List of commits:
Subject Hash Author Date (UTC)
t12 t13 914f8d4bc63f4d626ceaeaeddf11ad2d8668be5d Thai Thien 2020-06-07 04:22:17
data_flow fix load_data_shanghaitech_more_rnd f593543b86fd2aba890dd3fc8d26121c3ba5d5e1 Thai Thien 2020-06-07 04:09:40
1e-4 88dcc2e1340f0cfc20b0dca73bc374d742278a5a Thai Thien 2020-06-07 03:42:38
try to increase batch size and learning rate 55f5eedf8eea9b4df20b7f2107d9e4c89c3787bf Thai Thien 2020-06-07 03:42:29
t9 gpu 99153ea3c20ef26c651004d083086e7ea2c9452e Thai Thien 2020-06-06 18:08:00
t9 c4305310d8376b1814c1c1ed77fa46919f02a898 Thai Thien 2020-06-06 18:07:01
t7 t8 d62a031e9b4506f7d8173906615cc6f32d0b7a4c Thai Thien 2020-06-06 18:06:13
_fixed 7c44ea2806c5b9e9b85cd496d2a3e400c437acd2 Thai Thien 2020-06-06 17:54:40
bigtail shb 6d7bcddf7613ab19c4022c533a9a6d8eb2cd4776 Thai Thien 2020-06-06 17:53:51
bigtail4 56 0a2cf847de58fc032ee966632af94cdef1f16245 Thai Thien 2020-06-05 09:36:40
bigtail 4 t3 t4 1dd1c61db8f34d6562909f9d37f0ca18fc91fa55 Thai Thien 2020-06-04 14:59:52
bigtal4 1a434051955cfaeda47780ab801924cfc9c22f94 Thai Thien 2020-06-02 18:00:43
l1 1e-4 2ea7293b60423704648df4a610a012f1da822ec9 Thai Thien 2020-05-29 16:38:44
fix log epoch 84e8beff8e305f81de7a05add2e58dcfe389ede5 Thai Thien 2020-05-29 16:38:31
skip evaluate on training set a38d5731a9d6209bc98a9cca0ad023b4798c68d5 Thai Thien 2020-05-28 16:15:29
t7 ac1f0d71c2d3e0a01241622c639a9090a5b3c427 Thai Thien 2020-05-28 15:55:56
rename 4e9754c3dff98577616d3f043f7f260aeef40ac6 Thai Thien 2020-05-27 15:54:54
not use gpu2 8324400a3d65c58cfdd5a63b0a940217f3277769 Thai Thien 2020-05-27 15:54:11
remove call loss in eval 06f13484f24b85b12cab15e5af16db4d086db497 Thai Thien 2020-05-27 15:52:44
expermient, bug fix e83e7e058b6f1d7ec1237677a2d4770f1f788ea0 Thai Thien 2020-05-27 15:43:58
Commit 914f8d4bc63f4d626ceaeaeddf11ad2d8668be5d - t12 t13
Author: Thai Thien
Author date (UTC): 2020-06-07 04:22
Committer name: Thai Thien
Committer date (UTC): 2020-06-07 04:22
Parent(s): f593543b86fd2aba890dd3fc8d26121c3ba5d5e1
Signer:
Signing key:
Signing status: N
Tree: 09ffedf0ce27e42f7d655c2ce11f2ffe46affe18
File Lines added Lines deleted
train_script/meow_one/big_tail/bigtail4_t12_shb.sh 3 3
train_script/meow_one/big_tail/bigtail4_t13_shb.sh 3 3
File train_script/meow_one/big_tail/bigtail4_t12_shb.sh copied from file train_script/debug/a1/bigtail4_t10_shb_fixed.sh (similarity 86%) (mode: 100644) (index 5f1bb7a..5942948)
1 task="bigtail4_t10_shb_fixed"
1 task="bigtail4_t12_shb_fixed"
2 2
3 3 CUDA_VISIBLE_DEVICES=4 OMP_NUM_THREADS=2 PYTHONWARNINGS="ignore" HTTPS_PROXY="http://10.60.28.99:86" nohup python experiment_main.py \ CUDA_VISIBLE_DEVICES=4 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 $task \
5 5 --note "bigtail4" \ --note "bigtail4" \
6 6 --model "BigTail4" \ --model "BigTail4" \
7 7 --input /data/rnd/thient/thient_data/shanghaitech_with_people_density_map/ShanghaiTech_fixed_sigma/part_B \ --input /data/rnd/thient/thient_data/shanghaitech_with_people_density_map/ShanghaiTech_fixed_sigma/part_B \
8 --lr 1e-4 \
8 --lr 2e-5 \
9 9 --decay 1e-4 \ --decay 1e-4 \
10 10 --loss_fn "MSE" \ --loss_fn "MSE" \
11 11 --skip_train_eval \ --skip_train_eval \
12 12 --batch_size 20 \ --batch_size 20 \
13 13 --datasetname shanghaitech_more_random \ --datasetname shanghaitech_more_random \
14 --epochs 400 > logs/$task.log &
14 --epochs 600 > logs/$task.log &
15 15
16 16 echo logs/$task.log # for convenience echo logs/$task.log # for convenience
File train_script/meow_one/big_tail/bigtail4_t13_shb.sh copied from file train_script/meow_one/big_tail/bigtail4_t8_shb.sh (similarity 84%) (mode: 100644) (index 260ebf4..dcd264a)
1 task="bigtail4_t8_shb_fixed"
1 task="bigtail4_t13_shb_fixed"
2 2
3 3 CUDA_VISIBLE_DEVICES=5 OMP_NUM_THREADS=2 PYTHONWARNINGS="ignore" HTTPS_PROXY="http://10.60.28.99:86" nohup python experiment_main.py \ CUDA_VISIBLE_DEVICES=5 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 \
 
... ... CUDA_VISIBLE_DEVICES=5 OMP_NUM_THREADS=2 PYTHONWARNINGS="ignore" HTTPS_PROXY="ht
9 9 --decay 1e-4 \ --decay 1e-4 \
10 10 --loss_fn "L1" \ --loss_fn "L1" \
11 11 --skip_train_eval \ --skip_train_eval \
12 --batch_size 10 \
12 --batch_size 20 \
13 13 --datasetname shanghaitech_more_random \ --datasetname shanghaitech_more_random \
14 --epochs 800 > logs/$task.log &
14 --epochs 600 > logs/$task.log &
15 15
16 16 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