List of commits:
Subject Hash Author Date (UTC)
forgot to change the model cb8bde150d7e764f67f33c980759675a2f5cce8e Thai Thien 2020-03-18 17:23:51
log summary for adcrowdnet simple lrscheduler cefb188f185dbba3dd95f5034f17bd43dd194d44 Thai Thien 2020-03-18 17:18:36
prepare exp 4658d0a852d952f1e1f600d9c494b8d511b9d52c Thai Thien 2020-03-18 17:17:05
CompactCNNV6 with a bunch of batchnorm a9f21eac8ab6a328fac7a23bb5eddbbaa4496d04 Thai Thien 2020-03-18 17:09:26
implement attn_can_adcrowdnet_v5 c905bd76d3a5d3b933d1e6eab6e50da187cee3a2 Thai Thien 2020-03-18 16:56:02
forget add --momentum 58131da12819203ec13ea62e7ad6862cf6db301d thient 2020-03-18 03:41:30
shell script ebb46f6853a666ecdfbaf42bb927cad0ec9e548e thient 2020-03-18 03:38:56
add sgd a37f034b6231728629586223b9c1a0ca9f8c30ba thient 2020-03-18 03:38:21
increase epoch ... because we are loading old model 44c6dea2b2e5017f8c6f3bf87136220d6e9def42 thient 2020-03-18 03:16:49
continue train with higher lr (forgot a slash) 982a68aa7e2cd9879c24962459db41215415833f thient 2020-03-18 03:13:08
continue train with higher lr f2bd926e2db7f73065433ad6702c6edee31076b3 thient 2020-03-18 03:12:03
look like batch size 2 is fck up 85e85c211dc75dd5e4bd5033e33802699b000227 Thai Thien 2020-03-17 18:04:19
100 epoch batch size 2 7d3cd859496dd2c268e0d9c7cb02b67c88e71de4 Thai Thien 2020-03-17 18:01:44
batch_size 1 57017c52dd5788f481173cefae2aab56dd15bad4 Thai Thien 2020-03-17 17:59:13
remove inplace relu, let batchsize = 4 5de3e36f31d3e2b000a1bd8972bda580ecf92c3e Thai Thien 2020-03-17 17:52:29
batchsize 5 a4332d10d2a776f2b3b72c74cc706bfd9b9ff665 Thai Thien 2020-03-17 17:48:11
batchsize to 6 7437e22c7bd11a29421bfc645efc7ade5f0fb42a Thai Thien 2020-03-17 17:46:11
deformable ccnn 10a75cf43918482b285c1d130a44c7f21d65b74b Thai Thien 2020-03-17 17:43:21
change cuda vis 8f3bad803408eda16953a040ca5ec5895ad1e6cc Thai Thien 2020-03-16 17:23:35
add bias = false to cnn aba5e4a6c68ac5908e6244ce6c1b6b8cddfeb3c9 Thai Thien 2020-03-16 17:23:08
Commit cb8bde150d7e764f67f33c980759675a2f5cce8e - forgot to change the model
Author: Thai Thien
Author date (UTC): 2020-03-18 17:23
Committer name: Thai Thien
Committer date (UTC): 2020-03-18 17:23
Parent(s): cefb188f185dbba3dd95f5034f17bd43dd194d44
Signer:
Signing key:
Signing status: N
Tree: 168d36d47d97bbe98d68ba9ef721d3540f8279b5
File Lines added Lines deleted
train_attn_can_adcrowdnet_simple_lrscheduler.py 2 2
train_compact_cnn.py 2 2
File train_attn_can_adcrowdnet_simple_lrscheduler.py changed (mode: 100644) (index 71a4b89..90b846b)
... ... 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 AttnCanAdcrowdNetSimpleV4
14 from models import AttnCanAdcrowdNetSimpleV5
15 15 import os import os
16 16
17 17 from ignite.contrib.handlers import PiecewiseLinear from ignite.contrib.handlers import PiecewiseLinear
 
... ... if __name__ == "__main__":
53 53 print("len train_loader ", len(train_loader)) print("len train_loader ", len(train_loader))
54 54
55 55 # model # model
56 model = AttnCanAdcrowdNetSimpleV4()
56 model = AttnCanAdcrowdNetSimpleV5()
57 57 experiment.log_other("model_summary", summary(model, (3, 128, 128), device="cpu")) experiment.log_other("model_summary", summary(model, (3, 128, 128), device="cpu"))
58 58 model = model.to(device) model = model.to(device)
59 59
File train_compact_cnn.py changed (mode: 100644) (index 5a08de3..1045b25)
... ... 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 CompactCNNV2
14 from models import CompactCNNV6
15 15 import os import os
16 16 from model_util import get_lr from model_util import get_lr
17 17 from torchsummary import summary from torchsummary import summary
 
... ... if __name__ == "__main__":
52 52 print("len train_loader ", len(train_loader)) print("len train_loader ", len(train_loader))
53 53
54 54 # model # model
55 model = CompactCNNV2()
55 model = CompactCNNV6()
56 56 experiment.log_other("model_summary", summary(model, (3, 128, 128), device="cpu")) experiment.log_other("model_summary", summary(model, (3, 128, 128), device="cpu"))
57 57 model = model.to(device) model = model.to(device)
58 58
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