Volumetric Human Teleportation (SIGGRAPH 2020 Real-Time Live) Monocular Real-Time Volumetric Performance Capture(ECCV 2020)
Home Page: https://project-splinter.github.io/
License: Other
Attempted to run in on Google Colab:
Not finding get_cfg_defaults or Monoport
Traceback (most recent call last):
File "RTL/main.py", line 19, in
from monoport.lib.common.config import get_cfg_defaults
ModuleNotFoundError: No module named 'monoport'
Traceback (most recent call last):
File "RTL/main.py", line 19, in
from monoport.lib.common.config import get_cfg_defaults
ModuleNotFoundError: No module named 'monoport'
Traceback (most recent call last):
File "RTL/main.py", line 19, in
from monoport.lib.common.config import get_cfg_defaults
ModuleNotFoundError: No module named 'monoport'
When I've configured it, the running code prompts me to open the web page, but when I open page on the Web Server, I get an error message. I tried to add MESA_L_VERSION_OVERRIDE=3.3 in the running line, my page can be opened without error, but the page is still in the state of "waiting for ··". How can I solve this problem?
The print log is as follows:
loading networkG from ./data/PIFu/net_G ...
loading networkC from ./data/PIFu/net_C ...
initialize data streamer ...
Using cache found in /root/.cache/torch/hub/NVIDIA_DeepLearningExamples_torchhub
Using cache found in /root/.cache/torch/hub/NVIDIA_DeepLearningExamples_torchhub
***********************************************
* Serving Flask app "main" (lazy loading)
* Environment: production
WARNING: This is a development server. Do not use it in a production deployment.
Use a production WSGI server instead.
* Debug mode: on
* Running on http://0.0.0.0:5555/ (Press CTRL+C to quit)
172.17.0.1 - - [10/Oct/2020 10:36:04] "GET / HTTP/1.1" 200 -
172.17.0.1 - - [10/Oct/2020 10:36:48] "GET /favicon.ico HTTP/1.1" 404 -
0it [00:00, ?it/s]
172.17.0.1 - - [10/Oct/2020 10:36:48] "GET /video_feed HTTP/1.1" 200 -
172.17.0.1 - - [10/Oct/2020 10:40:48] "GET / HTTP/1.1" 200 -
172.17.0.1 - - [10/Oct/2020 10:41:47] "GET /favicon.ico HTTP/1.1" 404 -
0it [00:00, ?it/s]
172.17.0.1 - - [10/Oct/2020 10:41:47] "GET /video_feed HTTP/1.1" 200 -
Error; freeglut (foo): failed to open display ''
@zhouliuling
i have the same problem, and add MESA_GL_VERSION_OVERRIDE=3.3, the problem was disappeared.
But got another problem:
OpenGL.error.GLError: GLError(
err = 1286,
description = b'invalid framebuffer operation',
baseOperation = glClear,
cArguments = (16640,)
have u worked it recently?
Originally posted by @jiandandian2 in #6 (comment)
ubuntu 16.04
python 3.7
torch 1.4
It keeps downloading everytime
"https://github.com/NVIDIA/DeepLearningExamples/archive/torchhub.zip" to /home/asus/.cache/torch/hub/torchhub.zip
And finally occurs the error : sus/anaconda3/envs/mo/lib/python3.7/site-packages/PIL/_imaging.cpython-37m-x86_64-linux-gnu.soAborted (core dumped)
When I've configured it, the running code prompts me to open the web page, but when I open page on the Web Server, I get an error message.I want to know how to solve this problem.Thank you very much.
When I run RTL/main.py ,there's something wrong .I think the download failed because of the network.I've located the problem here so far.
I think torch.hub.load failed.But I can download the model when I open the link(https://github.com/NVIDIA/DeepLearningExamples/archive/torchhub.zip) directly.What can I do？
hello, I meet a OpenGL mistake , how to fix it? I'll be grateful
hi,
I tried to run demo code, but it keep output black screen.
already checked camera works fine, and when I switched not to run with server, i get this error:
IndexError : too many indices for tensor of dimension 4.
checked this is caused by data_dict["render_norm"]
numpy
torch==1.8.0
torchvision
Pillow
flask
scikit-image
opencv-python
tqdm
imageio
yacs
pyopengl
imageio-ffmpeg
human-det @ git+https://github.com/Project-Splinter/human_det
human-inst-seg @ git+https://github.com/Project-Splinter/human_inst_seg
implicit-seg @ git+https://github.com/Project-Splinter/ImplicitSegCUDA
streamer-pytorch @ git+https://github.com/Project-Splinter/streamer_pytorch
Traceback (most recent call last):
File "RTL/main.py", line 19, in
from monoport.lib.common.config import get_cfg_defaults
ModuleNotFoundError: No module named 'monoport.lib'
I want .obj file from a image (like PIFu or PIFuHD demos).
