Open KiritoHugh opened 4 years ago
Hi @KiritoHugh Thanks for your attention on our paper. This is my teacher config based on https://github.com/layumi/Person_reID_baseline_pytorch DukeMTMC-reID
PCB: false
angle: false
balance: false
batchsize: 8
color_jitter: false
data_dir: ../DukeMTMC-reID/pytorch
droprate: 0.75
erasing_p: 0
fp16: false
gpu_ids: '0'
h: 256
lr: 0.01
name: Duke_batch8_lr0.010000_p0.00_d0.75
stride: 1
train_all: true
use_dense: false
w: 128
pool: avg
nclass: 702
MSMT-17
PCB: false
angle: false
balance: false
batchsize: 8
color_jitter: false
data_dir: ../MSMT17_V1/pytorch
droprate: 0.5
erasing_p: 0
fp16: false
gpu_ids: '0'
h: 256
lr: 0.01
name: MSMT_batch8_lr0.010000_p0.00_d0.50
stride: 1
train_all: true
use_dense: false
w: 128
pool: avg
nclass: 1041
I used the same hyperparameters setting for DukeMTMC and MSMT17 as the setting in Market1501 training config file. And I used the pretrained Resnet model from https://kaiyangzhou.github.io/deep-person-reid/MODEL_ZOO as the teacher models.
Although I got a pretty nice result in Market1501, the result in the other two datasets are really poor(even both poorer than their teacher models).
I also post the training loss log of DukeMTMC below.
Your reply would be highly appreciated!