atomishcv

Training on custom datasets

2

Hi, i want to use my own datasets. I have the Homography matrix for pairs images. How to modify the dataloader? Could you give me some addvices?

Hi, I replase your 128 dimension feature map; in resnet_fpn.py 'x0 = self.relu(self.bn1(self.conv1(x)))'; i want to use my cnn net, but the result is different every time , sometimes matches...

when i train the code ，the program feedback such information： 0%| | 0/1250 [00:05

how to install the index_max?

1

I follow the prompts to install index_max and the following error occurs If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(),...

that is a good job! i have a question about code ‘sentence = klines_pos + enc_output[:,:,0,:].transpose(1,2)’ in the line_transformer.py's keylineencode. after the transformer encode the 'des', it out the dimension...

ERROR: Could not build wheels for cppcuda-tutorial, which is required to install pyproject.toml-based projects

7

when i run the 'pip install .', it will report 'ERROR: Could not build wheels for cppcuda-tutorial, which is required to install pyproject.toml-based projects'. my platform is windows+pytorch 1.12.1+cuda 11.3+py3.8....

Hello, can you provide the pre-trained model file?