If you don't mind, give me sample code or tell me how should I do.
Thank you.
Has anyone solved the issue when trying to run the RLT/main.py encounter TypeError: __init__() got an unexpected keyword argument 'weights' ? Or any suggestion to walk around this issue?
root@6d952ea9a8d1:/monoport# python RTL/main.py --use_server --ip 192.168.0.103 --port 5555 --image_folder images -- netG.ckpt_path ./data/PIFu/net_G netC.ckpt_path ./data/PIFu/net_C
loading networkG from ./data/PIFu/net_G ...
loading networkC from ./data/PIFu/net_C ...
initialize data streamer ...
Using cache found in /root/.cache/torch/hub/NVIDIA_DeepLearningExamples_torchhub
/root/.cache/torch/hub/NVIDIA_DeepLearningExamples_torchhub/PyTorch/Classification/ConvNets/image_classification/models/efficientnet.py:18: UserWarning: pytorch_quantization module not found, quantization will not be available
"pytorch_quantization module not found, quantization will not be available"
Using cache found in /root/.cache/torch/hub/NVIDIA_DeepLearningExamples_torchhub
Traceback (most recent call last):
File "RTL/main.py", line 157, in <module>
device=cuda_backbone_G, verbose=False)
File "/monoport/human_inst_seg/human_inst_seg/unet.py", line 64, in __init__
self.det_engine = Detection(device=device)
File "/monoport/human_det/human_det/ssd.py", line 23, in __init__
weights='IMAGENET1K_V1'
File "/usr/local/lib/python3.7/site-packages/torch/hub.py", line 339, in load
model = _load_local(repo_or_dir, model, *args, **kwargs)
File "/usr/local/lib/python3.7/site-packages/torch/hub.py", line 368, in _load_local
model = entry(*args, **kwargs)
File "/root/.cache/torch/hub/NVIDIA_DeepLearningExamples_torchhub/PyTorch/Detection/SSD/ssd/entrypoints.py", line 179, in nvidia_ssd
from . import model as ssd
File "/root/.cache/torch/hub/NVIDIA_DeepLearningExamples_torchhub/PyTorch/Detection/SSD/ssd/model.py", line 55, in <module>
class SSD300(nn.Module):
File "/root/.cache/torch/hub/NVIDIA_DeepLearningExamples_torchhub/PyTorch/Detection/SSD/ssd/model.py", line 56, in SSD300
def __init__(self, backbone=ResNet('resnet50')):
File "/root/.cache/torch/hub/NVIDIA_DeepLearningExamples_torchhub/PyTorch/Detection/SSD/ssd/model.py", line 30, in __init__
backbone = resnet50(weights=None if backbone_path else weights)
File "/usr/local/lib/python3.7/site-packages/torchvision/models/resnet.py", line 301, in resnet50
**kwargs)
File "/usr/local/lib/python3.7/site-packages/torchvision/models/resnet.py", line 260, in _resnet
model = ResNet(block, layers, **kwargs)
TypeError: __init__() got an unexpected keyword argument 'weights'
from implicit_seg.cuda import interp2x_boundary2d
ImportError: libtorch_cuda_cu.so: cannot open shared object file: No such file or directory
I am a beginner and I haven't understand the deployment on the server ...
Really interesting project, thanks for sharing! There are a few things that prevent this from running correctly. Currently running on Arch.
The monoport folder should be in the RTL folder, not the root directory.
requirements.txt doesn't have the specified torch and torchvision requirements. Please update it so that inconsistencies are solved.
I keep getting out of memory errors when trying to run this on an image sequence or video. I have 8GB of vram on my GPU.
Now for the questions. Does the full body need to be showing for inference to work properly? If so, any plans to change this? For example, only the chest, shoulders, and head showing in video.
How do we export the meshes into a separate file? Is this possible currently?
Thanks!
I tried to run the code but got error as shown in the pic. No idea how to solve it... Thx
Hi, In MonoPort, inappropriate dependency versioning constraints can cause risks.
Below are the dependencies and version constraints that the project is using
numpy
torch==1.4.0
torchvision
Pillow
flask
scikit-image
opencv-python
tqdm
imageio
yacs
pyopengl
imageio-ffmpeg
human-det@git+https://github.com/Project-Splinter/human_det
human-inst-seg@git+https://github.com/Project-Splinter/human_inst_seg
implicit-seg@git+https://github.com/Project-Splinter/ImplicitSegCUDA
streamer-pytorch@git+https://github.com/Project-Splinter/streamer_pytorch
The version constraint == will introduce the risk of dependency conflicts because the scope of dependencies is too strict.
