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_l1 sum 5dfcc9fd26945222bfed282daa3de323b389398d Thai Thien 2020-07-14 16:22:38
fix import mse_loss and l1_loss 5054eb05834a449760c2e7dcfe30fe61e4762b16 Thai Thien 2020-07-14 03:21:41
fix load_data_shanghaitech_non_overlap 2040aa2dd124831e75ad4b204c0ab447a2c9a936 Thai Thien 2020-07-13 11:09:55
ccnn_v7_t11_shb 93bf2d399e132456059b2b5709775a115231756e Thai Thien 2020-07-13 10:52:00
shuffle non-overlap, msel1 loss 8ef0edfc8b459326b4c7a7044bc6dc6d30fd7fd6 Thai Thien 2020-07-13 10:48:54
MSEL1Loss e2f4dc7bb1bee096ae17101331e0f221d05ba1af Thai Thien 2020-07-13 09:34:11
t10 2f443c077e186901cdbe2c9faf27d2f37905a775 Thai Thien 2020-07-12 18:57:39
t10 87d6dd6e7debf45e16953e39471c13071039fa59 Thai Thien 2020-07-12 18:57:17
fix 45617766d305df841b7b0af3c2f6204a2e6d4f46 Thai Thien 2020-07-12 18:45:01
ccnn_v7_t8_shb 9f921d9415b89d9c9d4f4e8ef9b65b32663e06ec Thai Thien 2020-07-12 16:00:42
fix shanghaitech_non_overlap 9332377476d2d7524822ba98e2321c75be90f709 Thai Thien 2020-07-12 15:57:08
fix flatten collate bb25738b0510915712a17daeb590b668b446b0be Thai Thien 2020-07-12 15:17:14
ccnn_v7_t6_shb c4f59ee01cbdab3f506302588b9667cd1c9f6411 Thai Thien 2020-07-12 14:19:03
do not *4 root if we have flatten augmentation list c534aa36bf314ea32643e92231194bd020d7bf1f Thai Thien 2020-07-12 14:19:00
train val split shb 61581543d16aaa2640bdee0b3573e41d1843770d Thai Thien 2020-07-12 14:06:25
flatten collate c04708ae0defc81dbf441395e1d27de6a1d598fc Thai Thien 2020-07-12 13:54:01
travis remove nightly d4b0c714823046bbafcd3c816d56f7079c76d126 Thai Thien 2020-07-12 13:27:55
travis e6368ec3102e01f1bdc71a80a78f0db3617d7e08 Thai Thien 2020-07-12 12:33:21
flatten_collate 1e460396875c205c42de27449f56e73cd4ec10e0 Thai Thien 2020-07-12 12:23:40
train val split test ratio to 0.1 5091da3f0b45d875a38c2829e4fec5e61116e869 Thai Thien 2020-07-11 03:14:26
Commit 5dfcc9fd26945222bfed282daa3de323b389398d - mse_l1 sum
Author: Thai Thien
Author date (UTC): 2020-07-14 16:22
Committer name: Thai Thien
Committer date (UTC): 2020-07-14 16:22
Parent(s): 5054eb05834a449760c2e7dcfe30fe61e4762b16
Signing key:
Tree: e2b6c72695c65a2389408bda8e3ef6aa6cfb3743
File Lines added Lines deleted
train_script/CCNN/group1/g1_ccnn_v7_t1_shb.sh 5 5
train_script/CCNN/group1/g1_ccnn_v7_t2_shb.sh 4 4
train_script/CCNN/group1/g1_ccnn_v7_t3_shb.sh 6 6
train_script/CCNN/group1/idea.md 5 0
File train_script/CCNN/group1/g1_ccnn_v7_t1_shb.sh copied from file train_script/CCNN/ccnn_v7_t11_shb.sh (similarity 70%) (mode: 100644) (index b4bbd51..1ac60eb)
1 task="ccnn_v7_t11_shb"
1 task="g1_ccnn_v7_t1_shb"
2 2
3 CUDA_VISIBLE_DEVICES=4 OMP_NUM_THREADS=3 PYTHONWARNINGS="ignore" HTTPS_PROXY="http://10.60.28.99:86" nohup python experiment_main.py \
3 CUDA_VISIBLE_DEVICES=1 OMP_NUM_THREADS=2 PYTHONWARNINGS="ignore" HTTPS_PROXY="http://10.60.28.99:86" nohup python experiment_main.py \
4 4 --task_id $task \ --task_id $task \
5 --note "try MEANL1 loss" \
5 --note "mse l1 mean, with -4 lr and decay" \
6 6 --model "CompactCNNV7" \ --model "CompactCNNV7" \
