sjingjia / planerectr Goto Github PK
View Code? Open in Web Editor NEWPlaneRecTR: Unified Query Learning for 3D Plane Recovery from a Single View
License: Apache License 2.0
PlaneRecTR: Unified Query Learning for 3D Plane Recovery from a Single View
License: Apache License 2.0
Hello, I found self.losses
contains ['labels', 'masks', 'plane_depths', 'params', 'Q', 'plane_depths'], I don't understand the meaning of loss_Q. Did the paper mention this loss? Thanks for your effort.
I went through the code but I am still confused if there are anything more needed than segmented and depth image to generate .ply file. Also, can you mention where to input my own segmented and depth image instead of the one generated by your network?
Cannot Inference on these pretrained models: PlaneRecTR_swinb_pretrained.pth & PlaneRecTR_hrnet32_pretrained.pth
Traceback (most recent call last):
File "/workspace/hardik/PlaneRecTR/demo/demo.py", line 211, in <module>
predictions = demo.run_on_image(img)
^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/hardik/PlaneRecTR/demo/predictor.py", line 54, in run_on_image
predictions = self.predictor(image)
^^^^^^^^^^^^^^^^^^^^^
File "/workspace/hardik/PlaneRecTR/detectron2/detectron2/engine/defaults.py", line 319, in __call__
predictions = self.model([inputs])[0]
^^^^^^^^^^^^^^^^^^^^
File "/root/anaconda3/envs/planerectr/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/anaconda3/envs/planerectr/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/hardik/PlaneRecTR/demo/../PlaneRecTR/PlaneRecTR_model.py", line 299, in forward
plane_seg, inferred_planes_depth, inferred_seg_depth, valid_param = retry_if_cuda_oom(self.plane_inference)(mask_cls_result, mask_pred_result, param_pred_result, depth_pred_result)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/hardik/PlaneRecTR/detectron2/detectron2/utils/memory.py", line 70, in wrapped
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/workspace/hardik/PlaneRecTR/demo/../PlaneRecTR/PlaneRecTR_model.py", line 367, in plane_inference
inferred_seg_depth = (segmentation * valid_depth_pred).sum(0) # [h, w]
~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~
RuntimeError: The size of tensor a (256) must match the size of tensor b (1088) at non-singleton dimension 2
Hi, Thank you for the great work. Would you please share the inference script of PlaneRecTR? I would like to test your work on my own image. Thanks!
Hi, thanks for the good work. When I downloaded tfrecords data from PlaneNet, and then ran the commands to convert it to npz data and generate json files required by detectron2, I met the following error. How can I solve it? Thanks!
...
...
18899
18999
19099
19199
19299
Traceback (most recent call last):
File "/home/zlq/anaconda3/envs/planerectr/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 1365, in _do_call
return fn(*args)
File "/home/zlq/anaconda3/envs/planerectr/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 1350, in _run_fn
target_list, run_metadata)
File "/home/zlq/anaconda3/envs/planerectr/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 1443, in _call_tf_sessionrun
run_metadata)
tensorflow.python.framework.errors_impl.OutOfRangeError: FIFOQueue '_2_batch/fifo_queue' is closed and has insufficient elements (requested 1, current size 0)
[[{{node batch}}]]
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "data_tools/convert_tfrecords.py", line 59, in
img, gt_dict = sess.run([img_inp_train, global_gt_dict_train])
File "/home/zlq/anaconda3/envs/planerectr/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 956, in run
run_metadata_ptr)
File "/home/zlq/anaconda3/envs/planerectr/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 1180, in _run
feed_dict_tensor, options, run_metadata)
File "/home/zlq/anaconda3/envs/planerectr/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 1359, in _do_run
run_metadata)
File "/home/zlq/anaconda3/envs/planerectr/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 1384, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.OutOfRangeError: FIFOQueue '_2_batch/fifo_queue' is closed and has insufficient elements (requested 1, current size 0)
[[node batch (defined at /home/zlq/anaconda3/envs/planerectr/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py:1748) ]]
Original stack trace for 'batch':
File "data_tools/convert_tfrecords.py", line 46, in
img_inp_train, global_gt_dict_train, local_gt_dict_train = reader_train.getBatch(filename_queue_train, batchSize=1, getLocal=True)
File "/home/zlq/code/PlaneRecTR/PlanarReconstruction/data_tools/RecordReaderAll.py", line 62, in getBatch
tf.train.batch([image, planes, depth, normal, semantics, segmentation, boundary, numPlanes, features['image_path'], features['info']], batch_size=batchSize, capacity=(NUM_THREADS + 2) * batchSize, num_threads=1)
File "/home/zlq/anaconda3/envs/planerectr/lib/python3.7/site-packages/tensorflow_core/python/util/deprecation.py", line 324, in new_func
return func(*args, **kwargs)
File "/home/zlq/anaconda3/envs/planerectr/lib/python3.7/site-packages/tensorflow_core/python/training/input.py", line 1020, in batch
name=name)
File "/home/zlq/anaconda3/envs/planerectr/lib/python3.7/site-packages/tensorflow_core/python/training/input.py", line 789, in _batch
dequeued = queue.dequeue_many(batch_size, name=name)
File "/home/zlq/anaconda3/envs/planerectr/lib/python3.7/site-packages/tensorflow_core/python/ops/data_flow_ops.py", line 489, in dequeue_many
self._queue_ref, n=n, component_types=self._dtypes, name=name)
File "/home/zlq/anaconda3/envs/planerectr/lib/python3.7/site-packages/tensorflow_core/python/ops/gen_data_flow_ops.py", line 3862, in queue_dequeue_many_v2
timeout_ms=timeout_ms, name=name)
File "/home/zlq/anaconda3/envs/planerectr/lib/python3.7/site-packages/tensorflow_core/python/framework/op_def_library.py", line 794, in _apply_op_helper
op_def=op_def)
File "/home/zlq/anaconda3/envs/planerectr/lib/python3.7/site-packages/tensorflow_core/python/util/deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "/home/zlq/anaconda3/envs/planerectr/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py", line 3357, in create_op
attrs, op_def, compute_device)
File "/home/zlq/anaconda3/envs/planerectr/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py", line 3426, in _create_op_internal
op_def=op_def)
File "/home/zlq/anaconda3/envs/planerectr/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py", line 1748, in init
self._traceback = tf_stack.extract_stack()
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 is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
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.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.