List of commits:
Subject Hash Author Date (UTC)
no_norm da3c84dca19b0d281082679d88af3b9d27165bfe Thai Thien 2020-04-25 17:32:45
M4_t3_sha_c_shb d0d61ff74ed23f595d05d6a813c0a93239f61438 Thai Thien 2020-04-25 17:17:56
training script 624ecec7b12641f734e12ee2ebb6158c7c89683a Thai Thien 2020-04-25 17:08:25
clean up trash 05fa10a45e7c4f9d0ba6b80e578a0f934a86121e Thai Thien 2020-04-25 17:08:04
increase epoch sha 96e0315a34286751258902b1e954ea5e43145ee1 Thai Thien 2020-04-23 17:24:53
turn off debug 36a2603484395ed130dd7dcb69c98c7057adf3ec Thai Thien 2020-04-23 17:21:51
chang proxy ce5434adf6002e3c1e14eee8fb50023ba9f1da39 Thai Thien 2020-04-23 17:19:00
fix typo 4f5c034e3fcbd9d3dd66333c7e81db79053c210b Thai Thien 2020-04-23 17:12:23
M4_t3 9ed8f35d94e43d0869d9ee07d98395ed4d4cd3fd Thai Thien 2020-04-23 16:18:49
fix b2235d1abdb20c3e1bfcc0d42870dad4b706babc Thai Thien 2020-04-23 16:13:17
debug 6cda7a90f14c5768be5bfbb9d87a985cae845f4c Thai Thien 2020-04-23 11:27:53
best score checkpoint , timer bb26cec915aa04d68a0dd00911c273542f9b34b5 Thai Thien 2020-04-23 11:16:24
typo 2636cf5b78f062c89196c4f462afc4b72aa39798 Thai Thien 2020-04-19 12:10:51
M4 317900419b7ba25c679dd582a6de5fc00fc764ec Thai Thien 2020-04-19 12:09:51
m4 t2 a02b9610e868f4ba5e64496dc0c861a269f4cb9f Thai Thien 2020-04-17 16:01:39
fix url 358f164d558dab393f65c0829d8d9c37b1437ff3 Thai Thien 2020-04-16 14:32:49
increase epoch 03be68a9e02df1ffa245394ea3096990e8f9d44b Thai Thien 2020-04-16 14:30:15
add load model 044a398d62add2e854b79b0b3c48c961a4a20bb0 Thai Thien 2020-04-16 14:27:43
M4 c960a8e3ddbfb7fc57f3f843fa4184c063cf8cdb Thai Thien 2020-04-16 14:22:37
typo again 3dbe3ce4634b8d4ca30b012851c5b9690b1d88d7 Thai Thien 2020-04-13 15:49:23
Commit da3c84dca19b0d281082679d88af3b9d27165bfe - no_norm
ccnn_v2_t9_sha

ccnn_v2_t10_sha
Author: Thai Thien
Author date (UTC): 2020-04-25 17:32
Committer name: Thai Thien
Committer date (UTC): 2020-04-25 17:32
Parent(s): d0d61ff74ed23f595d05d6a813c0a93239f61438
Signing key:
Tree: 9741a19f1e7a30155ac68db0d6991cafa107a30a
File Lines added Lines deleted
args_util.py 2 0
train_compact_cnn.py 6 1
train_script/CCNN/ccnn_v2_t10_sha.sh 9 0
train_script/CCNN/ccnn_v2_t9_sha.sh 9 0
File args_util.py changed (mode: 100644) (index 5f8c6f4..0edf39f)
... ... def my_args_parse():
96 96 parser.add_argument('--batch_size', action="store", default=1, type=int, parser.add_argument('--batch_size', action="store", default=1, type=int,
97 97 help="only set batch_size > 0 for dataset with image size equal") help="only set batch_size > 0 for dataset with image size equal")
98 98 parser.add_argument('--test', action="store_true", default=False) parser.add_argument('--test', action="store_true", default=False)
99 parser.add_argument('--no_norm', action="store_true", default=False,
100 help="if true, does not use transforms.Normalize in dataloader")
99 101 arg = parser.parse_args() arg = parser.parse_args()
100 102 return arg return arg
101 103
File train_compact_cnn.py changed (mode: 100644) (index 28bd010..966c973)
... ... if __name__ == "__main__":
53 53 test_list = create_image_list(TEST_PATH) test_list = create_image_list(TEST_PATH)
54 54
55 55 # create data loader # create data loader
56 train_loader, val_loader, test_loader = get_dataloader(train_list, None, test_list, dataset_name=dataset_name, batch_size=args.batch_size)
56 train_loader, val_loader, test_loader = get_dataloader(train_list,
57 None,
58 test_list,
59 dataset_name=dataset_name,
60 batch_size=args.batch_size,
61 visualize_mode=args.no_norm)
57 62
58 63 print("len train_loader ", len(train_loader)) print("len train_loader ", len(train_loader))
59 64
File train_script/CCNN/ccnn_v2_t10_sha.sh added (mode: 100644) (index 0000000..bcc1044)
1 CUDA_VISIBLE_DEVICES=6 HTTPS_PROXY="http://10.60.28.99:86" nohup python train_compact_cnn.py \
2 --task_id ccnn_v2_t10_sha \
3 --note "ccnnv2 keep full, try no_norm to see how it work, with e-5 lr" \
4 --input /data/rnd/thient/thient_data/ShanghaiTech/part_A \
5 --no_norm \
6 --lr 1e-5 \
7 --decay 1e-5 \
8 --datasetname shanghaitech_keepfull \
9 --epochs 1500 > logs/ccnn_v2_t10_sha.log &
File train_script/CCNN/ccnn_v2_t9_sha.sh added (mode: 100644) (index 0000000..5e7b8b5)
1 CUDA_VISIBLE_DEVICES=5 HTTPS_PROXY="http://10.60.28.99:86" nohup python train_compact_cnn.py \
2 --task_id ccnn_v2_t9_sha \
3 --note "ccnnv2 keep full, try no_norm to see how it work" \
4 --input /data/rnd/thient/thient_data/ShanghaiTech/part_A \
5 --no_norm \
6 --lr 1e-4 \
7 --decay 1e-4 \
8 --datasetname shanghaitech_keepfull \
9 --epochs 1500 > logs/ccnn_v2_t9_sha.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