7 7 --input /data/rnd/thient/thient_data/shanghaitech_with_people_density_map/ShanghaiTech_3/part_B \ --input /data/rnd/thient/thient_data/shanghaitech_with_people_density_map/ShanghaiTech_3/part_B \
8 --lr 1e-5 \
9 --decay 1e-5 \
8 --lr 1e-4 \
9 --decay 1e-4 \
10 10 --batch_size 4 \ --batch_size 4 \
11 11 --loss_fn "MSEL1Mean" \ --loss_fn "MSEL1Mean" \
12 12 --datasetname shanghaitech_non_overlap \ --datasetname shanghaitech_non_overlap \
File train_script/CCNN/group1/g1_ccnn_v7_t2_shb.sh copied from file train_script/CCNN/ccnn_v7_t11_shb.sh (similarity 71%) (mode: 100644) (index b4bbd51..2242784)
1 task="ccnn_v7_t11_shb"
1 task="g1_ccnn_v7_t2_shb"
2 2
3 CUDA_VISIBLE_DEVICES=4 OMP_NUM_THREADS=3 PYTHONWARNINGS="ignore" HTTPS_PROXY="http://10.60.28.99:86" nohup python experiment_main.py \
3 CUDA_VISIBLE_DEVICES=2 OMP_NUM_THREADS=2 PYTHONWARNINGS="ignore" HTTPS_PROXY="http://10.60.28.99:86" nohup python experiment_main.py \
4 4 --task_id $task \ --task_id $task \
5 --note "try MEANL1 loss" \
5 --note "mse l1 sum, with -5 lr and decay" \
6 6 --model "CompactCNNV7" \ --model "CompactCNNV7" \
7 7 --input /data/rnd/thient/thient_data/shanghaitech_with_people_density_map/ShanghaiTech_3/part_B \ --input /data/rnd/thient/thient_data/shanghaitech_with_people_density_map/ShanghaiTech_3/part_B \
8 8 --lr 1e-5 \ --lr 1e-5 \
9 9 --decay 1e-5 \ --decay 1e-5 \
10 10 --batch_size 4 \ --batch_size 4 \
11 --loss_fn "MSEL1Mean" \
11 --loss_fn "MSEL1Sum" \
12 12 --datasetname shanghaitech_non_overlap \ --datasetname shanghaitech_non_overlap \
13 13 --skip_train_eval \ --skip_train_eval \
14 14 --epochs 1201 > logs/$task.log & --epochs 1201 > logs/$task.log &
File train_script/CCNN/group1/g1_ccnn_v7_t3_shb.sh copied from file train_script/CCNN/ccnn_v7_t11_shb.sh (similarity 66%) (mode: 100644) (index b4bbd51..f8ffeed)
1 task="ccnn_v7_t11_shb"
1 task="g1_ccnn_v7_t3_shb"
2 2
3 CUDA_VISIBLE_DEVICES=4 OMP_NUM_THREADS=3 PYTHONWARNINGS="ignore" HTTPS_PROXY="http://10.60.28.99:86" nohup python experiment_main.py \
3 CUDA_VISIBLE_DEVICES=3 OMP_NUM_THREADS=2 PYTHONWARNINGS="ignore" HTTPS_PROXY="http://10.60.28.99:86" nohup python experiment_main.py \
4 4 --task_id $task \ --task_id $task \
5 --note "try MEANL1 loss" \
5 --note "mse l1 sum, with -4 lr and decay" \
6 6 --model "CompactCNNV7" \ --model "CompactCNNV7" \
7 7 --input /data/rnd/thient/thient_data/shanghaitech_with_people_density_map/ShanghaiTech_3/part_B \ --input /data/rnd/thient/thient_data/shanghaitech_with_people_density_map/ShanghaiTech_3/part_B \
8 --lr 1e-5 \
9 --decay 1e-5 \
8 --lr 1e-4 \
9 --decay 1e-4 \
10 10 --batch_size 4 \ --batch_size 4 \
11 --loss_fn "MSEL1Mean" \
11 --loss_fn "MSEL1Sum" \
12 12 --datasetname shanghaitech_non_overlap \ --datasetname shanghaitech_non_overlap \
13 13 --skip_train_eval \ --skip_train_eval \
14 14 --epochs 1201 > logs/$task.log & --epochs 1201 > logs/$task.log &
File train_script/CCNN/group1/idea.md added (mode: 100644) (index 0000000..cc1f5dc)
1 # MSE_L1 loss
2 we create MSE-L1 Loss, let see how it work through
3
4 # non overlap data augmentation
5 Yeah overlap is not working because it is pixel wise. What about non-overlapping.
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