Cpt.Captain/connecting_the_dots
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

added validation set and pre-trained model; tested on pytorch1.8

Browse Source
This commit is contained in:
Yiyi Liao
2021-06-07 17:54:54 +02:00
parent bdcc50a88f
commit 4617525f61
5 changed files with 68 additions and 60 deletions
Download Patch File Download Diff File Expand all files Collapse all files
torchext/ext/ext_cpu.cpp
+28 -28
View File
@@ -12,17 +12,17 @@ void iterate_cpu(FunctorT functor, int N) {
}
at::Tensor nn_cpu(at::Tensor in0, at::Tensor in1) {
CHECK_INPUT_CPU(in0)
CHECK_INPUT_CPU(in1)
CHECK_INPUT_CPU(in0);
CHECK_INPUT_CPU(in1);
auto nelem0 = in0.size(0);
auto nelem1 = in1.size(0);
auto dim = in0.size(1);
AT_ASSERTM(dim == in1.size(1), "in0 and in1 have to be the same shape")
AT_ASSERTM(dim == 3, "dim hast to be 3")
AT_ASSERTM(in0.dim() == 2, "in0 has to be N0 x 3")
AT_ASSERTM(in1.dim() == 2, "in1 has to be N1 x 3")
AT_ASSERTM(dim == in1.size(1), "in0 and in1 have to be the same shape");
AT_ASSERTM(dim == 3, "dim hast to be 3");
AT_ASSERTM(in0.dim() == 2, "in0 has to be N0 x 3");
AT_ASSERTM(in1.dim() == 2, "in1 has to be N1 x 3");
auto out = at::empty({nelem0}, torch::CPU(at::kLong));
@@ -37,11 +37,11 @@ at::Tensor nn_cpu(at::Tensor in0, at::Tensor in1) {
at::Tensor crosscheck_cpu(at::Tensor in0, at::Tensor in1) {
CHECK_INPUT_CPU(in0)
CHECK_INPUT_CPU(in1)
CHECK_INPUT_CPU(in0);
CHECK_INPUT_CPU(in1);
AT_ASSERTM(in0.dim() == 1, "")
AT_ASSERTM(in1.dim() == 1, "")
AT_ASSERTM(in0.dim() == 1, "");
AT_ASSERTM(in1.dim() == 1, "");
auto nelem0 = in0.size(0);
auto nelem1 = in1.size(0);
@@ -57,21 +57,21 @@ at::Tensor crosscheck_cpu(at::Tensor in0, at::Tensor in1) {
at::Tensor proj_nn_cpu(at::Tensor xyz0, at::Tensor xyz1, at::Tensor K, int patch_size) {
CHECK_INPUT_CPU(xyz0)
CHECK_INPUT_CPU(xyz1)
CHECK_INPUT_CPU(K)
CHECK_INPUT_CPU(xyz0);
CHECK_INPUT_CPU(xyz1);
CHECK_INPUT_CPU(K);
auto batch_size = xyz0.size(0);
auto height = xyz0.size(1);
auto width = xyz0.size(2);
AT_ASSERTM(xyz0.size(0) == xyz1.size(0), "")
AT_ASSERTM(xyz0.size(1) == xyz1.size(1), "")
AT_ASSERTM(xyz0.size(2) == xyz1.size(2), "")
AT_ASSERTM(xyz0.size(3) == xyz1.size(3), "")
AT_ASSERTM(xyz0.size(3) == 3, "")
AT_ASSERTM(xyz0.dim() == 4, "")
AT_ASSERTM(xyz1.dim() == 4, "")
AT_ASSERTM(xyz0.size(0) == xyz1.size(0), "");
AT_ASSERTM(xyz0.size(1) == xyz1.size(1), "");
AT_ASSERTM(xyz0.size(2) == xyz1.size(2), "");
AT_ASSERTM(xyz0.size(3) == xyz1.size(3), "");
AT_ASSERTM(xyz0.size(3) == 3, "");
AT_ASSERTM(xyz0.dim() == 4, "");
AT_ASSERTM(xyz1.dim() == 4, "");
auto out = at::empty({batch_size, height, width}, torch::CPU(at::kLong));
@@ -86,8 +86,8 @@ at::Tensor proj_nn_cpu(at::Tensor xyz0, at::Tensor xyz1, at::Tensor K, int patch
