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)
pacnn 967074890d14ab0eefc277801860270a468e8f9f Thai Thien 2019-09-22 03:54:48
wip: pacnn 2192d7c7b449fecf3868877d9cfbc09bb6f7ae98 Thai Thien 2019-09-22 03:44:56
wip: pacnn 37620e5a9bc0f9516ea964ec58d9bdaa1c40ff36 Thai Thien 2019-09-22 03:14:42
fix training flow 2b87b1b26c7296b64493fdc49fedb421b249dfa3 Thai Thien 2019-09-17 18:00:35
dataset script bc5c052f5f956510ab95ef9a45434fd486c57fae Thai Thien 2019-09-16 17:21:13
evaluator ffc5bf8290ae0c469a9a18a2d061cfd1bfeee822 Thai Thien 2019-09-14 04:56:35
some more test for data loader 25173578cde7d4e9fe6c6140d1ee01caa4fcfc32 Thai Thien 2019-09-14 02:51:58
some visualize to debug data loader e4f52007616acf307bddbde79c0fb4f8c649c785 Thai Thien 2019-09-13 17:35:45
wip d7d44cad6774355bdfa45414258763f6c6a0c299 Thai Thien 2019-08-31 16:58:16
commit all 6dad7a58f7dbf9fc288ce9dd3e92be538851c2a7 Thai Thien 2019-08-29 19:10:44
input d1,d2,d3 match fc2a809241f8b6356d964c63d40cbebd55ca5f6c Thai Thien 2019-08-28 17:57:05
WIP 39eab26d061e61dfffbf164dbd5fd878299b7250 thient 2019-08-28 11:09:12
output of de is ok dd770386674df3e0fbebafdfc48a9352bc28967d thient 2019-08-28 10:54:09
code pacnn c49537b5cc91e96e4e35c9338d2c95b9bb41c672 Thai Thien 2019-08-27 16:35:27
crowd counting stuff da9f27a39cba9bdd021b6b5c562f5f7c2be50190 Thai Thien 2019-08-24 18:27:44
seem ok 53fa176c31669a0e89b04adf290cb398f0316c45 Thai Thien 2019-08-24 18:26:31
flow ok ad849681000818dfbcd0c1715c2858aed7236041 Thai Thien 2019-08-24 17:00:02
wip 23c3ec48497782bbc91d829e1c8a682502360ab9 Thai Thien 2019-08-24 14:19:22
work in progress, try to use https://pytorch.org/ignite/quickstart.html 39c824fe8fc2501628ee42c236a844df45521007 Thai Thien 2019-08-24 07:41:46
Work in progress 984be31d85e5cbdb2af296ccdb128381fe9bf09e Thai Thien 2019-08-24 05:30:51
Commit 967074890d14ab0eefc277801860270a468e8f9f - pacnn
Author: Thai Thien
Author date (UTC): 2019-09-22 03:54
Committer name: Thai Thien
Committer date (UTC): 2019-09-22 03:54
Parent(s): 2192d7c7b449fecf3868877d9cfbc09bb6f7ae98
Signing key:
Tree: 738e642d8e39f1cabdc5d7f4c61b9b5fd57491dc
File Lines added Lines deleted
models/pacnn.py 6 6
models/test_PACNNWithPerspectiveMap.py 21 0
train_script/train_pacnn_shanghaitechA.sh 1 0
File models/pacnn.py changed (mode: 100644) (index 6ccb98e..82897d0)
... ... class PACNN(nn.Module):
31 31
32 32
33 33 class PACNNWithPerspectiveMap(nn.Module): class PACNNWithPerspectiveMap(nn.Module):
34 def __init__(self):
34 def __init__(self, perspective_aware_mode=False):
35 35 super(PACNNWithPerspectiveMap, self).__init__() super(PACNNWithPerspectiveMap, self).__init__()
36 36 self.backbone = models.vgg16(pretrained=True).features self.backbone = models.vgg16(pretrained=True).features
37 37 self.de1net = self.backbone[0:23] self.de1net = self.backbone[0:23]
 
... ... class PACNNWithPerspectiveMap(nn.Module):
56 56 self.perspective_11 = nn.Conv2d(512, 1, kernel_size=1) self.perspective_11 = nn.Conv2d(512, 1, kernel_size=1)
57 57
58 58 # deconvolution upsampling # deconvolution upsampling
59 self.up12 = nn.ConvTranspose2d(512, 1, 2, 2)
60 self.up23 = nn.ConvTranspose2d(512, 1, 2, 2)
61 self.up_perspective = nn.ConvTranspose2d(512, 1, 2, 2)
59 self.up12 = nn.ConvTranspose2d(1, 1, 2, 2)
60 self.up23 = nn.ConvTranspose2d(1, 1, 2, 2)
61 self.up_perspective = nn.ConvTranspose2d(1, 1, 2, 2)
62 62
63 63 # if true, use perspective aware # if true, use perspective aware
64 64 # if false, use average # if false, use average
65 self.perspective_aware_mode = False
65 self.perspective_aware_mode = perspective_aware_mode
66 66
67 67 def forward(self, x): def forward(self, x):
68 68 de1 = self.de1_11((self.de1net(x))) de1 = self.de1_11((self.de1net(x)))
 
... ... class PACNNWithPerspectiveMap(nn.Module):
73 73 pespective_w = self.up_perspective(pespective_w_s) pespective_w = self.up_perspective(pespective_w_s)
74 74 # TODO: code more here # TODO: code more here
75 75 de23 = pespective_w_s * de2 + (1 - pespective_w_s)*(de2 + self.up23(de3)) de23 = pespective_w_s * de2 + (1 - pespective_w_s)*(de2 + self.up23(de3))
76 de = pespective_w * de1 + (1 - pespective_w)*(de2 + self.up12(de23))
76 de = pespective_w * de1 + (1 - pespective_w)*(de1 + self.up12(de23))
77 77 else: else:
78 78 de23 = (de2 + self.up23(de3))/2 de23 = (de2 + self.up23(de3))/2
79 79 de = (de1 + self.up12(de23))/2 de = (de1 + self.up12(de23))/2
File models/test_PACNNWithPerspectiveMap.py added (mode: 100644) (index 0000000..cd3eab6)
1 from unittest import TestCase
2 from models.pacnn import PACNNWithPerspectiveMap
3 import torch
4
5 class TestPACNNWithPerspectiveMap(TestCase):
6
7 def test_avg_schema_pacnn(self):
8 net = PACNNWithPerspectiveMap()
9 # image
10 # batch size, channel, h, w
11 image = torch.rand(1, 3, 224, 224)
12 density_map = net(image)
13 print(density_map.size())
14
15 def test_perspective_aware_schema_pacnn(self):
16 net = PACNNWithPerspectiveMap(perspective_aware_mode=True)
17 # image
18 # batch size, channel, h, w
19 image = torch.rand(1, 3, 224, 224)
20 density_map = net(image)
21 print(density_map.size())
File train_script/train_pacnn_shanghaitechA.sh changed (mode: 100644) (index e69de29..d90895d)
1 python /home/tt/project/crowd_counting_framework/main_pacnn.py --input /home/tt/project/crowd_counting_framework/data/ShanghaiTech/part_A
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