The version constraint No Upper Bound and * will introduce the risk of the missing API Error because the latest version of the dependencies may remove some APIs.
After further analysis, in this project,
The version constraint of dependency numpy can be changed to >=1.8.0,<=1.23.0rc3.
The version constraint of dependency Pillow can be changed to ==9.2.0.
The version constraint of dependency Pillow can be changed to >=2.0.0,<=9.1.1.
The version constraint of dependency flask can be changed to >=0.11,<=0.12.5.
The version constraint of dependency tqdm can be changed to >=4.36.0,<=4.64.0.
The version constraint of dependency pyopengl can be changed to >=3.0.2a3,<=3.1.6.
The above modification suggestions can reduce the dependency conflicts as much as possible,
and introduce the latest version as much as possible without calling Error in the projects.
The invocation of the current project includes all the following methods.
numpy.linalg.inv numpy.linalg.norm
PIL.Image.open
flask.Flask.route flask.render_template flask.Flask json.load flask.Response flask.Flask.run
tqdm.tqdm
OpenGL.GL.glDeleteRenderbuffers OpenGL.GL.glGenFramebuffers OpenGL.GL.shaders.compileShader OpenGL.GL.glDeleteBuffers OpenGL.GL.glGenBuffers OpenGL.GL.glGenRenderbuffers OpenGL.GL.shaders.compileProgram OpenGL.GL.glDeleteTextures OpenGL.GL.glDeleteFramebuffers OpenGL.GL.glGenTextures
random.randint gl.glBlitFramebuffer glutInitWindowSize yacs.config.CfgNode.clone flask.Flask.route float.np.loadtxt.reshape colorization p1.clone.float gl.glEnableVertexAttribArray update_camera self.modules self.last_op.view intrinsic.copy.copy self.stage3 torch.nn.BatchNorm2d ord torch.rot90 numpy.sin super.__init__ motion.self.get_center_path.np.loadtxt.reshape.reshape PIFuNetCMLP.to PIFuResBlkFilters hasattr visulization torch.Tensor.to torch.nn.functional.leaky_relu monoport.lib.modeling.MonoPortNet.MonoPortNet.load_legacy_pifu self.normalize_vector torch.nn.ReflectionPad2d self._workers_status.append param.item.get gl.glViewport self._make_layer iter numpy.load.item vertex_data.append PIFuNetGMLP.to motion.self.get_center_path.np.loadtxt.reshape self.HourGlass.super.__init__ render self.renderer.get_color W.tW.W.H.tH.H.C.B.W.H.C.B.x.view.expand.contiguous.view self.SurfaceClassifier.super.__init__ dataloader.DataLoader implicit_seg.functional.Seg3dLossless OpenGL.GL.glGenFramebuffers opt_net.head.IMF.globals self._check_branches W.tW.W.H.tH.H.C.B.W.H.C.B.x.view.expand.contiguous DownSample4 self._logger.addHandler torch.cuda.is_available recon.pifu_calib Neck self._data_queue.get calib_tensor.to.to self.conv19 glob.glob z.clamp i.self.transition2 open.write torchvision.transforms.Compose self._workers.append OpenGL.GL.glGenRenderbuffers gl.glTexImage2D x.data.dim id torch.ceil cfg.netG.mean.torch.tensor.to gl.glFramebufferTexture2D numpy.concatenate torch._six.queue.Queue done_event.set torch.nn.Conv2d self.scheduler.load_state_dict normalize_v3 self._generate_network glClampColor cv2.cvtColor BaseCamera.BaseCamera.__init__ torch.Tensor setuptools.setup numpy.ones path.split cv2.UMat tuple gl.glTexParameteri gl.glUniformMatrix4fv self._logger.setLevel scene.MonoPortScene.update_camera torch.eye.unsqueeze torch.multiprocessing.get_context gl.glDrawBuffer torch.tanh map image.flip.flip Shader transition_layers.append torch.cuda.current_device os.makedirs scene.MonoPortScene self.conv1 color_data.append self.conv12 self.model numpy.random.uniform gl.glBufferData branches.append self.maxpool1 torch.ones_like gl.glTexImage2DMultisample self.normalizer motion_list_valid.append Yolov4Filters line.decode.startswith torch.nn.functional.softplus z_feat.scatter.scatter numpy.uint8 data_dict.cpu renderer.get_color.astype.clamp l self._shader.__enter__ Upsample reconEngine q.close torchvision.transforms.Normalize image_path.Image.open.convert.convert make_rotate OpenGL.GL.glDeleteFramebuffers self._get_data OpenGL.GL.shaders.compileShader self.bn1 self._next_index PIL.ImageFilter.GaussianBlur scene.make_rotate keep.nonzero.t monoport.lib.common.config.get_cfg_defaults self._logger.info calib.torch.from_numpy.unsqueeze self.down2 str mask.flip.flip self.net.train fuse_layer.append format MonoPortScene monoport.lib.modeling.MonoPortNet.MonoPortNet.eval extrinsic.np.array.reshape f logging.Formatter torch.optim.RMSprop p1.clone.clamp self.down1 gl.glDrawArrays PIFuNetCMLP torch.int64.torch.empty.random_ torch.arange self.