hahattpro / crowd_counting_framework (public) (License: Unspecified) (since 2020-12-23) (hash sha1)
backupfrom https://github.com/ttpro1995/crowd_counting_framework
Clone URLs: https://rocketgit.com/user/hahattpro/crowd_counting_framework ssh://rocketgit@ssh.rocketgit.com/user/hahattpro/crowd_counting_framework git://git.rocketgit.com/user/hahattpro/crowd_counting_framework
debug/a-1 develop feature/add_can_adcrowdnet feature/add_context_aware_network feature/attn_can_adcrowd_simple feature/cache_dataloader feature/compact_cnn feature/compare_with_original_count feature/dataloader_not_divide_8 feature/debug_viz feature/documentation feature/improve_density_gen feature/improve_loss_fn feature/loader_full_and_augment feature/refactor-dataflow feature/refactor_ccnn_basecode feature/save_best feature/simple_cometml feature/train_context_aware_network_on_shtA feature/train_dev_test_split hotfix/fix_visualize_data_loader master meow_exp server-training with_apex
List of commits:
Subject Hash Author Date (UTC)
ccnn_v1_t4_scheduler, also change lr milestones c27beba80ebf7686dc7f046b95d5e2739b6dae66 Thai Thien 2020-03-12 16:23:02
add load_data_shanghaitech_keepfull_and_crop 5af55c5b483263683db80bcf4b870bfbb241d668 Thai Thien 2020-03-12 16:19:19
change on how it log epoch adcb2aa917f02d4b5d567a9b70f08ec519f896d1 Thai Thien 2020-03-11 17:32:35
fix the milestone 4e8c048ff8db59cbedc819e4df2a48094568fc2c Thai Thien 2020-03-11 17:10:03
add COMET_ML_API 7fbec715d751544bcdafb34a686602839a2696de Thai Thien 2020-03-11 17:04:19
fix script name 631c37c068377706ae2cad4513baeea7e62ae0b5 Thai Thien 2020-03-11 16:59:24
intergrate comet ml into compact cnn 058e90a617acb76a7788e6a5d44f52563342490b Thai Thien 2020-03-11 16:57:17
something ?! fff52ff87af2a90452384a01bd6d6e6c4b91654e Thai Thien 2020-03-11 15:55:04
DilatedCCNNv2 75d2989232a8a68eba9b4920ab2374ac28438e0e Thai Thien 2020-03-10 05:11:12
fix script for ccnn_v2_t1_c2 57928056d13bc9b1f9b11e14dd305005a3a5aeea Thai Thien 2020-03-10 04:56:33
fix trash code 33c406b13b5d45527b05dfb7f4281c3966c6471e Thai Thien 2020-03-10 04:49:52
repair dir in config baf522825f906a3d1fc5524f42a80da33d059640 Thai Thien 2020-03-10 04:45:11
v3 t1 c2 2d4727f47f4262833dca2087fb9e48f0d117e334 Thai Thien 2020-03-10 04:29:23
dilated ccnn v1 t1 7807d7a979353fa84d0b7319820386e93dbe5cc4 Thai Thien 2020-03-09 17:20:58
new ccnn 44a669c1f918be9d74313f29a5dbbc876c29f2fc Thai Thien 2020-03-09 17:16:49
fix script aa331331b12e5b454d372a550524b30a4bebe706 Thai Thien 2020-03-07 18:32:06
try reproduct ccnn with keepfull and lr 1e-5 814c520cbd1bb2d7fd50d2a8d3579d43da79fe60 Thai Thien 2020-03-07 18:30:42
my simple v4 with addition deform cnn at the end 5392aaf6c14fdd910f52096dbb921bed7470c4f7 Thai Thien 2020-03-07 18:15:22
fix the scheduler 77e6737a040f5aa5745b8a8830f5bec12322b10f Thai Thien 2020-03-07 17:46:02
t4 lr 1e-5 acd41ed30c95f63e01a05a6d9929410637852d9e Thai Thien 2020-03-06 19:41:49
Commit c27beba80ebf7686dc7f046b95d5e2739b6dae66 - ccnn_v1_t4_scheduler, also change lr milestones
Author: Thai Thien
Author date (UTC): 2020-03-12 16:23
Committer name: Thai Thien
Committer date (UTC): 2020-03-12 16:23
Parent(s): 41c74ac4b3b4ddab9452bb05bc8f928bbd37caed
Signing key:
Tree: e0e5ea945e5c3895f13fe9f0e9a1fa52e30ef086
File Lines added Lines deleted
train_compact_cnn_lrscheduler.py 1 1
train_script/CCNN/ccnn_v1_t4_scheduler.sh 3 3
File train_compact_cnn_lrscheduler.py changed (mode: 100644) (index 0f5d332..18a72e0)
... ... if __name__ == "__main__":
60 60 optimizer = torch.optim.Adam(model.parameters(), args.lr, optimizer = torch.optim.Adam(model.parameters(), args.lr,
61 61 weight_decay=args.decay) weight_decay=args.decay)
62 62
63 milestones_values = [(20, 1e-4), (50, 5e-5), (100, 1e-5), (150, 5e-6), (200, 1e-6), (250, 1e-7)]
63 milestones_values = [(20, 1e-4), (50, 5e-5), (100, 1e-5), (200, 9e-6), (250, 5e-6), (300, 1e-6)]
64 64 lr_scheduler = PiecewiseLinear(optimizer, param_name="lr", milestones_values=milestones_values) lr_scheduler = PiecewiseLinear(optimizer, param_name="lr", milestones_values=milestones_values)
65 65
66 66 trainer = create_supervised_trainer(model, optimizer, loss_fn, device=device) trainer = create_supervised_trainer(model, optimizer, loss_fn, device=device)
File train_script/CCNN/ccnn_v1_t4_scheduler.sh copied from file train_script/CCNN/ccnn_v1_t3_scheduler.sh (similarity 60%) (mode: 100644) (index 25230f7..08511fb)
1 1 CUDA_VISIBLE_DEVICES=2 HTTPS_PROXY="http://10.30.58.36:81" nohup python train_compact_cnn_lrscheduler.py \ CUDA_VISIBLE_DEVICES=2 HTTPS_PROXY="http://10.30.58.36:81" nohup python train_compact_cnn_lrscheduler.py \
2 --task_id ccnn_v1_t3_scheduler \
2 --task_id ccnn_v1_t4_scheduler \
3 3 --input /data/rnd/thient/thient_data/ShanghaiTech/part_A \ --input /data/rnd/thient/thient_data/ShanghaiTech/part_A \
4 4 --lr 1e-4 \ --lr 1e-4 \
5 5 --decay 0 \ --decay 0 \
6 --datasetname shanghaitech \
7 --epochs 300 > logs/ccnn_v1_t3_scheduler.log &
6 --datasetname shanghaitech_keepfull_and_crop \
7 --epochs 400 > logs/ccnn_v1_t4_scheduler.log &
Hints:
Before first commit, do not forget to setup your git environment:
git config --global user.name "your_name_here"
git config --global user.email "your@email_here"

Clone this repository using HTTP(S):
git clone https://rocketgit.com/user/hahattpro/crowd_counting_framework

Clone this repository using ssh (do not forget to upload a key first):
git clone ssh://rocketgit@ssh.rocketgit.com/user/hahattpro/crowd_counting_framework

Clone this repository using git:
git clone git://git.rocketgit.com/user/hahattpro/crowd_counting_framework

You are allowed to anonymously push to this repository.
This means that your pushed commits will automatically be transformed into a merge request:
... clone the repository ...
... make some changes and some commits ...
git push origin main