-07-07 12:29:20,650 reid_baseline.eval INFO: --------------------
2019-07-07 12:31:01,269 reid_baseline.eval INFO: ReRanking Result:
2019-07-07 12:31:01,270 reid_baseline.eval INFO: CMC Rank-1: 93.14%
2019-07-07 12:31:01,270 reid_baseline.eval INFO: CMC Rank-5: 96.26%
2019-07-07 12:31:01,270 reid_baseline.eval INFO: CMC Rank-10: 97.12%
2019-07-07 12:31:01,270 reid_baseline.eval INFO: mAP: 90.22%
2019-07-07 12:31:01,270 reid_baseline.eval INFO: --------------------

Result training on Market1501, testing on Partial-iLIDS

2019-07-08 18:15:14,299 reid_baseline.eval INFO: Validation Result:
2019-07-08 18:15:14,299 reid_baseline.eval INFO: CMC Rank-1: 45.38%
2019-07-08 18:15:14,300 reid_baseline.eval INFO: CMC Rank-3: 57.14%
2019-07-08 18:15:14,300 reid_baseline.eval INFO: mAP: 55.76%
2019-07-08 18:15:14,300 reid_baseline.eval INFO: --------------------
2019-07-08 18:15:14,678 reid_baseline.eval INFO: ReRanking Result:
2019-07-08 18:15:14,678 reid_baseline.eval INFO: CMC Rank-1: 28.57%
2019-07-08 18:15:14,678 reid_baseline.eval INFO: CMC Rank-3: 48.74%
2019-07-08 18:15:14,678 reid_baseline.eval INFO: mAP: 42.62%
2019-07-08 18:15:14,679 reid_baseline.eval INFO: --------------------

Result on VeRI-WILD small test set

2019-07-12 22:47:57,250 reid_baseline.eval INFO: Validation Result:
2019-07-12 22:47:57,250 reid_baseline.eval INFO: CMC Rank-1: 90.43%
2019-07-12 22:47:57,250 reid_baseline.eval INFO: CMC Rank-5: 96.85%
2019-07-12 22:47:57,250 reid_baseline.eval INFO: CMC Rank-10: 98.19%
2019-07-12 22:47:57,250 reid_baseline.eval INFO: mAP: 74.27%
2019-07-12 22:47:57,251 reid_baseline.eval INFO: --------------------
2019-07-12 22:57:10,006 reid_baseline.eval INFO: ReRanking Result:
2019-07-12 22:57:10,006 reid_baseline.eval INFO: CMC Rank-1: 89.66%
2019-07-12 22:57:10,006 reid_baseline.eval INFO: CMC Rank-5: 95.45%
2019-07-12 22:57:10,006 reid_baseline.eval INFO: CMC Rank-10: 97.46%
2019-07-12 22:57:10,007 reid_baseline.eval INFO: mAP: 77.42%
2019-07-12 22:57:10,007 reid_baseline.eval INFO: --------------------

Result on VeRI776

2019-07-13 11:35:12,402 reid_baseline.eval INFO: Validation Result:
2019-07-13 11:35:12,402 reid_baseline.eval INFO: CMC Rank-1: 95.65%
2019-07-13 11:35:12,402 reid_baseline.eval INFO: CMC Rank-5: 97.91%
2019-07-13 11:35:12,403 reid_baseline.eval INFO: CMC Rank-10: 99.11%
2019-07-13 11:35:12,403 reid_baseline.eval INFO: mAP: 77.15%
2019-07-13 11:35:12,403 reid_baseline.eval INFO: --------------------
2019-07-13 11:36:02,050 reid_baseline.eval INFO: ReRanking Result:
2019-07-13 11:36:02,050 reid_baseline.eval INFO: CMC Rank-1: 97.20%
2019-07-13 11:36:02,050 reid_baseline.eval INFO: CMC Rank-5: 97.85%
2019-07-13 11:36:02,050 reid_baseline.eval INFO: CMC Rank-10: 98.75%
2019-07-13 11:36:02,050 reid_baseline.eval INFO: mAP: 81.74%
2019-07-13 11:36:02,050 reid_baseline.eval INFO: --------------------

reid_baseline_with_syncbn's Issues

multi-GPU training problem

HI, when i trained the model with multi-gpu training, the model didn't start training after more than 30 minutes, and i don't konw why, could you give me some suggestions? Thank you!

2019-09-25 14:56:36,708 reid_baseline.train INFO: More than one gpu used, convert model to use SyncBN.
2019-09-25 14:56:40,504 reid_baseline.train INFO: Using pytorch SyncBN implementation
2019-09-25 14:56:40,535 reid_baseline.train INFO: Trainer Built

lr rate of bias when training on multi gpus

Hi, should lr rate of bias be multiplied the num of gpus in the following codes ?

def make_optimizer(cfg, model, num_gpus=1):
    params = []
    for key, value in model.named_parameters():
        if not value.requires_grad:
            continue
        lr = cfg.SOLVER.BASE_LR * num_gpus
        # linear scaling rule
        weight_decay = cfg.SOLVER.WEIGHT_DECAY
        if "bias" in key:
            lr = cfg.SOLVER.BASE_LR * cfg.SOLVER.BIAS_LR_FACTOR
            weight_decay = cfg.SOLVER.WEIGHT_DECAY_BIAS
        params += [{"params": [value], "lr": lr, "weight_decay": weight_decay}]
    if cfg.SOLVER.OPTIMIZER_NAME == 'SGD':
        optimizer = getattr(torch.optim, cfg.SOLVER.OPTIMIZER_NAME)(params, momentum=cfg.SOLVER.MOMENTUM)
    else:
        optimizer = getattr(torch.optim, cfg.SOLVER.OPTIMIZER_NAME)(params)
    return optimizer

VeRi-wild数据集问题？

您好，我是reID刚入门的学生，在运行您的代码时发现VeRi-Wild数据集似乎与VeRi-776数据集有点差别，似乎将VeRi-Wild做了处理，图片进行了重新命名，请问，是否可以提供一下脚本文件，谢谢，已start完毕

train on VeRI776 dataset

您好，可以提一下怎么用veri776数据集训练这个模型么，十分感谢！

no module amp_C?

How can I solve this problem?I have already install the apex,but when I run main.py,this problem happended.

Why should lr need to multiply numgpus in make optimizer?

i dont understand why during mutiGPUS trainning ,lr should multiply numgpus,thx!

please help me how to use this model

l want to use it test two picture,can you help me,thank you

多gpu训练问题?

你好
多卡运行到这就卡着不动了
单卡的脚本没问题
2022-06-19 19:09:40,134 reid_baseline.train INFO: Trainer Built

我只修改了这个

MODEL:
PRETRAIN_PATH: '/home/wgj233/.cache/torch/checkpoints/resnet50-19c8e357.pth'

INPUT:
SIZE_TRAIN: [384, 384]
SIZE_TEST: [384, 384]
PIXEL_MEAN: [0.5, 0.5, 0.5]
PIXEL_STD: [0.5, 0.5, 0.5]
PROB: 0.5 # random horizontal flip
RE_PROB: 0.5 # random erasing
PADDING: 0

DATASETS:
NAMES: 'FVRID_sum' # 'market1501'
DATA_PATH: '/home/wgj233/Datasets/FVRID_sum' # '#/home/zbc/data/market1501'
TRAIN_PATH: 'train_foggy' # 'bounding_box_train'
QUERY_PATH: 'query_foggy' # 'query'
GALLERY_PATH: 'gallery_foggy' # 'bounding_box_test'

DATALOADER:
SAMPLER: 'softmax_triplet'
NUM_INSTANCE: 8
NUM_WORKERS: 4

SOLVER:
OPTIMIZER_NAME: 'Adam'
MAX_EPOCHS: 30
BASE_LR: 0.0001
BIAS_LR_FACTOR: 1
WEIGHT_DECAY: 0.0005
WEIGHT_DECAY_BIAS: 0.0005
IMS_PER_BATCH: 16

STEPS: [20, 30, 45, 60, 75, 90, 105, 120, 135, 150, 165, 180, 195, 210, 225, 240, 255]
GAMMA: 0.6

WARMUP_FACTOR: 0.01
WARMUP_ITERS: 10
WARMUP_METHOD: 'linear'

CHECKPOINT_PERIOD: 1
LOG_PERIOD: 100
EVAL_PERIOD: 1

TEST:
IMS_PER_BATCH: 16
DEBUG: True
WEIGHT: "path"
MULTI_GPU: True

OUTPUT_DIR: "/home/wgj233/reid_baseline_with_syncbn-master/outputs/debug_multi-gpu"

How to train ResNet on person and vehicle ReID datasets like MSMT17 and VeRi?

