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 v7 with ssim loss 40079e5354eef95e0e89cf23a7f2025ee362e232 Thai Thien 2020-04-30 12:16:19
local 1d4e08754bd493e76cf09076de7c76adf1a30a0a Thai Thien 2020-04-30 12:10:15
mse-ssim loss function 052de7c879bff7690a7cfc1905c8376bf8605c45 Thai Thien 2020-04-30 11:41:24
delete misinformation note ca07533d585def04eec086685f2e72eacc330ddc Thai Thien 2020-04-29 16:59:47
typo 3505077301af5349665f12121862db2512ad450a Thai Thien 2020-04-29 16:59:03
change, adapt, survive 6755c8375302af2146cb63adc967631d53a7b1c8 Thai Thien 2020-04-29 16:48:10
gpu 861ec0d41cea2eec359c6ddfe207e1ed6b583369 Thai Thien 2020-04-28 18:08:11
ccnn_v7_t4 a84f63e64fe8b31fe22c94d383de5ed4e1a27fe4 Thai Thien 2020-04-28 18:07:33
2500 d37516f53d21f3dfc05143ba5ffda80fc5a07825 Thai Thien 2020-04-28 17:56:57
change max epoch 246ae30e6dd2b4a15b7dc70a3dc05592ac1c48f2 Thai Thien 2020-04-28 17:55:23
h1 t3 h1 t4 fbcd13dd240e06a982a1ce48f27cd1d542a26b63 Thai Thien 2020-04-28 17:53:06
h1 96204cb5262500020371637741131d24e3fa91d0 Thai Thien 2020-04-27 17:35:51
typo adfb213c2564bc90b8b69811469534b004808644 Thai Thien 2020-04-27 17:17:58
batch size 8 for shb c90fa9a5d725a1ef0d29ed23f947ee05b9aa7894 Thai Thien 2020-04-27 17:10:34
change proxy 30cd53782eb17b416c471502f1e6c6e9975a644b Thai Thien 2020-04-27 17:06:28
experiment with CCNN when we max pooling after merge c8e8daec89ee71c2f30e30cf3030298ee7073e56 Thai Thien 2020-04-27 16:52:50
refactor train_compact_cnn 9d1ecece2382b79a98e6cf2d4579ae68172dbb6a Thai Thien 2020-04-27 16:35:47
we add head experiment 82a25e6b89945609486cbafc433eaea20dcdee39 Thai Thien 2020-04-27 16:23:50
CompactCNNV3 7de3766d085ebdbdf82b024eb517568dd82d8d6d Thai Thien 2020-04-27 16:23:20
no_norm da3c84dca19b0d281082679d88af3b9d27165bfe Thai Thien 2020-04-25 17:32:45
Commit 40079e5354eef95e0e89cf23a7f2025ee362e232 - ccnn v7 with ssim loss
Author: Thai Thien
Author date (UTC): 2020-04-30 12:16
Committer name: Thai Thien
Committer date (UTC): 2020-04-30 12:16
Parent(s): 5988cacadee8ce228537d3cdef39a1e8fcab71d0
Signing key:
Tree: 94d304c8f99acd6c77e61d0970a7e75ca22f1fd6
File Lines added Lines deleted
train_script/CCNN/ssim_exp/ccnn_v7_ssim_t1_shb.sh 6 5
train_script/CCNN/ssim_exp/ccnn_v7_ssim_t2_shb.sh 7 6
train_script/CCNN/ssim_exp/ccnn_v7_ssim_t3_shb.sh 15 0
train_script/CCNN/ssim_exp/ccnn_v7_ssim_t4_shb.sh 6 5
File train_script/CCNN/ssim_exp/ccnn_v7_ssim_t1_shb.sh copied from file train_script/CCNN/ccnn_v7_t2_shb.sh (similarity 59%) (mode: 100644) (index afed0fd..9fb20bf)
1 task="ccnn_v7_t2_shb"
1 task="ccnn_v7_ssim_t1_shb"
2 2
3 3 CUDA_VISIBLE_DEVICES=4 HTTPS_PROXY="http://10.60.28.99:86" nohup python train_compact_cnn.py \ CUDA_VISIBLE_DEVICES=4 HTTPS_PROXY="http://10.60.28.99:86" nohup python train_compact_cnn.py \
4 4 --task_id $task \ --task_id $task \
5 --note "v3 that only max pooling after concat 3 branch, with norm" \
5 --note "1e-4" \
6 6 --model "CompactCNNV7" \ --model "CompactCNNV7" \
7 7 --input /data/rnd/thient/thient_data/ShanghaiTech/part_B \ --input /data/rnd/thient/thient_data/ShanghaiTech/part_B \
8 8 --lr 1e-4 \ --lr 1e-4 \