at::Tensor xcorrvol_cpu(at::Tensor in0, at::Tensor in1, int n_disps, int block_size) {
CHECK_INPUT_CPU(in0)
CHECK_INPUT_CPU(in1)
CHECK_INPUT_CPU(in0);
CHECK_INPUT_CPU(in1);
auto channels = in0.size(0);
auto height = in0.size(1);
@@ -108,8 +108,8 @@ at::Tensor xcorrvol_cpu(at::Tensor in0, at::Tensor in1, int n_disps, int block_s
at::Tensor photometric_loss_forward(at::Tensor es, at::Tensor ta, int block_size, int type, float eps) {
CHECK_INPUT_CPU(es)
CHECK_INPUT_CPU(ta)
CHECK_INPUT_CPU(es);
CHECK_INPUT_CPU(ta);
auto batch_size = es.size(0);
auto channels = es.size(1);
@@ -145,16 +145,16 @@ at::Tensor photometric_loss_forward(at::Tensor es, at::Tensor ta, int block_size
}
at::Tensor photometric_loss_backward(at::Tensor es, at::Tensor ta, at::Tensor grad_out, int block_size, int type, float eps) {
CHECK_INPUT_CPU(es)
CHECK_INPUT_CPU(ta)
CHECK_INPUT_CPU(grad_out)
CHECK_INPUT_CPU(es);
CHECK_INPUT_CPU(ta);
CHECK_INPUT_CPU(grad_out);
auto batch_size = es.size(0);
auto channels = es.size(1);
auto height = es.size(2);
auto width = es.size(3);
CHECK_INPUT_CPU(ta)
CHECK_INPUT_CPU(ta);
auto grad_in = at::zeros({batch_size, channels, height, width}, grad_out.options());
AT_DISPATCH_FLOATING_TYPES(es.scalar_type(), "photometric_loss_backward_cpu", ([&] {
torchext/ext/ext_cuda.cpp
+27 -27
View File
@@ -7,16 +7,16 @@
void nn_kernel(at::Tensor in0, at::Tensor in1, at::Tensor out);
at::Tensor nn_cuda(at::Tensor in0, at::Tensor in1) {
CHECK_INPUT_CUDA(in0)
CHECK_INPUT_CUDA(in1)
CHECK_INPUT_CUDA(in0);
CHECK_INPUT_CUDA(in1);
auto nelem0 = in0.size(0);
auto dim = in0.size(1);
AT_ASSERTM(dim == in1.size(1), "in0 and in1 have to be the same shape")
AT_ASSERTM(dim == 3, "dim hast to be 3")
AT_ASSERTM(in0.dim() == 2, "in0 has to be N0 x 3")
AT_ASSERTM(in1.dim() == 2, "in1 has to be N1 x 3")
AT_ASSERTM(dim == in1.size(1), "in0 and in1 have to be the same shape");
AT_ASSERTM(dim == 3, "dim hast to be 3");
AT_ASSERTM(in0.dim() == 2, "in0 has to be N0 x 3");
AT_ASSERTM(in1.dim() == 2, "in1 has to be N1 x 3");
auto out = at::empty({nelem0}, torch::CUDA(at::kLong));
@@ -29,11 +29,11 @@ at::Tensor nn_cuda(at::Tensor in0, at::Tensor in1) {
void crosscheck_kernel(at::Tensor in0, at::Tensor in1, at::Tensor out);
at::Tensor crosscheck_cuda(at::Tensor in0, at::Tensor in1) {
CHECK_INPUT_CUDA(in0)
CHECK_INPUT_CUDA(in1)
CHECK_INPUT_CUDA(in0);
CHECK_INPUT_CUDA(in1);
AT_ASSERTM(in0.dim() == 1, "")
AT_ASSERTM(in1.dim() == 1, "")
AT_ASSERTM(in0.dim() == 1, "");
AT_ASSERTM(in1.dim() == 1, "");
auto nelem0 = in0.size(0);
auto out = at::empty({nelem0}, torch::CUDA(at::kByte));
@@ -45,21 +45,21 @@ at::Tensor crosscheck_cuda(at::Tensor in0, at::Tensor in1) {