Hi, I want to train ResNet-50 or 34 for person and vehicle on MSMT17 and VeRi dataset.

1- Can I train ResNet for two classes and use both datasets at the same time or I can train only and it's not suitable for two classes?
2- What is the training process?
2- Can I also use ResNet-18 or ResNet-34 in the same way to increase the speed?

My ultimate goal is to train ResNet ReID model for the person and car. and then combine with this project (https://github.com/GeekAlexis/FastMOT) for Fast multi-object tracking.

How I can achieve this goal?

veri776准确率

您好，我也用这个训练了veri776数据集（all tricks with center loss，resnet_ibn_a），训练了40个epoch，验证集准确率90以上，但是用test.py测试的时候，map只有3%，rank也很低。
我想知道您训练的模型类型，以及epoch数，还有用哪个预训练参数，非常想达到您这样的准确率！
谢谢回复，非常感谢！

请教下为什么多卡的精度比单卡低了这么多？

RT

车辆ReID如何训练？

你好，请问一下在数据集VeRI776上如何训练？是直接把数据集扔进去吗？

中断训练后，如何恢复训练呢？

我在train.py中load之后，出现：RuntimeError: Error(s) in loading state_dict for DataParallelWithCallback:
Missing key(s) in state_dict: "module.base.conv1.weight", "module.base.bn1.weight", "module.base.bn1.bias", "module.base.bn1.running_mean", "module.base.bn1.running_var", "module.base.layer1.0.conv1.weight", "module.base.layer1.0.bn1.weight", "module.base.layer1.0.bn1.bias", "module.base.layer1.0.bn1.running_mean", "module.base.layer1.0.bn1.running_var", "module.base.layer1.0.conv2.weight", "module.base.layer1.0.bn2.weight", "module.base.layer1.0.bn2.bias", "module.base.layer1.0.bn2.running_mean", "module.base.layer1.0.bn2.running_var", "module.base.layer1.0.conv3.weight", "module.base.layer1.0.bn3.weight", "module.base.layer1.0.bn3.bias", "module.base.layer1.0.bn3.running_mean", "module.base.layer1.0.bn3.running_var", "module.base.layer1.0.downsample.0.weight", "module.base.layer1.0.downsample.1.weight", "module.base.layer1.0.downsample.1.bias", "module.base.layer1.0.downsample.1.running_mean", "module.base.layer1.0.downsample.1.running_var", "module.base.layer1.1.conv1.weight", "module.base.layer1.1.bn1.weight", "module.base.layer1.1.bn1.bias", "module.base.layer1.1.bn1.running_mean", "module.base.layer1.1.bn1.running_var", "module.base.layer1.1.conv2.weight", "module.base.layer1.1.bn2.weight", "module.base.layer1.1.bn2.bias", "module.base.layer1.1.bn2.running_mean", "module.base.layer1.1.bn2.running_var", "module.base.layer1.1.conv3.weight", "module.base.layer1.1.bn3.weight", "module.base.layer1.1.bn3.bias", "module.base.layer1.1.bn3.running_mean", "module.base.layer1.1.bn3.running_var", "module.base.layer1.2.conv1.weight", "module.base.layer1.2.bn1.weight", "module.base.layer1.2.bn1.bias", "module.base.layer1.2.bn1.running_mean", "module.base.layer1.2.bn1.running_var", "module.base.layer1.2.conv2.weight", "module.base.layer1.2.bn2.weight", "module.base.layer1.2.bn2.bias", "module.base.layer1.2.bn2.running_mean", "module.base.layer1.2.bn2.running_var", "module.base.layer1.2.conv3.weight", "module.base.layer1.2.bn3.weight", "module.base.layer1.2.bn3.bias", "module.base.layer1.2.bn3.running_mean", "module.base.layer1.2.bn3.running_var", "module.base.layer2.0.conv1.weight", "module.base.layer2.0.bn1.weight", "module.base.layer2.0.bn1.bias", "module.base.layer2.0.bn1.running_mean", "module.base.layer2.0.bn1.running_var", "module.base.layer2.0.conv2.weight", "module.base.layer2.0.bn2.weight", "module.base.layer2.0.bn2.bias", "module.base.layer2.0.bn2.running_mean", "module.base.layer2.0.bn2.running_var", "module.base.layer2.0.conv3.weight", "module.base.layer2.0.bn3.weight", "module.base.layer2.0.bn3.bias", "module.base.layer2.0.bn3.running_mean", "module.base.layer2.0.bn3.running_var", "module.base.layer2.0.downsample.0.weight", "module.base.layer2.0.downsample.1.weight", "module.base.layer2.0.downsample.1.bias", "module.base.layer2.0.downsample