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)
CompactCNNV3 7de3766d085ebdbdf82b024eb517568dd82d8d6d Thai Thien 2020-04-27 16:23:20
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
Commit 7de3766d085ebdbdf82b024eb517568dd82d8d6d - CompactCNNV3
CCNN without batchnorm, max pooling after cat, does it do any good ?
Author: Thai Thien
Author date (UTC): 2020-04-27 16:23
Committer name: Thai Thien
Committer date (UTC): 2020-04-27 16:23
Parent(s): da3c84dca19b0d281082679d88af3b9d27165bfe
Signing key:
Tree: 61e420bdcd3cc49a0814a61d1711ff805745c25d
File Lines added Lines deleted
models/compact_cnn.py 44 0
File models/compact_cnn.py changed (mode: 100644) (index 16a7dcf..2aeec5a)
... ... class CompactCNNV2(nn.Module):
89 89 return x return x
90 90
91 91
92 class CompactCNNV3(nn.Module):
93 """
94 A REAL-TIME DEEP NETWORK FOR CROWD COUNTING
95 https://arxiv.org/pdf/2002.06515.pdf
96 """
97 def __init__(self, load_weights=False):
98 super(CompactCNNV3, self).__init__()
99 self.model_note = "CCNN without batchnorm, max pooling after cat, does it do any good ?"
100 self.red_cnn = nn.Conv2d(3, 10, 9, padding=4)
101 self.green_cnn = nn.Conv2d(3, 14, 7, padding=3)
102 self.blue_cnn = nn.Conv2d(3, 16, 5, padding=2)
103 self.c0 = nn.Conv2d(40, 40, 3, padding=1)
104
105 self.max_pooling = nn.MaxPool2d(kernel_size=2, stride=2)
106
107 self.c1 = nn.Conv2d(40, 60, 3, padding=1)
108 self.c2 = nn.Conv2d(60, 40, 3, padding=1)
109 self.c3 = nn.Conv2d(40, 20, 3, padding=1)
110 self.c4 = nn.Conv2d(20, 10, 3, padding=1)
111 self.output = nn.Conv2d(10, 1, 1)
112
113 def forward(self,x):
114 x_red = F.relu(self.red_cnn(x), inplace=True)
115 x_green = F.relu(self.green_cnn(x), inplace=True)
116 x_blue = F.relu(self.blue_cnn(x), inplace=True)
117
118 x = torch.cat((x_red, x_green, x_blue), 1)
119
120 x = self.max_pooling(x)
121 x = F.relu(self.c0(x), inplace=True)
122
123 x = F.relu(self.c1(x), inplace=True)
124
125 x = F.relu(self.c2(x), inplace=True)
126 x = self.max_pooling(x)
127
128 x = F.relu(self.c3(x), inplace=True)
129 x = self.max_pooling(x)
130
131 x = F.relu(self.c4(x), inplace=True)
132
133 x = self.output(x)
134 return x
135
92 136 class CompactCNNV6(nn.Module): class CompactCNNV6(nn.Module):
93 137 """ """
94 138 A REAL-TIME DEEP NETWORK FOR CROWD COUNTING A REAL-TIME DEEP NETWORK FOR CROWD COUNTING
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