__len__ opt_net.normalizer.IMF.globals Z.clamp.clamp torch.randn os.path.abspath human_inst_seg.Segmentation torch.no_grad glEnable numpy.eye verts.unsqueeze.repeat j.i.self.fuse_layers cv2.resize uv.unsqueeze.transpose monoport.lib.common.config.get_cfg_defaults.merge_from_list x.split self.get_texture_path self._dataset_fetcher.fetch uv.unsqueeze.unsqueeze self.get_mesh_path gl.glGenerateMipmap model.append numpy.cross netC.surface_classifier.to self.down3 logging.FileHandler.setFormatter numpy.fromstring self.filter torch.multiprocessing.get_context.Process self.last_op cv2.imread gl.glReadPixels.reshape feature.shape.feature.shape.self.num_views.feature.view.mean self.conv18 netC.image_filter.to gl.glDrawBuffers self.conv8 argparse.ArgumentParser.add_argument self.layer1 numpy.hstack self.logger.info Yolov4Filters.to netG.surface_classifier.to self._make_fuse_layers self.get_center_path gl.glReadPixels monoport.lib.render.BaseCamera.BaseCamera.get_projection_mat torch.utils.data.SequentialSampler self.conv13 self.renderer.draw self._worker_result_queue.put get_norm_layer self.get_image_path self.state_dict.update self.up.np.array.reshape calib.torch.from_numpy.unsqueeze.float logger.colorlogger load_calib torch.nn.Dropout self.image_filter.load_state_dict self._make_one_branch torch.cuda.device_count OpenGL.GL.glGenBuffers self._make_transition_layer numpy.logical_and data.to self.net.module.load_state_dict monoport.lib.render.gl.AlbedoRender.AlbedoRender.set_texture faces.reshape render_tex.torch.rot90.permute self.get_mask_path Yolov4 self.build_conv_block b_min.unsqueeze.numpy Yolov4Head self.shader.declare_uniform self.projection torch.from_numpy HRNet.init_weights conv3x3s.append math.tan next numpy.random.choice multiprocessing_context.Process.start torch.cat sdf.permute.size Uniform torch.utils.data._utils.pin_memory.pin_memory numpy.sqrt numpy.linalg.norm open.close numpy.matmul numpy.cos numpy.zeros self.conv14 self.upsample2 torch.nn.functional.avg_pool2d renderer.get_color.astype human_inst_seg.Segmentation.eval res render_norm.cpu.numpy.transpose gl.glBindTexture self.surface_classifier.load_state_dict PIL.Image.open torch.nn.Sigmoid self.vbo_list.append torch.cuda.set_device monoport.lib.modeling.geometry.orthogonal json.load torchvision.transforms.CenterCrop self.state_dict.keys self._shader_color_tex_list.append self._forward self.conv5 list torch.save self.surface_classifier self.down_conv2 self.get_calib_path PIFuHGFilters feat.to numpy.dot torch._utils.ExceptionWrapper.reraise in_img.float zip.items line.decode.decode max_c.view self.color_tex_list.append loss_func cuda_backbone_G.cfg.netG.std.torch.tensor.to.view flask.render_template line.decode.split self._try_get_data ConvBlock self.filters.append torch.utils.data._utils.signal_handling._set_worker_pids self.get_item numpy.linalg.inv self.sanity_check bytearray torchvision.transforms.ColorJitter i.self.transition1 line.split.split gl.glDeleteProgram OpenGL.GL.glDeleteTextures self._next_data glutInitDisplayMode os.path.exists torch.set_num_threads self._task_info.pop int.append self.maxpool3 monoport.lib.render.gl.AlbedoRender.AlbedoRender cuda_backbone_G.cfg.netG.mean.torch.tensor.to.view i.self.branches functools.partial cv2.imshow calib.center.reshape.projection.reshape ResBlock os.listdir torch.load calib.center.projection.reshape image_path.Image.open.convert.split gl.glVertexAttribPointer self.down5 set OpenGL.GL.shaders.compileProgram mask_path.Image.open.split self.center.np.array.reshape logging.StreamHandler.setFormatter self.shader.set_uniform utils.projection monoport.lib.modeling.MonoPortNet.MonoPortNet.filter self.optimizer.load_state_dict random.random OpenGL.GL.glDeleteBuffers MonoPortScene.update_camera self.down4 monoport.lib.render.gl.AlbedoRender.AlbedoRender.draw k.replace torch._C._log_api_usage_once torch.multiprocessing.get_context.Event monoport.lib.modeling.MonoPortNet.MonoPortNet.load_state_dict image_to_tensor cv2.rectangle numpy.flip numpy.vstack self.BasicBlock.super.