.1.running_mean", "module.base.layer2.0.downsample.1.running_var", "module.base.layer2.1.conv1.weight", "module.base.layer2.1.bn1.weight", "module.base.layer2.1.bn1.bias", "module.base.layer2.1.bn1.running_mean", "module.base.layer2.1.bn1.running_var", "module.base.layer2.1.conv2.weight", "module.base.layer2.1.bn2.weight", "module.base.layer2.1.bn2.bias", "module.base.layer2.1.bn2.running_mean", "module.base.layer2.1.bn2.running_var", "module.base.layer2.1.conv3.weight", "module.base.layer2.1.bn3.weight", "module.base.layer2.1.bn3.bias", "module.base.layer2.1.bn3.running_mean", "module.base.layer2.1.bn3.running_var", "module.base.layer2.2.conv1.weight", "module.base.layer2.2.bn1.weight", "module.base.layer2.2.bn1.bias", "module.base.layer2.2.bn1.running_mean", "module.base.layer2.2.bn1.running_var", "module.base.layer2.2.conv2.weight", "module.base.layer2.2.bn2.weight", "module.base.layer2.2.bn2.bias", "module.base.layer2.2.bn2.running_mean", "module.base.layer2.2.bn2.running_var", "module.base.layer2.2.conv3.weight", "module.base.layer2.2.bn3.weight", "module.base.layer2.2.bn3.bias", "module.base.layer2.2.bn3.running_mean", "module.base.layer2.2.bn3.running_var", "module.base.layer2.3.conv1.weight", "module.base.layer2.3.bn1.weight", "module.base.layer2.3.bn1.bias", "module.base.layer2.3.bn1.running_mean", "module.base.layer2.3.bn1.running_var", "module.base.layer2.3.conv2.weight", "module.base.layer2.3.bn2.weight", "module.base.layer2.3.bn2.bias", "module.base.layer2.3.bn2.running_mean", "module.base.layer2.3.bn2.running_var", "module.base.layer2.3.conv3.weight", "module.base.layer2.3.bn3.weight", "module.base.layer2.3.bn3.bias", "module.base.layer2.3.bn3.running_mean", "module.base.layer2.3.bn3.running_var", "module.base.layer3.0.conv1.weight", "module.base.layer3.0.bn1.weight", "module.base.layer3.0.bn1.bias", "module.base.layer3.0.bn1.running_mean", "module.base.layer3.0.bn1.running_var", "module.base.layer3.0.conv2.weight", "module.base.layer3.0.bn2.weight", "module.base.layer3.0.bn2.bias", "module.base.layer3.0.bn2.running_mean", "module.base.layer3.0.bn2.running_var", "module.base.layer3.0.conv3.weight", "module.base.layer3.0.bn3.weight", "module.base.layer3.0.bn3.bias", "module.base.layer3.0.bn3.running_mean", "module.base.layer3.0.bn3.running_var", "module.base.layer3.0.downsample.0.weight", "module.base.layer3.0.downsample.1.weight", "module.base.layer3.0.downsample.1.bias", "module.base.layer3.0.downsample.1.running_mean", "module.base.layer3.0.downsample.1.running_var", "module.base.layer3.1.conv1.weight", "module.base.layer3.1.bn1.weight", "module.base.layer3.1.bn1.bias", "module.base.layer3.1.bn1.running_mean", "module.base.layer3.1.bn1.running_var", "module.base.layer3.1.conv2.weight", "module.base.layer3.1.bn2.weight", "module.base.layer3.1.bn2.bias", "module.base.layer3.1.bn2.running_mean", "module.base.layer3.1.bn2.running_var", "module.base.layer3.1.conv3.weight", "module.base.layer3.1.bn3.weight", "module.base.layer3.1.bn3.bias", "module.base.layer3.1.bn3.running_mean", "module.base.layer3.1.bn3.running_var", "module.base.layer3.2.conv1.weight", "module.base.layer3.2.bn1.weight", "module.base.layer3.2.bn1.bias", "module.base.layer3.2.bn1.running_mean", "module.base.layer3.2.bn1.running_var", "module.base.layer3.2.conv2.weight", "module.base.layer3.2.bn2.weight", "module.base.layer3.2.bn2.bias", "module.base.layer3.2.bn2.running_mean", "module.base.layer3.2.bn2.running_var", "module.base.layer3.2.conv3.weight", "module.base.layer3.2.bn3.weight", "module.base.layer3.2.bn3.bias", "module.base.layer3.2.bn3.running_mean", "module.base.layer3.2.bn3.running_var", "module.base.layer3.3.conv1.weight", "module.base.layer3.3.bn1.weight", "module