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)
add bias = false to cnn aba5e4a6c68ac5908e6244ce6c1b6b8cddfeb3c9 Thai Thien 2020-03-16 17:23:08
customccnn v3 with many batchnorm 42ea62efcce0489673cdf71db792eb06d88fa5e6 Thai Thien 2020-03-16 17:22:30
CustomCNNv3 b1b117d627147bc23727e55ab0c3026e920d9f20 Thai Thien 2020-03-16 16:05:02
fix dimension mismake again d2341d70250a38071fefa9e6af24d7382ccf3138 Thai Thien 2020-03-15 09:29:03
fix custom ccnn dimension mismake 8b2fe4f669469196685a37974b5e7fee5e9a5fe0 Thai Thien 2020-03-15 08:57:16
custom ccnn fa81a2a28140cc8a84e3d5df49443ebe79e89268 Thai Thien 2020-03-15 08:54:19
forgot to add batch size arg in "train_compact_cnn" bc9f7ca249f6719d8ee67a631bce184914d6b199 Thai Thien 2020-03-14 17:58:26
ccnn_v5_t2shb 85dcfe49ecbcef2ccb1bb70b2a1b898440180286 Thai Thien 2020-03-14 17:43:00
add batchsize, ready train shb with batch5 254ba309e8031fcffb911f29d92a46f56106e8aa Thai Thien 2020-03-14 17:39:18
gpu 5 44fb230848afb391fa4efa4e412d3def3e32965a Thai Thien 2020-03-14 11:29:26
reduce lr to 1e-4 9c5e5b64621b33ae7ecc0124c204c4053296d426 Thai Thien 2020-03-14 11:24:24
train with scheduler 390958d81f108ed3ca3cfe668ceef2a4ebf6a69f Thai Thien 2020-03-14 10:57:44
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
Commit aba5e4a6c68ac5908e6244ce6c1b6b8cddfeb3c9 - add bias = false to cnn
Author: Thai Thien
Author date (UTC): 2020-03-16 17:23
Committer name: Thai Thien
Committer date (UTC): 2020-03-16 17:23
Parent(s): 42ea62efcce0489673cdf71db792eb06d88fa5e6
Signer:
Signing key:
Signing status: N
Tree: 98dbc2a078f8c43eef0bf797bfaea0c9aca65e3c
File Lines added Lines deleted
models/my_ccnn.py 4 4
File models/my_ccnn.py changed (mode: 100644) (index 9ee3cc0..22c0cbf)
... ... class CustomCNNv3(nn.Module):
168 168 # self.blue_cnn = nn.Conv2d(3, 16, 5, padding=2) # self.blue_cnn = nn.Conv2d(3, 16, 5, padding=2)
169 169
170 170 # ideal from crowd counting using DMCNN # ideal from crowd counting using DMCNN
171 self.front_cnn_1 = nn.Conv2d(3, 20, 3, padding=1)
171 self.front_cnn_1 = nn.Conv2d(3, 20, 3, padding=1, bias=False)
172 172 self.front_bn1 = nn.BatchNorm2d(20) self.front_bn1 = nn.BatchNorm2d(20)
173 self.front_cnn_2 = nn.Conv2d(20, 16, 3, padding=1)
173 self.front_cnn_2 = nn.Conv2d(20, 16, 3, padding=1, bias=False)
174 174 self.front_bn2 = nn.BatchNorm2d(16) self.front_bn2 = nn.BatchNorm2d(16)
175 self.front_cnn_3 = nn.Conv2d(16, 14, 3, padding=1)
175 self.front_cnn_3 = nn.Conv2d(16, 14, 3, padding=1, bias=False)
176 176 self.front_bn3 = nn.BatchNorm2d(14) self.front_bn3 = nn.BatchNorm2d(14)
177 self.front_cnn_4 = nn.Conv2d(14, 10, 3, padding=1)
177 self.front_cnn_4 = nn.Conv2d(14, 10, 3, padding=1, bias=False)
178 178 self.front_bn4 = nn.BatchNorm2d(10) self.front_bn4 = nn.BatchNorm2d(10)
179 179
180 180 self.c0 = nn.Conv2d(40, 40, 3, padding=1) self.c0 = nn.Conv2d(40, 40, 3, padding=1)
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