__init__ self.renderer.set_attrib self.query done_event.is_set sdf.permute.permute face_uv_data.append math.sqrt DownSample1 Yolov4Filters.to.eval render_norm.cpu.numpy resolution.resolution.torch.linspace.to RBO level.str.self._modules HGFilter keep.nonzero.t.long self.conv16 _MultiProcessingDataLoaderIter self.conv17 self.net.module.state_dict self._worker_result_queue.close self.front.np.array.reshape mat.to.unsqueeze self.get_loss gl.glUniform1i render_norm.torch.rot90.permute.unsqueeze itertools.cycle tensorboardX.SummaryWriter self.optimizer.state_dict numpy.ones.detach super torch.multiprocessing.get_context.Queue torch.optim.SGD self.branches torch.zeros self._logger.debug streamer_pytorch.ImageListStreamer x_list.append face_norm_data.append torch.nn.init.kaiming_normal_ SurfaceClassifier self.scheduler.state_dict self._init_shader cv2.namedWindow setuptools.find_packages in_queue.put torch.empty torch.nn.ReplicationPad2d opt_net.backbone.IMF.globals load_calib.float self.bn3 self.Bottleneck.super.__init__ self.conv3 _InfiniteConstantSampler face_textures.reshape RuntimeError self._pin_memory_thread.join multiprocessing_context.Process.is_alive self.conv2 print DownSample3 MonoPortScene.render torch.float32.resolutions.resolutions.torch.ones.to torch.randn.to _SingleProcessDataLoaderIter self.net.parameters torch.load.float range tinyobjloader.ObjReader self.get_sampling_geo os.path.dirname downsample3.size self.stage2 sorted torch.utils.data.RandomSampler zip torch.eye self.conv9 i.str.self._modules PIFuHGFilters.to torch.linspace self.HighResolutionModule.super.__init__ _DatasetKind.create_fetcher float torch.nn.functional.interpolate gl.glActiveTexture torch.tensor.float gl.glUniform3fv self.head torch.ones self.conv6 ResnetFilter sum self.get_scale_path numpy.load OpenGL.GL.glGenTextures monoport.lib.render.gl.glcontext.create_opengl_context scaled_boxes.cpu.numpy torch.floor.long numpy.ones.cpu torch.stack modules.append torch.utils.data._utils.fetch._MapDatasetFetcher PIFuResBlkFilters.to float.np.loadtxt.reshape.mean gl.glGetUniformLocation self.DataLoader.super.__setattr__ torch.tensor.float.unsqueeze b_max.unsqueeze.numpy os.path.join streamer_pytorch.CaptureStreamer self._make_stage monoport.lib.common.config.get_cfg_defaults.merge_from_file PIFuNetGMLP multiprocessing_context.Process.join threading.Thread.start torch.optim.lr_scheduler.MultiStepLR f.read cv2.imencode gl.glClear z.size.soft_dim.z.size.torch.zeros.to Y.float torch.utils.data.BatchSampler l.view torch.nn.MaxPool2d self._make_branches self.get_translation_vector self._shutdown_workers self.get_rotation_matrix Trainer.get_default_opt image.flip.float failed_workers.append torch.int64.torch.empty.random_.item bind_func torch.nn.Tanh fuse_layers.append utils.projection.max glutInit type mask_to_tensor x_fuse.append model torch.floor renderer.get_color.astype.t keep.nonzero.t.clone in_queue.get streamer_pytorch.VideoListStreamer glutCreateWindow W.H.C.B.x.view.expand self.image_filter FBO modules.get_num_inchannels netG.image_filter.to self.add_module flask.Flask.run self.get_sample_path y.shape.y.shape.self.num_views.y.view.mean self.neek self._logger.error enumerate str.update self.ConvBlock.super.__init__ seg_engine torch.eye.to self._index_queues.append ResnetBlock data_dict.to tqdm.tqdm keep.nonzero.t.float utils.load_image self._try_put_index sdf.size.torch.arange.long self.renderer.set_texture monoport.lib.common.config.get_cfg_defaults.freeze torch.nn.Conv1d NameError self.load_state_dict self.conv10 monoport.lib.modeling.geometry.orthogonal.permute q.put torch.nn.Upsample _load_floor scene.MonoPortScene.shift_floor self.bn2 _load_intrinsic _model.state_dict.update monoport.lib.render.BaseCamera.BaseCamera self._workers_done_event.set HRNet threading.Event self.DepthNormalizer.super.