.base.layer3.3.bn1.bias", "module.base.layer3.3.bn1.running_mean", "module.base.layer3.3.bn1.running_var", "module.base.layer3.3.conv2.weight", "module.base.layer3.3.bn2.weight", "module.base.layer3.3.bn2.bias", "module.base.layer3.3.bn2.running_mean", "module.base.layer3.3.bn2.running_var", "module.base.layer3.3.conv3.weight", "module.base.layer3.3.bn3.weight", "module.base.layer3.3.bn3.bias", "module.base.layer3.3.bn3.running_mean", "module.base.layer3.3.bn3.running_var", "module.base.layer3.4.conv1.weight", "module.base.layer3.4.bn1.weight", "module.base.layer3.4.bn1.bias", "module.base.layer3.4.bn1.running_mean", "module.base.layer3.4.bn1.running_var", "module.base.layer3.4.conv2.weight", "module.base.layer3.4.bn2.weight", "module.base.layer3.4.bn2.bias", "module.base.layer3.4.bn2.running_mean", "module.base.layer3.4.bn2.running_var", "module.base.layer3.4.conv3.weight", "module.base.layer3.4.bn3.weight", "module.base.layer3.4.bn3.bias", "module.base.layer3.4.bn3.running_mean", "module.base.layer3.4.bn3.running_var", "module.base.layer3.5.conv1.weight", "module.base.layer3.5.bn1.weight", "module.base.layer3.5.bn1.bias", "module.base.layer3.5.bn1.running_mean", "module.base.layer3.5.bn1.running_var", "module.base.layer3.5.conv2.weight", "module.base.layer3.5.bn2.weight", "module.base.layer3.5.bn2.bias", "module.base.layer3.5.bn2.running_mean", "module.base.layer3.5.bn2.running_var", "module.base.layer3.5.conv3.weight", "module.base.layer3.5.bn3.weight", "module.base.layer3.5.bn3.bias", "module.base.layer3.5.bn3.running_mean", "module.base.layer3.5.bn3.running_var", "module.base.layer4.0.conv1.weight", "module.base.layer4.0.bn1.weight", "module.base.layer4.0.bn1.bias", "module.base.layer4.0.bn1.running_mean", "module.base.layer4.0.bn1.running_var", "module.base.layer4.0.conv2.weight", "module.base.layer4.0.bn2.weight", "module.base.layer4.0.bn2.bias", "module.base.layer4.0.bn2.running_mean", "module.base.layer4.0.bn2.running_var", "module.base.layer4.0.conv3.weight", "module.base.layer4.0.bn3.weight", "module.base.layer4.0.bn3.bias", "module.base.layer4.0.bn3.running_mean", "module.base.layer4.0.bn3.running_var", "module.base.layer4.0.downsample.0.weight", "module.base.layer4.0.downsample.1.weight", "module.base.layer4.0.downsample.1.bias", "module.base.layer4.0.downsample.1.running_mean", "module.base.layer4.0.downsample.1.running_var", "module.base.layer4.1.conv1.weight", "module.base.layer4.1.bn1.weight", "module.base.layer4.1.bn1.bias", "module.base.layer4.1.bn1.running_mean", "module.base.layer4.1.bn1.running_var", "module.base.layer4.1.conv2.weight", "module.base.layer4.1.bn2.weight", "module.base.layer4.1.bn2.bias", "module.base.layer4.1.bn2.running_mean", "module.base.layer4.1.bn2.running_var", "module.base.layer4.1.conv3.weight", "module.base.layer4.1.bn3.weight", "module.base.layer4.1.bn3.bias", "module.base.layer4.1.bn3.running_mean", "module.base.layer4.1.bn3.running_var", "module.base.layer4.2.conv1.weight", "module.base.layer4.2.bn1.weight", "module.base.layer4.2.bn1.bias", "module.base.layer4.2.bn1.running_mean", "module.base.layer4.2.bn1.running_var", "module.base.layer4.2.conv2.weight", "module.base.layer4.2.bn2.weight", "module.base.layer4.2.bn2.bias", "module.base.layer4.2.bn2.running_mean", "module.base.layer4.2.bn2.running_var", "module.base.layer4.2.conv3.weight", "module.base.layer4.2.bn3.weight", "module.base.layer4.2.bn3.bias", "module.base.layer4.2.bn3.running_mean", "module.base.layer4.2.bn3.running_var", "module.bottleneck.weight", "module.bottleneck.bias", "module.bottleneck.running_mean", "module.bottleneck.running_var", "module.classifier.weight".
Unexpected key(s) in state_dict: "state", "param_groups".
我需要做些什么吗

