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)
reduction = sum caaf7ea2f013097c2d0275a3c49bffb6ae7e4b69 Thai Thien 2020-12-06 15:40:13
cuda() and we fix 41f49e7aa28595cb6438519dddb5e17434a44d3e Thai Thien 2020-12-06 15:34:53
minor fix 138 6178f63cb061ec7086a1748a8e9d4f4a03ea96e5 Thai Thien 2020-12-06 15:33:08
fix measure ssim psnr 88bb9b78e8ae45199074aa1076b15c73f13e6cb6 Thai Thien 2020-12-06 15:30:58
print y and y_pred shape 90ab90465dabc4bd1171f4500eb01c45cca97420 Thai Thien 2020-12-06 15:23:09
ccnn baseline f02c3084f28f811879e36e9a309993d468535dc3 Thai Thien 2020-12-06 15:08:11
ccnn shb and sha d1d4152ada2c5dfc18c65299f32cb12935b90fe4 Thai Thien 2020-12-06 14:46:36
sha 3196ece275027e4d032a0bddb84ce310c15f2380 Thai Thien 2020-12-06 13:46:28
abs clamp 524c6f7196908527367ddcbfc340107e4092cc6e Thai Thien 2020-12-06 11:16:12
use abs instead of ssim 92226d63c9732e66bf50f0b78e61f915ad2bce77 Thai Thien 2020-12-06 10:56:56
claim both y and y_pred d1f6764a691fc2f2f1adc63ae65d63a8347d8a45 Thai Thien 2020-12-06 10:52:14
clamp 0.0 5569f7dad3c9e792e65636bb29b66a84ff250282 Thai Thien 2020-12-06 10:46:57
dataloader target crop e41c17147de7c05f213329009c7662fbb2f1dc91 Thai Thien 2020-12-06 10:43:12
clamp min = 0 5245898e5282aa4cdc4b6539e68cb36a1c2d0c1f Thai Thien 2020-12-06 10:40:47
fix metric 9739b99b836657377eb9dce05fafeef4a90546e9 Thai Thien 2020-12-06 10:38:37
eval density d02232a419cd22bc79e0325c1c6791a7e5fc15b0 Thai Thien 2020-12-06 10:37:22
. 926498e13908770b072aeca0ccecbf5d3a64808e Thai Thien 2020-12-06 10:27:13
if self.dataset_name == "shanghaitech_non_overlap_test_with_densitygt" and not self.train: ca2bf6f9372ccdd5b880f2dd7be2023840afdd1d Thai Thien 2020-12-06 10:24:21
yeah forgot to change ds name bfdf3cfe27be5f51de300e231b6b79f903a71624 Thai Thien 2020-12-06 10:17:37
eval_only mode should not save bf03ec80b43e070501c043f7428d55d8409b960c Thai Thien 2020-12-06 10:14:22
Commit caaf7ea2f013097c2d0275a3c49bffb6ae7e4b69 - reduction = sum
Author: Thai Thien
Author date (UTC): 2020-12-06 15:40
Committer name: Thai Thien
Committer date (UTC): 2020-12-06 15:40
Parent(s): 41f49e7aa28595cb6438519dddb5e17434a44d3e
Signer:
Signing key:
Signing status: N
Tree: 1414235287cc62dad2cad815c4f1829d1f37437a
File Lines added Lines deleted
crowd_counting_error_metrics.py 8 9
File crowd_counting_error_metrics.py changed (mode: 100644) (index e4cb55b..91ba7e1)
... ... class CrowdCountingMeanSSIMabs(Metric):
138 138 pad_density_map_tensor[:, 0, :y_pred.shape[2],:y_pred.shape[3]] = y_pred pad_density_map_tensor[:, 0, :y_pred.shape[2],:y_pred.shape[3]] = y_pred
139 139 y_pred = pad_density_map_tensor y_pred = pad_density_map_tensor
140 140
141 ssim_metric = piq.ssim(y, y_pred)
141 ssim_metric = piq.ssim(y, y_pred, reduction=sum())
142 142
143 self._sum += ssim_metric.item() * y.shape[0]
143 self._sum += ssim_metric.item()
144 144 # we multiply because ssim calculate mean of each image in batch # we multiply because ssim calculate mean of each image in batch
145 145 # we multiply so we will divide correctly # we multiply so we will divide correctly
146 146
 
... ... class CrowdCountingMeanPSNRabs(Metric):
178 178 pad_density_map_tensor[:, 0, :y_pred.shape[2], :y_pred.shape[3]] = y_pred pad_density_map_tensor[:, 0, :y_pred.shape[2], :y_pred.shape[3]] = y_pred
179 179 y_pred = pad_density_map_tensor y_pred = pad_density_map_tensor
180 180
181 psnr_metric = piq.psnr(y, y_pred)
181 psnr_metric = piq.psnr(y, y_pred, reduction=sum())
182 182
183 self._sum += psnr_metric.item() * y.shape[0]
183 self._sum += psnr_metric.item()
184 184 # we multiply because ssim calculate mean of each image in batch # we multiply because ssim calculate mean of each image in batch
185 185 # we multiply so we will divide correctly # we multiply so we will divide correctly
186 186
 
... ... class CrowdCountingMeanSSIMclamp(Metric):
218 218 pad_density_map_tensor[:, 0, :y_pred.shape[2], :y_pred.shape[3]] = y_pred pad_density_map_tensor[:, 0, :y_pred.shape[2], :y_pred.shape[3]] = y_pred
219 219 y_pred = pad_density_map_tensor y_pred = pad_density_map_tensor
220 220
221 ssim_metric = piq.ssim(y, y_pred)
221 ssim_metric = piq.ssim(y, y_pred, reduction=sum())
222 222
223 self._sum += ssim_metric.item() * y.shape[0]
223 self._sum += ssim_metric.item()
224 224 # we multiply because ssim calculate mean of each image in batch # we multiply because ssim calculate mean of each image in batch
225 225 # we multiply so we will divide correctly # we multiply so we will divide correctly
226 226
 
... ... class CrowdCountingMeanPSNRclamp(Metric):
256 256 pad_density_map_tensor[:, 0, :y_pred.shape[2], :y_pred.shape[3]] = y_pred pad_density_map_tensor[:, 0, :y_pred.shape[2], :y_pred.shape[3]] = y_pred
257 257 y_pred = pad_density_map_tensor y_pred = pad_density_map_tensor
258 258
259 psnr_metric = piq.psnr(y, y_pred, reduction=sum())
259 260
260 psnr_metric = piq.psnr(y, y_pred)
261
262 self._sum += psnr_metric.item() * y.shape[0]
261 self._sum += psnr_metric.item()
263 262 # we multiply because ssim calculate mean of each image in batch # we multiply because ssim calculate mean of each image in batch
264 263 # we multiply so we will divide correctly # we multiply so we will divide correctly
265 264
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