9 9 --decay 1e-4 \ --decay 1e-4 \
10 --batch_size 8 \
11 --datasetname shanghaitech_keepfull \
12 --epochs 2001 > logs/$task.log &
10 --use_ssim \
11 --batch_size 20 \
12 --datasetname shanghaitech_more_rnd \
13 --epochs 901 > logs/$task.log &
13 14
14 15 echo logs/$task.log # for convenience echo logs/$task.log # for convenience
File train_script/CCNN/ssim_exp/ccnn_v7_ssim_t2_shb.sh copied from file train_script/CCNN/ccnn_v7_t5_shb.sh (similarity 51%) (mode: 100644) (index f5225ee..4353272)
1 task="ccnn_v7_t5_shb"
1 task="ccnn_v7_ssim_t2_shb"
2 2
3 CUDA_VISIBLE_DEVICES=1 HTTPS_PROXY="http://10.60.28.99:86" nohup python train_compact_cnn.py \
3 CUDA_VISIBLE_DEVICES=5 HTTPS_PROXY="http://10.60.28.99:86" nohup python train_compact_cnn.py \
4 4 --task_id $task \ --task_id $task \
5 --note "v3 that only max pooling after concat 3 branch, with norm" \
5 --note "1e-5" \
6 6 --model "CompactCNNV7" \ --model "CompactCNNV7" \
7 7 --input /data/rnd/thient/thient_data/ShanghaiTech/part_B \ --input /data/rnd/thient/thient_data/ShanghaiTech/part_B \
8 --lr 2e-5 \
9 --decay 1e-4 \
8 --lr 1e-5 \
9 --decay 1e-5 \
10 --use_ssim \
10 11 --batch_size 20 \ --batch_size 20 \
11 12 --datasetname shanghaitech_more_rnd \ --datasetname shanghaitech_more_rnd \
12 --epochs 1001 > logs/$task.log &
13 --epochs 901 > logs/$task.log &
13 14
14 15 echo logs/$task.log # for convenience echo logs/$task.log # for convenience
File train_script/CCNN/ssim_exp/ccnn_v7_ssim_t3_shb.sh added (mode: 100644) (index 0000000..54288af)
1 task="ccnn_v7_ssim_t3_shb"
2
3 CUDA_VISIBLE_DEVICES=6 HTTPS_PROXY="http://10.60.28.99:86" nohup python train_compact_cnn.py \
4 --task_id $task \
5 --note "1e-5 keepfull" \
6 --model "CompactCNNV7" \
7 --input /data/rnd/thient/thient_data/ShanghaiTech/part_B \
8 --lr 1e-5 \
9 --decay 1e-5 \
10 --use_ssim \
11 --batch_size 20 \
12 --datasetname shanghaitech_keepfull \
13 --epochs 601 > logs/$task.log &
14
15 echo logs/$task.log # for convenience
File train_script/CCNN/ssim_exp/ccnn_v7_ssim_t4_shb.sh copied from file train_script/CCNN/ccnn_v7_t2_shb.sh (similarity 53%) (mode: 100644) (index afed0fd..7e276d0)
1 task="ccnn_v7_t2_shb"
1 task="ccnn_v7_ssim_t4_shb"
2 2
3 CUDA_VISIBLE_DEVICES=4 HTTPS_PROXY="http://10.60.28.99:86" nohup python train_compact_cnn.py \
3 CUDA_VISIBLE_DEVICES=7 HTTPS_PROXY="http://10.60.28.99:86" nohup python train_compact_cnn.py \
4 4 --task_id $task \ --task_id $task \
5 --note "v3 that only max pooling after concat 3 branch, with norm" \
5 --note "1e-4 keepfull" \
6 6 --model "CompactCNNV7" \ --model "CompactCNNV7" \
7 7 --input /data/rnd/thient/thient_data/ShanghaiTech/part_B \ --input /data/rnd/thient/thient_data/ShanghaiTech/part_B \
8 8 --lr 1e-4 \ --lr 1e-4 \
9 9 --decay 1e-4 \ --decay 1e-4 \
10 --batch_size 8 \
10 --use_ssim \
11 --batch_size 20 \
11 12 --datasetname shanghaitech_keepfull \ --datasetname shanghaitech_keepfull \
12 --epochs 2001 > logs/$task.log &
13 --epochs 601 > logs/$task.log &
13 14
14 15 echo logs/$task.log # for convenience echo logs/$task.log # for convenience
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