void proj_nn_kernel(at::Tensor xyz0, at::Tensor xyz1, at::Tensor K, int patch_size, at::Tensor out);
at::Tensor proj_nn_cuda(at::Tensor xyz0, at::Tensor xyz1, at::Tensor K, int patch_size) {
CHECK_INPUT_CUDA(xyz0)
CHECK_INPUT_CUDA(xyz1)
CHECK_INPUT_CUDA(K)
CHECK_INPUT_CUDA(xyz0);
CHECK_INPUT_CUDA(xyz1);
CHECK_INPUT_CUDA(K);
auto batch_size = xyz0.size(0);
auto height = xyz0.size(1);
auto width = xyz0.size(2);
AT_ASSERTM(xyz0.size(0) == xyz1.size(0), "")
AT_ASSERTM(xyz0.size(1) == xyz1.size(1), "")
AT_ASSERTM(xyz0.size(2) == xyz1.size(2), "")
AT_ASSERTM(xyz0.size(3) == xyz1.size(3), "")
AT_ASSERTM(xyz0.size(3) == 3, "")
AT_ASSERTM(xyz0.dim() == 4, "")
AT_ASSERTM(xyz1.dim() == 4, "")
AT_ASSERTM(xyz0.size(0) == xyz1.size(0), "");
AT_ASSERTM(xyz0.size(1) == xyz1.size(1), "");
AT_ASSERTM(xyz0.size(2) == xyz1.size(2), "");
AT_ASSERTM(xyz0.size(3) == xyz1.size(3), "");
AT_ASSERTM(xyz0.size(3) == 3, "");
AT_ASSERTM(xyz0.dim() == 4, "");
AT_ASSERTM(xyz1.dim() == 4, "");
auto out = at::empty({batch_size, height, width}, torch::CUDA(at::kLong));
@@ -71,8 +71,8 @@ at::Tensor proj_nn_cuda(at::Tensor xyz0, at::Tensor xyz1, at::Tensor K, int patc
void xcorrvol_kernel(at::Tensor in0, at::Tensor in1, int n_disps, int block_size, at::Tensor out);
at::Tensor xcorrvol_cuda(at::Tensor in0, at::Tensor in1, int n_disps, int block_size) {
CHECK_INPUT_CUDA(in0)
CHECK_INPUT_CUDA(in1)
CHECK_INPUT_CUDA(in0);
CHECK_INPUT_CUDA(in1);
// auto channels = in0.size(0);
auto height = in0.size(1);
@@ -90,8 +90,8 @@ at::Tensor xcorrvol_cuda(at::Tensor in0, at::Tensor in1, int n_disps, int block_
void photometric_loss_forward_kernel(at::Tensor es, at::Tensor ta, int block_size, int type, float eps, at::Tensor out);
at::Tensor photometric_loss_forward(at::Tensor es, at::Tensor ta, int block_size, int type, float eps) {
CHECK_INPUT_CUDA(es)
CHECK_INPUT_CUDA(ta)
CHECK_INPUT_CUDA(es);
CHECK_INPUT_CUDA(ta);
auto batch_size = es.size(0);
auto height = es.size(2);
@@ -107,9 +107,9 @@ at::Tensor photometric_loss_forward(at::Tensor es, at::Tensor ta, int block_size
void photometric_loss_backward_kernel(at::Tensor es, at::Tensor ta, at::Tensor grad_out, int block_size, int type, float eps, at::Tensor grad_in);
at::Tensor photometric_loss_backward(at::Tensor es, at::Tensor ta, at::Tensor grad_out, int block_size, int type, float eps) {
CHECK_INPUT_CUDA(es)
CHECK_INPUT_CUDA(ta)
CHECK_INPUT_CUDA(grad_out)
CHECK_INPUT_CUDA(es);
CHECK_INPUT_CUDA(ta);
CHECK_INPUT_CUDA(grad_out);
auto batch_size = es.size(0);
auto channels = es.size(1);
torchext/setup.py
-3
View File
@@ -8,9 +8,6 @@ include_dirs = [
]
nvcc_args = [
'-arch=sm_30',
'-gencode=arch=compute_30,code=sm_30',
'-gencode=arch=compute_35,code=sm_35',
]
setup(