__init__ pretrained_dict.items.items utils.projection.min torch.utils.data._utils.signal_handling._remove_worker_pids self._find_shader_file NotImplementedError argparse.ArgumentParser.parse_args monoport.lib.render.gl.AlbedoRender.AlbedoRender.get_color torch._utils.ExceptionWrapper gl.glBindFramebuffer torch.load.items self._logger.critical numpy.flip.tostring OpenGL.GL.glDeleteRenderbuffers cache.float.transpose worker_queue_idx.self._index_queues.put Mish torch.float32.resolutions.resolutions.torch.ones.to.clone torch.nn.Sequential torch.nn.ReLU gl.glDisableVertexAttribArray DownSample2 self._InfiniteConstantSampler.super.__init__ torch.multiprocessing.get_all_start_methods MonoPortNet self.conv_block numpy.random.shuffle torch.tensor mask.float.filter self.conv15 block numpy.array render_tex.torch.rot90.permute.unsqueeze self.ResnetBlock.super.__init__ processor random.uniform argparse.ArgumentParser face_data.append torch.utils.data._utils.fetch._IterableDatasetFetcher len DepthNormalizer torch.utils.data._utils.signal_handling._set_SIGCHLD_handler gl.glFramebufferRenderbuffer mask_to_tensor.float cv2.waitKey torch.baddbmm center.R.np.matmul.reshape self.get_motion_list numpy.ascontiguousarray monoport.lib.render.BaseCamera.BaseCamera.set_parameters layers.append self.set_parameters mask.flip.float points.repeat monoport.lib.render.gl.AlbedoRender.AlbedoRender.set_attrib labels_geo.float HighResolutionModule Z.float math.radians self._shader.__exit__ norm_data.append self.upsample1 z.size self._pin_memory_thread_done_event.set self.relu samples_geo.float DownSample5 output.input.np.hstack.astype self._SingleProcessDataLoaderIter.super.__init__ torch.nn.Sequential.state_dict self.renderer.get_color.astype self.Upsample.super.__init__ self.ResnetFilter.super.__init__ self.HGFilter.super.__init__ compute_normal image_path.Image.open.convert logging.getLogger torch.nn.DataParallel val_motions.append torch.nn.GroupNorm cfg.netG.std.torch.tensor.to torch.nn.init.constant_ thread.join numpy.identity self.downsample torchvision.transforms.ToTensor numpy.loadtxt logging.FileHandler self.stage4.size main_loop self.get_skeleton_path torch.norm self.last_layer isinstance Texture logging.StreamHandler.setLevel torch.stack.unsqueeze i.self.fuse_layers i.self.transition3 torch.nn.LeakyReLU keep.nonzero VBO uv_data.append dict gl.glReadBuffer self._MultiProcessingDataLoaderIter.super.__init__ threading.Thread sys.argv.index logging.StreamHandler join torch.optim.Adadelta q.cancel_join_thread self.conv.append feature.view easydict.EasyDict x.data.size self.conv11 self.santity_check yacs.config.CfgNode torch.optim.Adam downsample4.size X.float tinyobjloader.ObjReader.GetAttrib BatchNorm2d render_norm.torch.rot90.permute extrinsic.copy.copy numpy.array.reshape monoport.lib.modeling.MonoPortNet.MonoPortNet torch.eye.unsqueeze.to norm_layer os.path.isfile torch.Tensor.to.cpu int warnings.warn self.query.append self.stage4 torch.nn.functional.relu render_tex.cpu.numpy.transpose torch.nn.Sequential.load_state_dict ValueError MultiSampleTexture Conv_Bn_Activation globals vertices.mean.mean self.release self.maxpool2 tinyobjloader.ObjReader.ParseFromFile gl.glCheckFramebufferStatus flask.Flask logging.FileHandler.setLevel torch.nn.functional.grid_sample render_tex.cpu.numpy kwargs.items gl.glClearColor flask.Response monoport.lib.mesh_util.load_obj_mesh monoport.lib.modeling.MonoPortNet.MonoPortNet.query reference.reference.reference.np.logical_and.np.logical_and.reshape conv3x3 self._shutdown_worker random.choice Render.__init__ torch.ceil.long data_dict.cpu.numpy open torchvision.transforms.Resize attrib.vertices.np.array.reshape self.conv4 resolutions.b_max.unsqueeze.numpy.b_min.unsqueeze.numpy.query_func.Seg3dLossless.to self._pin_memory_thread.is_alive out_queue.put self.conv20 Conv2d torch.nn.ModuleList.append self._logger.warning recon.forward_vertices self.HRNet.super.__init__ self.module_list.append self.state_dict _load_extrinsic resolution.resolution.torch.linspace.to.max geometry.index torch.nn.ModuleList self.conv7 self._process_data PIFuHGFilters.to.eval glutInitWindowPosition HourGlass self.resblock gl.glRenderbufferStorageMultisample data_dict.cpu.numpy.transpose
@developer
Could please help me check this issue?
