Skip to content

Create the CCR_version1. #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Inoriros wants to merge 1 commit into
base: old
Choose a base branch
from
Open

Create the CCR_version1. #3

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 1 addition & 2 deletions models/autoencoder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,6 @@

from .encoders import *
from .diffusion import *
import open3d as o3d


class AutoEncoder(Module):
Expand Down Expand Up @@ -77,7 +76,7 @@ def decode(self, code, num_points, flexibility=0.0, ret_traj=False):

def get_loss(self, x, img):
PtsNum_ori = x.size(dim=1)
input_num_points = int(x.size(dim=1)/10)
input_num_points = int(x.size(dim=1)/self.args.input_downsample)
pcd_sameNum_list = list(np.linspace(0, PtsNum_ori-1, input_num_points).round().astype(int))
x_input = x[:, pcd_sameNum_list, :]

Expand Down
75 changes: 75 additions & 0 deletions run_train_input_downsample_10_v100.script
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,75 @@
#!/bin/sh
################################### Start of SLRUM Script ###################################

################################### Select your cluster ###################################
###SBATCH --cluster=ub-hpc
#SBATCH --cluster=faculty

## Select your partition
#SBATCH --partition=scavenger --qos=scavenger

################################### Set your running time ###################################
#SBATCH --time=48:00:00
#SBATCH --nodes=1
#SBATCH --ntasks-per-node=8

################################### Select your GPU ###################################
## Use snodes command to check their status first
#SBATCH --gres=gpu:tesla_v100-pcie-32gb:1
##SBATCH --gres=gpu:tesla_v100-pcie-16gb:1
###SBATCH --gres=gpu:a100-pcie-40gb:1


################################### Set your memory ###################################
#SBATCH --mem=32768
# Memory per node specification is in MB. It is optional.
# The default limit is 3000MB per core.

################################### Set your job name ###################################
#SBATCH --job-name="super_map_train_input_downsample_10"

## Set output name (not work very well right now)
### SBATCH --output= "result_$(date +"%Y_%m_%d_%k_%M_%S").out"

############################ Set the email to receive email #############################
#SBATCH --mail-user=yidu@buffalo.edu
#SBATCH --mail-type=ALL
##SBATCH --requeue
#Specifies that the job will be requeued after a node failure.
#The default is that the job will not be requeued.


################### Beginning of your scipt, it is written with shell ####################

echo "SLURM_JOBID="$SLURM_JOBID
echo "SLURM_TIME="$(date +"%Y_%m_%d_%k_%M_%S")

echo "SLURM_JOB_NODELIST"=$SLURM_JOB_NODELIST
echo "SLURM_NNODES"=$SLURM_NNODES
echo "SLURMTMPDIR="$SLURMTMPDIR

echo "working directory = "$SLURM_SUBMIT_DIR


# module use /projects/academic/cwx/modulefiles
# module load python/my-python-3
source ~/.bashrc
conda activate supermap

## List the module your are using
module list
ulimit -s unlimited

which python
which pytest

nvidia-smi


cat run_train_input_downsample_10_v100.script


python train_ae.py --dataset_path '/user/yidu/projects/yidu/super_map/super_map_point_based_one_branch/data/shapenet_oneTraj_50000pts.hdf5' --latent_dim 64 --input_downsample 10 --run_name 'TwoBranch' --project_name 'Super-Map-Project-SmallDataset'


################################### End of SLRUM Script ###################################
75 changes: 75 additions & 0 deletions run_train_input_downsample_2_latent1024_v100.script
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,75 @@
#!/bin/sh
################################### Start of SLRUM Script ###################################

################################### Select your cluster ###################################
###SBATCH --cluster=ub-hpc
#SBATCH --cluster=faculty

## Select your partition
#SBATCH --partition=scavenger --qos=scavenger

################################### Set your running time ###################################
#SBATCH --time=48:00:00
#SBATCH --nodes=1
#SBATCH --ntasks-per-node=8

################################### Select your GPU ###################################
## Use snodes command to check their status first
#SBATCH --gres=gpu:tesla_v100-pcie-32gb:1
##SBATCH --gres=gpu:tesla_v100-pcie-16gb:1
###SBATCH --gres=gpu:a100-pcie-40gb:1


################################### Set your memory ###################################
#SBATCH --mem=32768
# Memory per node specification is in MB. It is optional.
# The default limit is 3000MB per core.

################################### Set your job name ###################################
#SBATCH --job-name="super_map_train_input_downsample_2_latent1024"

## Set output name (not work very well right now)
### SBATCH --output= "result_$(date +"%Y_%m_%d_%k_%M_%S").out"

############################ Set the email to receive email #############################
#SBATCH --mail-user=yidu@buffalo.edu
#SBATCH --mail-type=ALL
##SBATCH --requeue
#Specifies that the job will be requeued after a node failure.
#The default is that the job will not be requeued.


