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)
mse mean e96c22a36e305681d7fed415a5a949fa0c1791c9 Thai Thien 2020-05-10 18:32:02
no fix 7bd97e91de5d7c2d307407287c82e60e893c0c92 Thai Thien 2020-05-10 18:22:45
no fix fc20ae6922c2e53f7d37f4228fb921894cd78eab Thai Thien 2020-05-10 18:19:59
t9 d8ef865ea602670548e897d8b7ac4c925cc9b393 Thai Thien 2020-05-10 18:19:30
test with L1 loss 6492b65da4bdf6351b661f39b6bce6f08d37f17c Thai Thien 2020-05-10 18:10:49
H2 1d6d11b2eeecb67dd7d329e38de61b872870a9aa Thai Thien 2020-05-06 17:42:52
do something with l1 loss 5268c4fc163bb512f293fbac381a64a75c4fe462 Thai Thien 2020-05-06 17:32:45
typo b7b8e2303ce99b2196402ec93334598598e71e5a Thai Thien 2020-05-05 17:32:31
increase epoch 67f89509e4294c4310b42e790425c82279df16b3 Thai Thien 2020-05-05 17:25:17
H1 t8 1c692b37536bd72abaa0995001d3a396b82bc2f0 Thai Thien 2020-05-05 17:24:56
OMP_NUM_THREADS=5 ac76431f8ca1ada27ca7ffdaa289996baee064c1 Thai Thien 2020-05-05 17:14:41
train da020f46703ca4fae867a09960593ef6818b4a91 Thai Thien 2020-05-05 17:05:06
batch_size 10 6b6478b9570f9133489c8a9427a857c14a14fb13 Thai Thien 2020-05-02 11:26:38
change dataset preprocess for t3 267d31931fd80178714812fced9f86a27479d54f Thai Thien 2020-05-02 11:23:19
t3 e2a1c6f6e8a6d34b36aa8d6c86a5509bc8d41cdd Thai Thien 2020-05-02 11:20:05
batch size 20 ea5737c694cb2967cb041db99ca391d06a66100d Thai Thien 2020-05-02 11:19:18
ccn v7 shb fixed 15 4b28c4049c4b25a6afeb563864f76907a1e2360e Thai Thien 2020-05-02 11:16:14
shb 7af5a7bb61d8858a2f6ef36d44844506cde917c3 Thai Thien 2020-05-02 11:14:03
batch đéo 62e1e9124b7e611c6749c1544c60687abd30895e Thai Thien 2020-05-01 17:10:44
sanity check 67ff41702b4da7956c1c2d67b9c8c40fd65d866d Thai Thien 2020-05-01 17:08:52
Commit e96c22a36e305681d7fed415a5a949fa0c1791c9 - mse mean
mse mean, l1 mean
Author: Thai Thien
Author date (UTC): 2020-05-10 18:32
Committer name: Thai Thien
Committer date (UTC): 2020-05-10 18:32
Parent(s): 7bd97e91de5d7c2d307407287c82e60e893c0c92
Signing key:
Tree: 1286c01c98ec18f3484be02c87f237585c6cfab4
File Lines added Lines deleted
train_compact_cnn.py 6 0
train_script/CCNN/ccnn_v7_t11_sha.sh 4 4
train_script/CCNN/sha_fixed/ccnn_v7_t11_shb_fixed.sh 3 3
File train_compact_cnn.py changed (mode: 100644) (index a3b34b2..664051f)
... ... if __name__ == "__main__":
89 89 if args.loss_fn == "MSE": if args.loss_fn == "MSE":
90 90 loss_fn = nn.MSELoss(reduction='sum').to(device) loss_fn = nn.MSELoss(reduction='sum').to(device)
91 91 print("use MSELoss") print("use MSELoss")
92 elif args.loss_fn == "MSEmean":
93 loss_fn = nn.MSELoss(reduction='mean').to(device)
94 print("use MSELoss with reduction mean")
92 95 elif args.loss_fn == "L1": elif args.loss_fn == "L1":