May I pull a request to fix it?
Thank you very much.
Thanks vary much to provide your codes.It takes place some errors when installing your specific libs.which operating system and which version do you run this project?
i have run install the requirments.
I search the Internet for help and know it may be the incorrect installation of pyOpenGL. However, many solutions on the Internet are based on win_amd64 platform. I wonder how to install the pyOpenGL in Ubuntu18.04 correctly?
Environments: Windows 10
How can I solve this problem?
When I tried to open this url : https://api.ngc.nvidia.com/v2/models/nvidia/ssdpyt_fp32/versions/1/files/nvidia_ssdpyt_fp32_20190225.pt in my web, I got following returns in that page:
{"requestStatus":{"statusCode":"NOT_FOUND","statusDescription":"Model not found","requestId":"11c72acd-0d81-4dc4-88cd-7e327a3f9d50"}}
Hello, I tried to run the demo with two TITAN xp GPUs(12G per GPU),but always failed when initial the human segmentation model. Here's my log.
loading networkG from ./data/PIFu/net_G ...
loading networkC from ./data/PIFu/net_C ...
initialize data streamer ...
[ WARN:0] global /tmp/pip-req-build-7m_g9lbm/opencv/modules/videoio/src/cap_v4l.cpp (893) open VIDEOIO(V4L2:/dev/video0): can't open camera by index
Using cache found in /home/pbb/.cache/torch/hub/NVIDIA_DeepLearningExamples_torchhub
Using cache found in /home/pbb/.cache/torch/hub/NVIDIA_DeepLearningExamples_torchhub
Traceback (most recent call last):
File "RTL/main.py", line 155, in
device=cuda_backbone_G, verbose=False)
File "/disk4/pbb/opensource/human_inst_seg/human_inst_seg/unet.py", line 63, in init
self.det_engine = Detection(device=device)
File "/home/pbb/.local/lib/python3.7/site-packages/human_det/ssd.py", line 22, in init
model_math='fp16' if self.fp16 else 'fp32'
File "/disk4/pbb/anaconda3/envs/MonoPort/lib/python3.7/site-packages/torch/hub.py", line 366, in load
model = entry(*args, **kwargs)
File "/home/pbb/.cache/torch/hub/NVIDIA_DeepLearningExamples_torchhub/hubconf.py", line 369, in nvidia_ssd
ckpt = torch.load(ckpt_file)
File "/disk4/pbb/anaconda3/envs/MonoPort/lib/python3.7/site-packages/torch/serialization.py", line 529, in load
return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
File "/disk4/pbb/anaconda3/envs/MonoPort/lib/python3.7/site-packages/torch/serialization.py", line 709, in _legacy_load
deserialized_objects[key].set_from_file(f, offset, f_should_read_directly)
RuntimeError: unexpected EOF, expected 85292 more bytes. The file might be corrupted.
