diff --git a/readme.md b/readme.md
index f503221..f3ec6af 100644
--- a/readme.md
+++ b/readme.md
@@ -32,6 +32,7 @@ The network training/evaluation code is based on `Pytorch`.
 PyTorch>=1.1
 Cuda>=10.0
 ```
+Updated on 07.06.2021: The code is now compatible with the latest Pytorch version (1.8).
 
 The other python packages can be installed with `anaconda`:
 ```
@@ -65,11 +66,12 @@ python setup.py build_ext --inplace
 ## Running
 
 
-### Creating synthetic data
+### Creating Synthetic Data
 To create synthetic data and save it locally, download [ShapeNet V2](https://www.shapenet.org/) and correct `SHAPENET_ROOT` in `config.json`. Then the data can be generated and saved to `DATA_ROOT` in `config.json` by running
 ```
 ./create_syn_data.sh
 ```
+If you are only interested in evaluating our pre-trained model, [here (3.7G)](https://s3.eu-central-1.amazonaws.com/avg-projects/connecting_the_dots/val_data.zip) is a validation set that contains a small amount of images.
 
 ### Training Network
 
@@ -90,6 +92,15 @@ To evaluate a specific checkpoint, e.g. the 50th epoch, one can run
 python train_val.py --cmd retest --epoch 50
 ```
 
+### Evaluating a Pre-trained Model
+We provide a model pre-trained using the photometric loss. Once you have prepared the synthetic dataset and changed `DATA_ROOT` in `config.json`, the pre-trained model can be evaluated on the validation set by running:
+```
+mkdir -p output
+mkdir -p output/exp_syn
+wget -O output/exp_syn/net_0099.params https://s3.eu-central-1.amazonaws.com/avg-projects/connecting_the_dots/net_0099.params
+python train_val.py --cmd retest --epoch 99
+```
+You can also download our validation set from [here (3.7G)](https://s3.eu-central-1.amazonaws.com/avg-projects/connecting_the_dots/val_data.zip).
 
 ## Acknowledgement 
 This work was supported by the Intel Network on Intelligent Systems.
diff --git a/renderer/Makefile b/renderer/Makefile
index ed59b34..c5b85a5 100644
--- a/renderer/Makefile
+++ b/renderer/Makefile
@@ -4,7 +4,7 @@ C_FLAGS = -O3 -msse -msse2 -msse3 -msse4.2 -fPIC -Wall
 CXX = g++ -c
 CXX_FLAGS = -O3 -std=c++11 -msse -msse2 -msse3 -msse4.2 -fPIC -Wall
 CUDA = nvcc -c
-CUDA_FLAGS = -x cu -Xcompiler -fPIC -arch=sm_30 -std=c++11 --expt-extended-lambda
+CUDA_FLAGS = -x cu -Xcompiler -fPIC -std=c++11 --expt-extended-lambda
 
 
 PYRENDER_DEPENDENCIES = setup.py \
diff --git a/torchext/ext/ext_cpu.cpp b/torchext/ext/ext_cpu.cpp
index ca4c795..436f2a2 100644
--- a/torchext/ext/ext_cpu.cpp
+++ b/torchext/ext/ext_cpu.cpp
@@ -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", ([&] {
diff --git a/torchext/ext/ext_cuda.cpp b/torchext/ext/ext_cuda.cpp
index d98c9d6..d6c93ca 100644
--- a/torchext/ext/ext_cuda.cpp
+++ b/torchext/ext/ext_cuda.cpp
@@ -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);
diff --git a/torchext/setup.py b/torchext/setup.py
index bde6e37..4d89756 100644
--- a/torchext/setup.py
+++ b/torchext/setup.py
@@ -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(