can not get satisfiying result using default parameters

[JiaXiaofei0909]

Hello I test the FID using public model and the output is similar to paper result. However, I train the model the FID is much bigger. I do not know what happened. The option is as follows
----------------- Options ---------------
QS_mode: global
batch_size: 1
beta1: 0.5
beta2: 0.999
checkpoints_dir: ./checkpoints
continue_train: False
crop_size: 256
dataroot: /cache/data/horse2zebra [default: ./datasets/horse2zebra]
dataset_mode: unaligned
direction: AtoB
display_env: main
display_freq: 400
display_id: 0 [default: None]
display_ncols: 4
display_port: 8097
display_server: http://localhost
display_winsize: 256
easy_label: experiment_name
epoch: latest
epoch_count: 1
evaluation_freq: 5000
flip_equivariance: False
gan_mode: lsgan
gpu_ids: 0
init_gain: 0.02
init_type: xavier
input_nc: 3
isTrain: True [default: None]
lambda_GAN: 1.0
lambda_NCE: 1.0
load_size: 286
lr: 0.0002
lr_decay_iters: 50
lr_policy: linear
max_dataset_size: inf
model: qs
n_epochs: 200
n_epochs_decay: 200
n_layers_D: 3
name: horse2zebra_QSAttn_global [default: horse2zebra_qsattn_global]
nce_T: 0.07
nce_idt: True
nce_layers: 0,4,8,12,16
ndf: 64
netD: basic
netF: mlp_sample
netF_nc: 256
netG: resnet_9blocks
ngf: 64
no_antialias: False
no_antialias_up: False
no_dropout: True
no_flip: False
no_html: False
normD: instance
normG: instance
num_patches: 256
num_threads: 4
output_nc: 3
phase: train
pool_size: 0
preprocess: resize_and_crop
pretrained_name: None
print_freq: 100
save_by_iter: False
save_epoch_freq: 5
save_latest_freq: 5000
save_path: ./1.query-selected-attention/
serial_batches: False
suffix:
update_html_freq: 1000
verbose: False
----------------- End -------------------

[haoren55555]

@JiaXiaofei0909 sorry to bother, I also tested the pretrained model, but I found its FID score is somehow higher than that of paper. Did you get the same score as the paper?

[JiaXiaofei0909]

much higher. I do not know what happened.

[sapphire497]

I tested the model every epoch, the metrics listed in paper are the best among the epoches.

[JiaXiaofei0909]

no much higher than paper 在 2022年5月18日星期三，niceshot ***@***.***> 写道：

…

@JiaXiaofei0909 <https://github.com/JiaXiaofei0909> sorry to bother, I also tested the pretrained model, but I found its FID score is somehow higher than that of paper. Did you get the same score as the paper? — Reply to this email directly, view it on GitHub <#6 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AZF4WBDE5266EQS47ST5CTLVKSSJRANCNFSM5WAR6P6Q> . You are receiving this because you were mentioned.Message ID: ***@***.***>

[hd201708010401]

I met the same problem