93 96 loss_fn = nn.L1Loss(reduction='sum').to(device) loss_fn = nn.L1Loss(reduction='sum').to(device)
94 97 print("use L1Loss") print("use L1Loss")
98 elif args.loss_fn == "L1mean":
99 loss_fn = nn.L1Loss(reduction='mean').to(device)
100 print("use L1Loss with reduction mean")
95 101
96 102 optimizer = torch.optim.Adam(model.parameters(), args.lr, optimizer = torch.optim.Adam(model.parameters(), args.lr,
97 103 weight_decay=args.decay) weight_decay=args.decay)
File train_script/CCNN/ccnn_v7_t11_sha.sh copied from file train_script/CCNN/sha_fixed/ccnn_v7_t4_sha_fixed.sh (similarity 62%) (mode: 100644) (index bfa388b..0f0d4dc)
1 task="ccnn_v7_t4_sha_fixed"
1 task="ccnn_v7_t11_sha"
2 2
3 3 CUDA_VISIBLE_DEVICES=6 OMP_NUM_THREADS=5 HTTPS_PROXY="http://10.60.28.99:86" nohup python train_compact_cnn.py \ CUDA_VISIBLE_DEVICES=6 OMP_NUM_THREADS=5 HTTPS_PROXY="http://10.60.28.99:86" nohup python train_compact_cnn.py \
4 4 --task_id $task \ --task_id $task \
5 --note "l1 loss" \
5 --note "MSE mean with sha" \
6 6 --model "CompactCNNV7" \ --model "CompactCNNV7" \
7 --input /data/rnd/thient/thient_data/shanghaitech_with_people_density_map/ShanghaiTech_fixed_sigma/part_A \
7 --input /data/rnd/thient/thient_data/ShanghaiTech/part_A \
8 8 --lr 1e-4 \ --lr 1e-4 \
9 9 --decay 1e-4 \ --decay 1e-4 \
10 --loss_fn L1 \
10 --loss_fn MSEmean \
11 11 --datasetname shanghaitech_20p \ --datasetname shanghaitech_20p \
12 12 --epochs 1001 > logs/$task.log & --epochs 1001 > logs/$task.log &
13 13
File train_script/CCNN/sha_fixed/ccnn_v7_t11_shb_fixed.sh copied from file train_script/CCNN/sha_fixed/ccnn_v7_t4_shb_fixed.sh (similarity 84%) (mode: 100644) (index 33d73f2..63b0901)
1 task="ccnn_v7_t4_shb_fixed"
1 task="ccnn_v7_t11_shb_fixed"
2 2
3 3 CUDA_VISIBLE_DEVICES=7 OMP_NUM_THREADS=5 HTTPS_PROXY="http://10.60.28.99:86" nohup python train_compact_cnn.py \ CUDA_VISIBLE_DEVICES=7 OMP_NUM_THREADS=5 HTTPS_PROXY="http://10.60.28.99:86" nohup python train_compact_cnn.py \
4 4 --task_id $task \ --task_id $task \
5 --note "test about l1 loss" \
5 --note "mse mean" \
6 6 --model "CompactCNNV7" \ --model "CompactCNNV7" \
7 7 --input /data/rnd/thient/thient_data/shanghaitech_with_people_density_map/ShanghaiTech_fixed_sigma/part_B \ --input /data/rnd/thient/thient_data/shanghaitech_with_people_density_map/ShanghaiTech_fixed_sigma/part_B \
8 8 --lr 1e-4 \ --lr 1e-4 \
9 9 --decay 1e-4 \ --decay 1e-4 \
10 10 --batch_size 20 \ --batch_size 20 \
11 --loss_fn L1 \
11 --loss_fn MSEmean \
12 12 --datasetname shanghaitech_rnd \ --datasetname shanghaitech_rnd \
13 13 --epochs 901 > logs/$task.log & --epochs 901 > logs/$task.log &
14 14
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