lxx1991 / vs-reid Goto Github PK
View Code? Open in Web Editor NEWVideo Object Segmentation with Re-identification
License: BSD 2-Clause "Simplified" License
Video Object Segmentation with Re-identification
License: BSD 2-Clause "Simplified" License
"After download, you need to remove the color-map from annotations."
Hello, thank you for publishing the source code. Can you tell me what this step is for? Remove the color-map from annotations, what are the annotations next?
I have tried to run davis_test by following your instruction. I would like to know, how much memory this one need for running? My GPU is 1080ti x2
I have encountered the problem out of memory at predict function, not even changing frame_fr_dir from full-resolution to training images. The error is:
THCudaCheck FAIL file=/opt/conda/conda-bld/pytorch_1525909934016/work/aten/src/THC/generic/THCStorage.cu line=58 error=2 : out of memory
Traceback (most recent call last):
File "davis_test.py", line 518, in
main()
File "davis_test.py", line 421, in main
predict(1, frames_num, 1, range(instance_num))
File "davis_test.py", line 88, in predict
prob = model(image_patch, flow_patch, warp_label_patch)
File "/home/watt/anaconda2/envs/emask/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in call
result = self.forward(*input, **kwargs)
File "/home/watt/workspace/pytorch/vs-reid/core/models/MP2S.py", line 131, in forward
x = self.backbone(x, p)
File "/home/watt/anaconda2/envs/emask/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in call
result = self.forward(*input, **kwargs)
File "/home/watt/workspace/pytorch/vs-reid/core/models/backbones/sense_resnet.py", line 150, in forward
x = self.layer4(x)
File "/home/watt/anaconda2/envs/emask/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in call
result = self.forward(*input, **kwargs)
File "/home/watt/anaconda2/envs/emask/lib/python3.6/site-packages/torch/nn/modules/container.py", line 91, in forward
input = module(input)
File "/home/watt/anaconda2/envs/emask/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in call
result = self.forward(*input, **kwargs)
File "/home/watt/workspace/pytorch/vs-reid/core/models/backbones/sense_resnet.py", line 73, in forward
residual = self.downsample(x)
File "/home/watt/anaconda2/envs/emask/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in call
result = self.forward(*input, **kwargs)
File "/home/watt/anaconda2/envs/emask/lib/python3.6/site-packages/torch/nn/modules/container.py", line 91, in forward
input = module(input)
File "/home/watt/anaconda2/envs/emask/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in call
result = self.forward(*input, **kwargs)
File "/home/watt/anaconda2/envs/emask/lib/python3.6/site-packages/torch/nn/modules/batchnorm.py", line 49, in forward
self.training or not self.track_running_stats, self.momentum, self.eps)
File "/home/watt/anaconda2/envs/emask/lib/python3.6/site-packages/torch/nn/functional.py", line 1194, in batch_norm
training, momentum, eps, torch.backends.cudnn.enabled
RuntimeError: cuda runtime error (2) : out of memory at /opt/conda/conda-bld/pytorch_1525909934016/work/aten/src/THC/generic/THCStorage.cu:58
File "davis_test.py", line 8, in
from core import models
This is after running the code on DAVIS test set.
result = prob_to_label(combine_prob(pred_prob[th]))
File "/media/abhishek/Data1/src_codes/VS-ReID/core/utils/bbox.py", line 46, in combine_prob
temp_prob[..., i] = prob[..., i * 2 - 1]
ValueError: could not broadcast input array from shape (480,854,3) into shape (480,854)
Hi, there.
How can I get the 'Guided Probability Map' mentioned in your paper, if I use my own video sequence.
can you please me with the generation of .flo and .rflo files. I tried visiting https://github.com/lmb-freiburg/flownet2 but i don't think they provide it for windows. Can you refer me with some other repos from where i can generate these files. I also tried https://github.com/NVIDIA/flownet2-pytorch/blob/master/run_a_pair.py but they generate only .flo files.
Hi again,
Could you perhaps give a look at the following error and say if it makes any sense to you. This shows up for the last instance..rest of them goes fine
main()
File "/media/abhishek/Data1/src_codes/VS-ReID/davis_test.py", line 405, in main
person_reid[th][i] = person_reid[th][i][:, [0, 1, 2, 3, 5]]
IndexError: list index out of range
Ask a stupid question: '.flo' means optical flow image,what does '.rflo' mean? And how to generate it?
I removed color map from annotations. Also generated bidirectional flow for DAVIS JPEGIMAGES folder.
I am getting following error when I try to test for test_dev list -
=> loading checkpoint 'models/MP2S.pth.tar'
=> loaded checkpoint
Traceback (most recent call last):
File "davis_test.py", line 516, in <module>
main()
File "davis_test.py", line 399, in main
pred_prob[th] = label_to_prob(np.zeros_like(label_0, np.uint8), instance_num)
File "~/VS-ReID/core/utils/bbox.py", line 35, in label_to_prob
prob = np.zeros(label.shape + (channels * 2, ))
MemoryError
When I checked GPU(Titan X) usage it is using only:
| NVIDIA-SMI 384.130 Driver Version: 384.130 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
|===============================+======================+======================|
| 0 GeForce GTX 108... Off | 00000000:01:00.0 Off | N/A |
| 23% 38C P8 10W / 250W | 1169MiB / 11171MiB | 0% Default |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: GPU Memory |
| GPU PID Type Process name Usage |
|=============================================================================|
| 0 25396 C python3 1159MiB |
+-----------------------------------------------------------------------------+
Can you suggest what is going wrong? I assume it is not using gpu memory to full extent.
Hi,
I am getting following error while trying to run test_dev from DAVIS dataset. I have generated bi-directional flows and also removed color map from annotations earlier.
=> loading checkpoint 'models/MP2S.pth.tar'
=> loaded checkpoint
Traceback (most recent call last):
File "davis_test.py", line 516, in
main()
File "davis_test.py", line 419, in main
predict(1, frames_num, 1, range(instance_num))
File "davis_test.py", line 50, in predict
warp_prob = flo.get_warp_label(flow1[th - 1], flow2[th], combine_prob(pred_prob[th - 1]))
File "~/VS-ReID/core/utils/flow.py", line 52, in get_warp_label
label2[valid, :] = label1[dx[valid].round().astype(int), dy[valid].round().astype(int), :]
IndexError: index 480 is out of bounds for axis 0 with size 480
Can you suggest what is happening?
Hi, are all the results for classification, object search and person search the ones you use for the challenge? I tested them with optical flow results from PWC-Net and got a mean J&F score around 0.65. There is still a huge gap to 0.73, which you got in the challenge.
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.