Alwyn Mathew
Alwyn Mathew
`2 * flow_field - 1` normalize the image coordinates. `F.grid_sample` takes only flow-field with values [-1,1].
@mdfirman Even though its [mentioned](https://github.com/nianticlabs/monodepth2/blob/master/datasets/kitti_dataset.py#L27) not to horizontally flip the image if the principal point is far from the center. But is it advisable to update the principal point if...
I couldn’t find a `module` in `model`. Could you point me to the code section where its defined. `AttributeError: 'model' object has no attribute 'module'`
Set `gpu_ids` as `-1` to run in `cpu`. https://github.com/NVIDIA/pix2pixHD/blob/5a2c87201c5957e2bf51d79b8acddb9cc1920b26/models/models.py#L17 if `gpu_ids` is not set to `-1`, `model` will be wrapped in `DataParallel` https://github.com/NVIDIA/pix2pixHD/blob/5a2c87201c5957e2bf51d79b8acddb9cc1920b26/models/models.py#L18 when its wrapped in `DataParallel`, everything in...
Replace [linkalibr/CMakeLists.txt](https://github.com/unmannedlab/imu_lidar_calibration/blob/main/linkalibr/CMakeLists.txt) with the below ``` cmake_minimum_required(VERSION 3.10) # Project name project(linkalibr) set(CMAKE_CXX_STANDARD 14) set(CMAKE_BUILD_TYPE "RELEASE") #SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=native ") #set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -O1") find_package(OpenMP) if (OPENMP_FOUND) set (CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${OpenMP_C_FLAGS}")...
The process died on [ros_calib_init_optimizer.cpp#L173](https://github.com/unmannedlab/imu_lidar_calibration/blob/main/linkalibr/src/ros_calib_init_optimizer.cpp#L173) just after processing the last frame of the test data given in [imu_lidar_calibration#data-collection-for-extrinsic-calibration](https://github.com/unmannedlab/imu_lidar_calibration#data-collection-for-extrinsic-calibration). ``` [ INFO] [1692115069.770867042]: Frame: 550 / 550 ================================================================================ REQUIRED process [ros_calib_init_optimizer-2]...
No, I have been going through `grid_sample` recently. I'll update you if I could find a way, please update me if you could crack it before me.
@scholltan how to make a field flow(grid) when the input image is 4D? According to [doc](https://pytorch.org/docs/master/nn.html?highlight=grid_sample#grid-sample): Input : `N x C x ID x IH x IW` Grid: `N x...
Instead of making the grid in range (0, h) then converting to (-1,+1): ``` i_range = torch.autograd.Variable(torch.arange(0, h).view(1, h, 1).expand(1,h,w),requires_grad = False)# .type_as(depth) # [1, H, W] copy 0-height for...