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)
v3 t1 c2 2d4727f47f4262833dca2087fb9e48f0d117e334 Thai Thien 2020-03-10 04:29:23
dilated ccnn v1 t1 7807d7a979353fa84d0b7319820386e93dbe5cc4 Thai Thien 2020-03-09 17:20:58
new ccnn 44a669c1f918be9d74313f29a5dbbc876c29f2fc Thai Thien 2020-03-09 17:16:49
fix script aa331331b12e5b454d372a550524b30a4bebe706 Thai Thien 2020-03-07 18:32:06
try reproduct ccnn with keepfull and lr 1e-5 814c520cbd1bb2d7fd50d2a8d3579d43da79fe60 Thai Thien 2020-03-07 18:30:42
my simple v4 with addition deform cnn at the end 5392aaf6c14fdd910f52096dbb921bed7470c4f7 Thai Thien 2020-03-07 18:15:22
fix the scheduler 77e6737a040f5aa5745b8a8830f5bec12322b10f Thai Thien 2020-03-07 17:46:02
t4 lr 1e-5 acd41ed30c95f63e01a05a6d9929410637852d9e Thai Thien 2020-03-06 19:41:49
no more lr scheduler 7289adb41de7807258eb8c29e6108fa65f59525a Thai Thien 2020-03-06 19:35:49
reduce learning rate bc8241e5b88b91c18bb7999a8d5d12fc79a5e3f7 Thai Thien 2020-03-06 19:28:27
dilated ccnn 5c5d92bdc0a288dd5d4ec5f1367d8cb928175bbe Thai Thien 2020-03-06 19:04:01
done 9f05e093ec7c10284a4aedf0738f9e61d5ac6fb6 Thai Thien 2020-03-06 18:02:34
with lr scheduler 466c364b60ed22c77319b14ccc9a201614b908bf Thai Thien 2020-03-04 17:57:49
train with learning rate scheduler fcd5a3c8da2dd6763e0d40742edf47b49c95fcfb Thai Thien 2020-03-04 17:55:11
ccnn no padding at output layer 57563fc07f656c63f807de4d80712ff11345109d Thai Thien 2020-03-04 17:36:43
fix dimension of ccnn f4439d9a78273ab3ba450f31a528509816b4352f Thai Thien 2020-03-04 17:32:48
ready to train dbe0d6c3271dbb22490f0877fa31ba9cd7852b99 Thai Thien 2020-03-04 15:55:05
done implement c-cnn 2deecef953baf1e07ce5cf5477d208bc7ffa34cf Thai Thien 2020-03-03 17:25:03
fix script 0e9d372b9ad60b32939f1e558b2a59fc7d518fa2 Thai Thien 2020-03-02 16:23:55
simple v3 to 91 epoch 539fdd03c3e3497fd22b7db2aaa14f067cbf6f8d Thai Thien 2020-03-02 16:09:43
Commit 2d4727f47f4262833dca2087fb9e48f0d117e334 - v3 t1 c2
Author: Thai Thien
Author date (UTC): 2020-03-10 04:29
Committer name: Thai Thien
Committer date (UTC): 2020-03-10 04:29
Parent(s): 7807d7a979353fa84d0b7319820386e93dbe5cc4
Signing key:
Tree: 77784c77e272b51359ce5f5b97492f6d49d0fbea
File Lines added Lines deleted
explore_model_summary.py 16 12
train_script/CCNN/ccnn_v3_t1_c2.sh 3 2
File explore_model_summary.py changed (mode: 100644) (index d5f3bc4..9d5c32d)
1 from models import CompactCNN, AttnCanAdcrowdNetSimpleV3, CompactDilatedCNN
1 from models import CompactCNN, AttnCanAdcrowdNetSimpleV3, CompactDilatedCNN, DefDilatedCCNN
2 2 from torchsummary import summary from torchsummary import summary
3 3
4 4 def very_simple_param_count(model): def very_simple_param_count(model):
 
... ... def very_simple_param_count(model):
6 6 return result return result
7 7
8 8 if __name__ == "__main__": if __name__ == "__main__":
9 print("Compact CNN")
10 ccnn = CompactCNN()
11 print(ccnn)
12 print("-------------")
13 # print(summary(ccnn, (3, 128, 128))) # we print twice to confirm trainable parameter independent with input size
14 print("-------------")
15 print(summary(ccnn, (3, 512, 512)))
16 print("simple count", very_simple_param_count(ccnn))
17 print("===========================================================================")
9 # print("Compact CNN")
10 # ccnn = CompactCNN()
11 # print(ccnn)
12 # print("-------------")
13 # # print(summary(ccnn, (3, 128, 128))) # we print twice to confirm trainable parameter independent with input size
14 # print("-------------")
15 # print(summary(ccnn, (3, 512, 512)))
16 # print("simple count", very_simple_param_count(ccnn))
17 # print("===========================================================================")
18 # print("dilate ccnn")
19 # dcnn1 = CompactDilatedCNN()
20 # print(summary(dcnn1, (3, 512, 512)))
21 # print("=============================================================================")
18 22 print("dilate ccnn") print("dilate ccnn")
19 dcnn = CompactDilatedCNN()
20 print(summary(dcnn, (3, 512, 512)))
23 dcnn2 = DefDilatedCCNN()
24 print(summary(dcnn2, (3, 512, 512)))
21 25 print("=============================================================================") print("=============================================================================")
22 26 # print("simple_v3") # print("simple_v3")
23 27 # simplev3 = AttnCanAdcrowdNetSimpleV3() # simplev3 = AttnCanAdcrowdNetSimpleV3()
File train_script/CCNN/ccnn_v3_t1_c2.sh copied from file train_script/CCNN/ccnn_v3_t1.sh (similarity 59%) (mode: 100644) (index a3102e5..4fef813)
1 1 CUDA_VISIBLE_DEVICES=6 nohup python train_compact_cnn.py \ CUDA_VISIBLE_DEVICES=6 nohup python train_compact_cnn.py \
2 --task_id ccnn_v3_t1 \
2 --task_id ccnn_v3_t1_c2 \
3 3 --input /data/rnd/thient/thient_data/ShanghaiTech/part_A \ --input /data/rnd/thient/thient_data/ShanghaiTech/part_A \
4 4 --lr 1e-5 \ --lr 1e-5 \
5 5 --decay 5e-5 \ --decay 5e-5 \
6 --load_model saved_model/ccnn_v3_t1_checkpoint_478800.pth \
6 7 --datasetname shanghaitech_keepfull \ --datasetname shanghaitech_keepfull \
7 --epochs 401 > logs/ccnn_v3_t1.log &
8 --epochs 401 > logs/ccnn_v3_t1_c2.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