Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

load data to transfer learning #14

Open
Ricardo-Fellini4 opened this issue Dec 6, 2023 · 0 comments
Open

load data to transfer learning #14

Ricardo-Fellini4 opened this issue Dec 6, 2023 · 0 comments

Comments

@Ricardo-Fellini4
Copy link

==========Options============
means: [0.485, 0.456, 0.406]
stds: [0.229, 0.224, 0.225]
gpu: 2
exp_name: Totaltext
num_workers: 0
batch_size: 6
max_epoch: 250
start_epoch: 0
lr: 0.001
cuda: True
output_dir: output
input_size: 640
max_annotation: 2000
adj_num: 4
num_points: 20
use_hard: True
load_memory: False
scale: 1
grad_clip: 25
dis_threshold: 0.35
cls_threshold: 0.875
approx_factor: 0.004
know: False
knownet: MixNet_FSNet_M
know_resume: /kaggle/working/Mixnet/model/Totaltext_mid/MixNet_FSNet_M_622.pth
resume: None
mgpu: False
save_dir: ./model/
vis_dir: ./vis/
log_dir: ./logs/
loss: CrossEntropyLoss
pretrain: False
verbose: True
viz: False
lr_adjust: fix
stepvalues: []
weight_decay: 0.0
gamma: 0.1
momentum: 0.9
optim: Adam
save_freq: 5
display_freq: 10
viz_freq: 50
log_freq: 10000
val_freq: 1000
net: FSNet_M
mid: True
embed: False
onlybackbone: False
rescale: 255.0
test_size: [640, 960]
checkepoch: 1070
img_root: None
device: cuda
=============End=============
MixNet backbone parameter size: 29339968
load pretrain weight from /kaggle/working/Mixnet/pretrained/triHRnet_Synth_weight.pth.
Start training MixNet.
Epoch: 0 : LR = [0.001]
Traceback (most recent call last):
File "/kaggle/working/Mixnet/train_mixNet.py", line 418, in
main()
File "/kaggle/working/Mixnet/train_mixNet.py", line 399, in main
train(model, train_loader, criterion, scheduler, optimizer, epoch)
File "/kaggle/working/Mixnet/train_mixNet.py", line 99, in train
input_dict = _parse_data(inputs)
File "/kaggle/working/Mixnet/train_mixNet.py", line 74, in _parse_data
input_dict['edge_field'] = inputs[10]
IndexError: list index out of range

i have cut the MixNet_FSNet_M_622.pth to transfer learning and get an error when loading the data, although i have same format when testing

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant