C-3-Framework
C-3-Framework copied to clipboard
gjy3035
An open-source PyTorch code for crowd counting
绝对路径
在datasets/SHHB/setting.py中 __C_SHHB.DATA_PATH = '../ProcessedData/shanghaitech_part_B' 此处的__C_SHHB.DATA_PATH是不是要赋值绝对路径呢？如果是相对路径的话，运行到SHHB.py中下面的这句话 self.data_files = [filename for filename in os.listdir(self.img_path) \ if os.path.isfile(os.path.join(self.img_path, filename))] 则会报错，因为 os.path.isfile()的输入需要绝对路径？
validate_V2 in trainer.py line202 has referenced a undefined value mse, and it could cause run error ``` self.train_record = update_model(self.net,self.optimizer,self.scheduler,self.epoch,self.i_tb,self.exp_path,self.exp_name, \ [mae, **mse**, loss],self.train_record,self.log_txt) ``` 
I tried to this: tensorboard --logdir=exp --port=6006 But I can not any solution. In the "exp" directory includes an other directory like that: 01-....AlexNet_... Therefore I changed --logdir=exp/01.... But the...
I get the following error while running test.py. I am using the vgg16-397923af.pth as a pretrained model. Any help on this will be appreciated. I have already looked into the...
``` UserWarning: Detected call of `lr_scheduler.step()` before `optimizer.step()`. In PyTorch 1.1.0 and later, you should call them in the opposite order: `optimizer.step()` before `lr_scheduler.step()`. Failure to do this will result...
please add document on how to test with exist model on exist datasset
I haven't validated this in detail because I don't run the code in this repo. I only use it for looking up settings. I noticed that the point masks are...
I download the processed WE dataset, and trained MCNN using the training parameters of the original framework. But the best MAE is around 19, which is much higher than the...
RuntimeError: Error(s) in loading state_dict for CrowdCounter: Missing key(s) in state_dict: "CCN.de_pred.0.conv.bias", "CCN.de_pred.0.conv.weight", "CCN.de_pred.1.conv.bias", "CCN.de_pred.1.conv.weight", "CCN.frontend.0.weight", "CCN.frontend.1.running_var", "CCN.frontend.1.bias", "CCN.frontend.1.weight", "CCN.frontend.1.running_mean", "CCN.frontend.4.0.conv1.weight", "CCN.frontend.4.0.bn1.running_var", "CCN.frontend.4.0.bn1.bias", "CCN.frontend.4.0.bn1.weight", "CCN.frontend.4.0.bn1.running_mean", "CCN.frontend.4.0.conv2.weight", "CCN.frontend.4.0.bn2.running_var", "CCN.frontend.4.0.bn2.bias", "CCN.frontend.4.0.bn2.weight", "CCN.frontend.4.0.bn2.running_mean",...