terminate called after throwing an instance of 'c10::Error'
what(): owning_ptr == NullType::singleton() || owning_ptr->refcount.load() > 0 INTERNAL ASSERT FAILED at /pytorch/c10/util/intrusive_ptr.h:348, please report a bug to PyTorch. intrusive_ptr: Can only intrusive_ptr::reclaim() owning pointers that were created using intrusive_ptr::release(). (reclaim at /pytorch/c10/util/intrusive_ptr.h:348)
frame #0: c10::Error::Error(c10::SourceLocation, std::string const&) + 0x33 (0x7fb0f45c8193 in /disk4/pbb/anaconda3/envs/MonoPort/lib/python3.7/site-packages/torch/lib/libc10.so)
frame #1: + 0x18cd59f (0x7fb0344da59f in /disk4/pbb/anaconda3/envs/MonoPort/lib/python3.7/site-packages/torch/lib/libtorch.so)
frame #2: THStorage_free + 0x17 (0x7fb034ca2ba7 in /disk4/pbb/anaconda3/envs/MonoPort/lib/python3.7/site-packages/torch/lib/libtorch.so)
frame #3: + 0x939a17 (0x7fb0c65f8a17 in /disk4/pbb/anaconda3/envs/MonoPort/lib/python3.7/site-packages/torch/lib/libtorch_python.so)
frame #21: __libc_start_main + 0xe7 (0x7fb102f17bf7 in /lib/x86_64-linux-gnu/libc.so.6)
Aborted (core dumped)
I run it on the Google Colab, and I get this problem, do u know how to solve it? thank u
It would be very helpful to have a docker image.
I faild in install ImplicitSegCUDA
x86_64-linux-gnu-gcc -pthread -DNDEBUG -g -fwrapv -O2 -Wall -g -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 -fPIC -I/usr/local/lib/python3.7/dist-packages/torch/include -I/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include -I/usr/local/lib/python3.7/dist-packages/torch/include/TH -I/usr/local/lib/python3.7/dist-packages/torch/include/THC -I/usr/local/cuda/include -I/usr/include/python3.7m -c implicit_seg/cuda/interp2x_boundary2d.cpp -o build/temp.linux-x86_64-3.7/implicit_seg/cuda/interp2x_boundary2d.o -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=interp2x_boundary2d -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++11
/usr/local/cuda/bin/nvcc -I/usr/local/lib/python3.7/dist-packages/torch/include -I/usr/local/lib/python3.7/dist-packages/torch/include/torch/csrc/api/include -I/usr/local/lib/python3.7/dist-packages/torch/include/TH -I/usr/local/lib/python3.7/dist-packages/torch/include/THC -I/usr/local/cuda/include -I/usr/include/python3.7m -c implicit_seg/cuda/interp2x_boundary2d_kernel.cu -o build/temp.linux-x86_64-3.7/implicit_seg/cuda/interp2x_boundary2d_kernel.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options '-fPIC' -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=interp2x_boundary2d -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_75,code=sm_75 -std=c++11
In file included from /usr/local/cuda/include/cuda_runtime.h:83,
from <command-line>:
/usr/local/cuda/include/crt/host_config.h:129:2: error: #error -- unsupported GNU version! gcc versions later than 7 are not supported!
#error -- unsupported GNU version! gcc versions later than 7 are not supported!
^~~~~
error: command '/usr/local/cuda/bin/nvcc' failed with exit status 1
win10
python 3.7
I have both used the pip and git command but I fail to install it .
It has reported such errors:
ERROR:root:Internal Python error in the inspect module.
Below is the traceback from this internal error.
Traceback (most recent call last):
File "Z:\anaconda\envs\XC\lib\distutils_msvccompiler.py", line 492, in link
self.spawn([self.linker] + ld_args)
File "Z:\anaconda\envs\XC\lib\distutils_msvccompiler.py", line 502, in spawn
return super().spawn(cmd)
File "Z:\anaconda\envs\XC\lib\distutils\ccompiler.py", line 910, in spawn
spawn(cmd, dry_run=self.dry_run)
File "Z:\anaconda\envs\XC\lib\distutils\spawn.py", line 38, in spawn
_spawn_nt(cmd, search_path, dry_run=dry_run)
File "Z:\anaconda\envs\XC\lib\distutils\spawn.py", line 81, in _spawn_nt
"command %r failed with exit status %d" % (cmd, rc))
distutils.errors.DistutilsExecError: command 'C:\Program Files (x86)\Microsoft Visual Studio\2017\Community\VC\Tools\MSVC\14.16.27023\bin\HostX86\x64\link.exe' failed with exit status 1181
from implicit_seg.cuda import interp2x_boundary2d
ImportError: cannot import name 'interp2x_boundary2d'
Thanks for you sharing codes. I have a question about running. When appearing error, about freeglut (foo): failed to open display. Could you tell how to solve it? Thanks again.
my environment as follows:
ubuntu 18.04 without desktop, with server version
I have installed vncserver, xfce4, but still appeared this error
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
Django
The Web framework for perfectionists with deadlines.
Laravel
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft
Open source projects and samples from Microsoft.
Google
Google ❤️ Open Source for everyone.
Alibaba
Alibaba Open Source for everyone
D3
Data-Driven Documents codes.
Tencent
China tencent open source team.