gd2016229035 / faster-rcnn-rgbd Goto Github PK
View Code? Open in Web Editor NEWTwo stream Faster-RCNN evaluated on NYU Depth V2 dataset for RGBD object detection task.
License: Other
Two stream Faster-RCNN evaluated on NYU Depth V2 dataset for RGBD object detection task.
License: Other
in ur utils/array_tool.py, you use t._TensorBase
but when I run the code, it turns wrong and pops up:
AttributeError: module 'torch' has no attribute '_TensorBase'
Hello,
When I run train.sh script, I get this error. Can someone tell me why this is happening?
My guess is that since there is no unet_models.py file, rather only its compiled .pyc version, I am getting this error. How do I fix this?
there is a problem in line 248 of trainer.py:
meter.add(loss_d[key])
TypeError: can't convert CUDA tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.
how to solve it?
Hello,
I have some problem about dataloader.
Could someone gave me some help?
$ python3 train.py train --env='fasterrcnn' --plot-every=20
======user config========
{'caffe_pretrain': False,
'caffe_pretrain_path': './vgg16_caffe.pth',
'concat_layer': 1,
'data': 'voc',
'debug_file': '/tmp/debugf',
'env': 'fasterrcnn',
'epoch': 13,
'load_depth_extimater': '../depth_etimation/model_best.pth_L2_U-net_vgg11.tar',
'load_depth_path': None,
'load_head': None,
'load_path': None,
'load_rgb_path': None,
'load_rpn': None,
'lr': 0.001,
'lr_decay': 0.1,
'max_size': 1000,
'min_size': 600,
'num_workers': 4,
'plot_every': 20,
'port': 8097,
'pretrained_model': 'vgg16',
'roi_sigma': 1.0,
'rpn_sigma': 3.0,
'test_num': 10000,
'test_num_workers': 4,
'use_adam': False,
'use_chainer': False,
'use_drop': False,
'voc_data_dir': '/home/jiou/faster-rcnn-rgbd/faster-rcnn-rgbd/NYUv2/',
'weight_decay': 0.0005}
==========end============
load data
model construct completed
Traceback (most recent call last):
File "train.py", line 150, in
fire.Fire()
File "/home/jiou/.local/lib/python3.5/site-packages/fire/core.py", line 127, in Fire
component_trace = _Fire(component, args, context, name)
File "/home/jiou/.local/lib/python3.5/site-packages/fire/core.py", line 366, in Fire
component, remaining_args)
File "/home/jiou/.local/lib/python3.5/site-packages/fire/core.py", line 542, in CallCallable
result = fn(*varargs, **kwargs)
File "train.py", line 84, in train
for ii, (img, img_depth, bbox, label, scale) in tqdm(enumerate(dataloader)):
File "/usr/local/lib/python3.5/dist-packages/tqdm/_tqdm.py", line 953, in iter
for obj in iterable:
File "/usr/local/lib/python3.5/dist-packages/torch/utils/data/dataloader.py", line 286, in next
return self._process_next_batch(batch)
File "/usr/local/lib/python3.5/dist-packages/torch/utils/data/dataloader.py", line 307, in _process_next_batch
raise batch.exc_type(batch.exc_msg)
ValueError: Traceback (most recent call last):
File "/usr/local/lib/python3.5/dist-packages/torch/utils/data/dataloader.py", line 57, in _worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/usr/local/lib/python3.5/dist-packages/torch/utils/data/dataloader.py", line 57, in
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/jiou/faster-rcnn-rgbd/faster-rcnn-rgbd/data/dataset.py", line 160, in getitem
ori_img, ori_img_depth, bbox, label, difficult = self.db.get_example(idx)
File "/home/jiou/faster-rcnn-rgbd/faster-rcnn-rgbd/data/voc_dataset.py", line 145, in get_example
label = np.stack(label).astype(np.int32)
File "/usr/local/lib/python3.5/dist-packages/numpy/core/shape_base.py", line 349, in stack
raise ValueError('need at least one array to stack')
ValueError: need at least one array to stack
Hello,
Can anyone explain me what are the functions of the following operators?
b43e1a358b5853ffb749ac931c9cd97a6dccf862
Thanks.
I understand that I can get RGB or depth results by simply changing line 127 in $data/voc_dataset.py. However, I do not know how to get the RGBD results. I would appreciate if you could help me out.
Thanks.
Hello,
Can you share converted version of nyu depth v2 dataset or code for conversion?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ 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. ๐๐๐
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 โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.