################### Beginning of your scipt, it is written with shell ####################

echo "SLURM_JOBID="$SLURM_JOBID
echo "SLURM_TIME="$(date +"%Y_%m_%d_%k_%M_%S")

echo "SLURM_JOB_NODELIST"=$SLURM_JOB_NODELIST
echo "SLURM_NNODES"=$SLURM_NNODES
echo "SLURMTMPDIR="$SLURMTMPDIR

echo "working directory = "$SLURM_SUBMIT_DIR


# module use /projects/academic/cwx/modulefiles
# module load python/my-python-3
source ~/.bashrc
conda activate supermap

## List the module your are using
module list
ulimit -s unlimited

which python
which pytest

nvidia-smi


cat run_train_input_downsample_2_latent1024_v100.script


python train_ae.py --dataset_path '/user/yidu/projects/yidu/super_map/super_map_point_based_one_branch/data/shapenet_oneTraj_50000pts.hdf5' --latent_dim 1024 --input_downsample 2 --run_name 'TwoBranch' --project_name 'Super-Map-Project-SmallDataset'


################################### End of SLRUM Script ###################################
75 changes: 75 additions & 0 deletions run_train_input_downsample_2_latent256_v100.script
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,75 @@
#!/bin/sh
################################### Start of SLRUM Script ###################################

################################### Select your cluster ###################################
###SBATCH --cluster=ub-hpc
#SBATCH --cluster=faculty

## Select your partition
#SBATCH --partition=scavenger --qos=scavenger

################################### Set your running time ###################################
#SBATCH --time=48:00:00
#SBATCH --nodes=1
#SBATCH --ntasks-per-node=8

################################### Select your GPU ###################################
## Use snodes command to check their status first
#SBATCH --gres=gpu:tesla_v100-pcie-32gb:1
##SBATCH --gres=gpu:tesla_v100-pcie-16gb:1
###SBATCH --gres=gpu:a100-pcie-40gb:1


################################### Set your memory ###################################
#SBATCH --mem=32768
# Memory per node specification is in MB. It is optional.
# The default limit is 3000MB per core.

################################### Set your job name ###################################
#SBATCH --job-name="super_map_train_input_downsample_2_latent256"

## Set output name (not work very well right now)
### SBATCH --output= "result_$(date +"%Y_%m_%d_%k_%M_%S").out"

############################ Set the email to receive email #############################
#SBATCH --mail-user=yidu@buffalo.edu
#SBATCH --mail-type=ALL
##SBATCH --requeue
#Specifies that the job will be requeued after a node failure.
#The default is that the job will not be requeued.


################### Beginning of your scipt, it is written with shell ####################

echo "SLURM_JOBID="$SLURM_JOBID
echo "SLURM_TIME="$(date +"%Y_%m_%d_%k_%M_%S")

echo "SLURM_JOB_NODELIST"=$SLURM_JOB_NODELIST
echo "SLURM_NNODES"=$SLURM_NNODES
echo "SLURMTMPDIR="$SLURMTMPDIR

echo "working directory = "$SLURM_SUBMIT_DIR


# module use /projects/academic/cwx/modulefiles
# module load python/my-python-3
source ~/.bashrc
conda activate supermap

## List the module your are using
module list
ulimit -s unlimited

which python
which pytest

nvidia-smi


cat run_train_input_downsample_2_latent256_v100.script


python train_ae.py --dataset_path '/user/yidu/projects/yidu/super_map/super_map_point_based_one_branch/data/shapenet_oneTraj_50000pts.hdf5' --latent_dim 256 --input_downsample 2 --run_name 'TwoBranch' --project_name 'Super-Map-Project-SmallDataset'


################################### End of SLRUM Script ###################################
75 changes: 75 additions & 0 deletions run_train_input_downsample_2_latent64_v100.script
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,75 @@
#!/bin/sh
################################### Start of SLRUM Script ###################################

################################### Select your cluster ###################################
###SBATCH --cluster=ub-hpc
#SBATCH --cluster=faculty

## Select your partition
#SBATCH --partition=scavenger --qos=scavenger

################################### Set your running time ###################################
#SBATCH --time=48:00:00
#SBATCH --nodes=1
#SBATCH --ntasks-per-node=8

################################### Select your GPU ###################################
## Use snodes command to check their status first
#SBATCH --gres=gpu:tesla_v100-pcie-32gb:1
##SBATCH --gres=gpu:tesla_v100-pcie-16gb:1
###SBATCH --gres=gpu:a100-pcie-40gb:1


################################### Set your memory ###################################
#SBATCH --mem=32768
# Memory per node specification is in MB. It is optional.
# The default limit is 3000MB per core.

################################### Set your job name ###################################
#SBATCH --job-name="super_map_train_input_downsample_2_latent64"

## Set output name (not work very well right now)
### SBATCH --output= "result_$(date +"%Y_%m_%d_%k_%M_%S").out"

############################ Set the email to receive email #############################
#SBATCH --mail-user=yidu@buffalo.edu
#SBATCH --mail-type=ALL
##SBATCH --requeue
#Specifies that the job will be requeued after a node failure.
#The default is that the job will not be requeued.


################### Beginning of your scipt, it is written with shell ####################

echo "SLURM_JOBID="$SLURM_JOBID
echo "SLURM_TIME="$(date +"%Y_%m_%d_%k_%M_%S")

echo "SLURM_JOB_NODELIST"=$SLURM_JOB_NODELIST
echo "SLURM_NNODES"=$SLURM_NNODES
echo "SLURMTMPDIR="$SLURMTMPDIR

echo "working directory = "$SLURM_SUBMIT_DIR


# module use /projects/academic/cwx/modulefiles
# module load python/my-python-3
source ~/.bashrc
conda activate supermap

## List the module your are using
module list
ulimit -s unlimited

which python
which pytest

nvidia-smi


cat run_train_input_downsample_2_latent64_v100.script


python train_ae.py --dataset_path '/user/yidu/projects/yidu/super_map/super_map_point_based_one_branch/data/shapenet_oneTraj_50000pts.hdf5' --latent_dim 64 --input_downsample 2 --run_name 'TwoBranch' --project_name 'Super-Map-Project-SmallDataset'


################################### End of SLRUM Script ###################################
Loading