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)
prepare to train 8c16b70c805d48e4f944fa469cb370f1ee1297f0 Thai Thien 2020-03-14 10:15:22
add 1 move layer to ccnn 10d5d3711dda204d7b059b79d775c0359d1a964d Thai Thien 2020-03-14 10:04:17
continue train 3627b8cbf4192856d7453b72972a11659c34ae5f Thai Thien 2020-03-14 01:58:25
simple v4 t2 4dee2eba24246cf21a84dd7f9ef74d6c434edf1d Thai Thien 2020-03-13 18:36:33
nll to loss 958f0895b81d42e6d31a0bbd5787211538c081fe Thai Thien 2020-03-13 16:27:27
ccnn_v4_t1 1f950b91f4fb89a0f08baf08dffb2a501546b64f Thai Thien 2020-03-13 16:23:39
add proxy 9afb66a73e3ae24b2144faf311b128dbe5768f3c Thai Thien 2020-03-13 16:09:30
add comet, add scheduler to simple 4ef5939124745dfc54ad8a87936954a2bde8a5a2 Thai Thien 2020-03-13 16:06:24
ccnn v1_t5 lr scheduler 31f7a693eff8e60a07bd7bc439575cc7712fe31b Thai Thien 2020-03-13 15:37:37
ccnn_v1_t4_scheduler, also change lr milestones c27beba80ebf7686dc7f046b95d5e2739b6dae66 Thai Thien 2020-03-12 16:23:02
add load_data_shanghaitech_keepfull_and_crop 5af55c5b483263683db80bcf4b870bfbb241d668 Thai Thien 2020-03-12 16:19:19
change on how it log epoch adcb2aa917f02d4b5d567a9b70f08ec519f896d1 Thai Thien 2020-03-11 17:32:35
fix the milestone 4e8c048ff8db59cbedc819e4df2a48094568fc2c Thai Thien 2020-03-11 17:10:03
add COMET_ML_API 7fbec715d751544bcdafb34a686602839a2696de Thai Thien 2020-03-11 17:04:19
fix script name 631c37c068377706ae2cad4513baeea7e62ae0b5 Thai Thien 2020-03-11 16:59:24
intergrate comet ml into compact cnn 058e90a617acb76a7788e6a5d44f52563342490b Thai Thien 2020-03-11 16:57:17
something ?! fff52ff87af2a90452384a01bd6d6e6c4b91654e Thai Thien 2020-03-11 15:55:04
DilatedCCNNv2 75d2989232a8a68eba9b4920ab2374ac28438e0e Thai Thien 2020-03-10 05:11:12
fix script for ccnn_v2_t1_c2 57928056d13bc9b1f9b11e14dd305005a3a5aeea Thai Thien 2020-03-10 04:56:33
fix trash code 33c406b13b5d45527b05dfb7f4281c3966c6471e Thai Thien 2020-03-10 04:49:52
Commit 8c16b70c805d48e4f944fa469cb370f1ee1297f0 - prepare to train
Author: Thai Thien
Author date (UTC): 2020-03-14 10:15
Committer name: Thai Thien
Committer date (UTC): 2020-03-14 10:15
Parent(s): 10d5d3711dda204d7b059b79d775c0359d1a964d
Signing key:
Tree: ea56db1d87633473cf918d23c33d27c869b2301b
File Lines added Lines deleted
train_compact_cnn.py 3 2
train_script/CCNN/ccnn_v5_t1.sh 3 3
File train_compact_cnn.py changed (mode: 100644) (index a79ba4a..5fb5b7f)
... ... from visualize_util import get_readable_time
11 11
12 12 import torch import torch
13 13 from torch import nn from torch import nn
14 from models import CompactCNN
14 from models import CompactCNNV2
15 15 import os import os
16 16 from model_util import get_lr from model_util import get_lr
17 17
 
... ... if __name__ == "__main__":
27 27
28 28 experiment.set_name(args.task_id) experiment.set_name(args.task_id)
29 29 experiment.set_cmd_args() experiment.set_cmd_args()
30 experiment.log_text(args.note)
30 31
31 32 DATA_PATH = args.input DATA_PATH = args.input
32 33 TRAIN_PATH = os.path.join(DATA_PATH, "train_data") TRAIN_PATH = os.path.join(DATA_PATH, "train_data")
 
... ... if __name__ == "__main__":
50 51 print("len train_loader ", len(train_loader)) print("len train_loader ", len(train_loader))
51 52
52 53 # model # model
53 model = CompactCNN()
54 model = CompactCNNV2()
54 55 model = model.to(device) model = model.to(device)
55 56
56 57 # loss function # loss function
File train_script/CCNN/ccnn_v5_t1.sh copied from file train_script/CCNN/ccnn_v4_t1.sh (similarity 54%) (mode: 100644) (index 2f6e700..f7032bc)
1 1 CUDA_VISIBLE_DEVICES=6 HTTPS_PROXY="http://10.30.58.36:81" nohup python train_compact_cnn.py \ CUDA_VISIBLE_DEVICES=6 HTTPS_PROXY="http://10.30.58.36:81" nohup python train_compact_cnn.py \
2 --task_id ccnn_v4_t1 \
3 --note "train ccnn with fixed lr 1e-5 no decay on keepfull and crop dataset part_A" \
2 --task_id ccnn_v5_t1 \
3 --note "train CompactCNNV2 (fixed by adding 1 layer of cnn) with fixed lr 1e-5 no decay on keepfull and crop dataset part_A" \
4 4 --input /data/rnd/thient/thient_data/ShanghaiTech/part_A \ --input /data/rnd/thient/thient_data/ShanghaiTech/part_A \
5 5 --lr 1e-5 \ --lr 1e-5 \
6 6 --decay 0 \ --decay 0 \
7 7 --datasetname shanghaitech_keepfull_and_crop \ --datasetname shanghaitech_keepfull_and_crop \
8 --epochs 502 > logs/ccnn_v4_t1.log &
8 --epochs 402 > logs/ccnn_v5_t1.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