使用VehicleID进行训练

Vehicle数据集的QUERY和GALLERY怎么选呢？我个人把其中一个测试集里的800个id分别选出一个作为QUERY，其他的作为GALLERY。然后我对所有图片按照格式重命名为：“00000001_c0000_00000005.jpg”。当我对比使用veri.yml训练的时候，提示如下：
ValueError: Error initializing torch.distributed using env:// rendezvous: environment variable RANK expected, but not set .
如果我注释掉FP16，代码会一直停留在等待状态（后来发现改小batch_size就好了）但我发现训练速度有点慢呀，3块1080Ti训练一个epoch需要1个多小时，这速度正常吗？

test on windows

Hello,Can it be tested on windows？I test in windows,but always report Permission denied: 'configs'，The full error report is：
Traceback (most recent call last):
File "main.py", line 186, in
main()
File "main.py", line 59, in main
train(args)
File "main.py", line 63, in train
cfg.merge_from_file(args.config_file)
File "E:\Anaconda\lib\site-packages\yacs\config.py", line 211, in merge_from_file
with open(cfg_filename, "r") as f:
PermissionError: [Errno 13] Permission denied: 'configs'

(base) E:\code\reid_baseline_with_syncbn-master>ion denied: 'configs'
'ion' 不是内部或外部命令，也不是可运行的程序
或批处理文件。

(base) E:\code\reid_baseline_with_syncbn-master>
(base) E:\code\reid_baseline_with_syncbn-master>(base) E:\code\reid_baseline_with_syncbn-master>
此时不应有 E:\code\reid_baseline_with_syncbn-master。
(base) E:\code\reid_baseline_with_syncbn-master>python main.py -c configs / debug.yml
Traceback (most recent call last):
File "main.py", line 186, in
main()
File "main.py", line 59, in main
train(args)
File "main.py", line 63, in train
cfg.merge_from_file(args.config_file)
File "E:\Anaconda\lib\site-packages\yacs\config.py", line 211, in merge_from_file
with open(cfg_filename, "r") as f:
PermissionError: [Errno 13] Permission denied: 'configs'

veri-wild参数？

这数据集实在太大了，普通实验室跑不起，老哥能分享下训练这个数据集的处理脚本吗？
要训练的话，你还需要把数据集中的图片重命名成0001_c014_00001.jpg（vehicleid_cameraid_imageid.jpg）。

老哥能分享下训veri_wild的参数吗

这数据集实在是太太太太大了，小实验室跑不起
老哥能分享下训练这个数据集的参数或者pth文件吗

regarding veri 776

The results are really good. Just wanted to make sure - if you have followed the Veri 776 evaluation as mentioned in the paper. that is, to remove the same camera retrievals from the test set ?

VeRI776

By tuning the parameters and using focal loss, the mAP in VeRi776 can be up to 80.0%.

Pre-trained model

Hi, Where I can find the VeRi pre-trained model for the only test?