Pascal VOC dataset #2

fmassa · 2016-11-10T18:55:20Z

FYI, I started writing a simple Pascal VOC dataset class.
https://github.com/fmassa/vision/tree/voc_dataset

szagoruyko · 2016-11-28T13:23:43Z

@fmassa don't think you need that, coco is already there and supports VOC json

fmassa · 2016-11-28T13:37:25Z

@szagoruyko in this case, we should provide a converter from VOC format to COCO format. But this might be better than writing a new (almost reduntant) class.
Also, I was updating the code, and we could use a TargetTransformer to convert between different formats.

acgtyrant · 2017-04-21T03:19:06Z

@fmassa Is it completed now?

acgtyrant · 2017-06-06T11:31:49Z

@szagoruyko How to get the VOC json? I download PASCAL VOC 2007 trainval dataset and only fint their xml. Thank you!

acgtyrant · 2017-06-06T11:49:08Z

I find it in the COCO official website.

fmassa · 2018-12-06T14:20:54Z

Fixed via #663

mrpositron · 2019-02-15T12:39:19Z

hey! @fmassa ,
I am using pascal voc 2007 det dataset.
and there is an error occuring when i am using to load them in batches.
i found that error occurs when i am trying to merge dicts of annotations of different size.

do you know how to handle it?
for dataset i am using official implementation (from ver 1.0.1)
and i am using usual dataloader

fmassa · 2019-02-15T13:27:49Z

@mrpositron you need to have a custom collate_fn in the DataLoader that pads the image before merging, so that the images have the same size. Check how it's done in maskrcnn-benchmark: here is the collate_fn, and the padding happens in here.

mrpositron · 2019-02-15T15:28:16Z

the problem is that all images by default are resized to 224*224, and the problem is that it (dataloader from torch.utils) merges dictionaries from targets in a batch. so i don't know exactly how to avoid that problem. since the images contain different # of objects, and merging fails

Merge with upstream

* adding base files * setup modification to actually build the thing * video api constructor registration * FAIL metadata * FAIL update for QS * revert * debugging with Victor * adding base files * setup modification to actually build the thing * video api constructor registration * FAIL metadata * FAIL update for QS * revert * debugging with Victor * metadata registration works * API build next * test * Merge change * formatting parameters to avoid the segfault * next now works on a video * make size of the output tensor format dependent * Make next work on audio stream only as well * refactoring the _setCurrentStream param * Fixing the last frame return and sensor * todo docs * Formatting * cleanup and comments * introducing new tests for the API * cleanup * Comment out unnecesary format (will add following FFMPEG fix) * Reformat parsing function * removing the seek bug `get_decoder_params` * Removing unnecessary code/variables * enforce RGB24 as a reading format (will crash before ffmpeg fix) * permute the dimensions to return (RGB x H x W) * Changing the return type to std::tuple<torch::Tensor, double> as opposed to tensor list * Adjusting tests for the new return type * remove unnecessary jitter * clangangangang * Metadata return changes (#1) * remove implicit calls to set a current stream (#2) * Adding new tests to check the accuracy of the seek * cleanup debugging statements * adding base files * setup modification to actually build the thing * video api constructor registration * FAIL metadata * FAIL update for QS * revert * debugging with Victor * adding base files * video api constructor registration * FAIL metadata * FAIL update for QS * revert * debugging with Victor * metadata registration works * API build next * test * Merge change * formatting parameters to avoid the segfault * next now works on a video * make size of the output tensor format dependent * Make next work on audio stream only as well * refactoring the _setCurrentStream param * Fixing the last frame return and sensor * todo docs * Formatting * cleanup and comments * introducing new tests for the API * cleanup * Comment out unnecesary format (will add following FFMPEG fix) * Reformat parsing function * removing the seek bug `get_decoder_params` * Removing unnecessary code/variables * enforce RGB24 as a reading format (will crash before ffmpeg fix) * permute the dimensions to return (RGB x H x W) * Changing the return type to std::tuple<torch::Tensor, double> as opposed to tensor list * Adjusting tests for the new return type * remove unnecessary jitter * clangangangang * Metadata return changes (#1) * remove implicit calls to set a current stream (#2) * Adding new tests to check the accuracy of the seek * cleanup debugging statements * Addressing PR comments * addressing Francisco's comments * CLANG build formatting * Updated testing to test against pyav for the video tensor reads * Formatting * remove pyav from pip deps and add it to conda build * add pyav and ffmeped to conda builds * Formatting? * Setting up linter once and for all hopefully * Testing pyav * Fix to 8.0.0 * Try 6.2.0 * See what happens with av from pip * Remove FFMPEG blocker * What is going on? * More tests * Forgot something * unblocker * Check if cache is messing up with things * Now try with different ffmpeg * Now try with different ffmpeg * Testing pyav * Fix to 8.0.0 * Try 6.2.0 * See what happens with av from pip * What is going on? * More tests * Forgot something * Check if cache is messing up with things * Now try with different ffmpeg * Now try with different ffmpeg * Do not install av * Test with ffmpeg 4.2 * clean up video tests * cleaning up the tests a bit to better test partial reading * arrgh linter * Forgot the av test * forgot av test * checkout build files from master * revert circleci * addressing Franciscos comments * addressing Franciscos comments * Ignore ffmpeg in travis Co-authored-by: Francisco Massa <fvsmassa@gmail.com> Co-authored-by: Edgar Andrés Margffoy Tuay <andfoy@gmail.com>

* adding base files * setup modification to actually build the thing * video api constructor registration * FAIL metadata * FAIL update for QS * revert * debugging with Victor * adding base files * setup modification to actually build the thing * video api constructor registration * FAIL metadata * FAIL update for QS * revert * debugging with Victor * metadata registration works * API build next * test * Merge change * formatting parameters to avoid the segfault * next now works on a video * make size of the output tensor format dependent * Make next work on audio stream only as well * refactoring the _setCurrentStream param * Fixing the last frame return and sensor * todo docs * Formatting * cleanup and comments * introducing new tests for the API * cleanup * Comment out unnecesary format (will add following FFMPEG fix) * Reformat parsing function * removing the seek bug `get_decoder_params` * Removing unnecessary code/variables * enforce RGB24 as a reading format (will crash before ffmpeg fix) * permute the dimensions to return (RGB x H x W) * Changing the return type to std::tuple<torch::Tensor, double> as opposed to tensor list * Adjusting tests for the new return type * remove unnecessary jitter * clangangangang * Metadata return changes (pytorch#1) * remove implicit calls to set a current stream (pytorch#2) * Adding new tests to check the accuracy of the seek * cleanup debugging statements * adding base files * setup modification to actually build the thing * video api constructor registration * FAIL metadata * FAIL update for QS * revert * debugging with Victor * adding base files * video api constructor registration * FAIL metadata * FAIL update for QS * revert * debugging with Victor * metadata registration works * API build next * test * Merge change * formatting parameters to avoid the segfault * next now works on a video * make size of the output tensor format dependent * Make next work on audio stream only as well * refactoring the _setCurrentStream param * Fixing the last frame return and sensor * todo docs * Formatting * cleanup and comments * introducing new tests for the API * cleanup * Comment out unnecesary format (will add following FFMPEG fix) * Reformat parsing function * removing the seek bug `get_decoder_params` * Removing unnecessary code/variables * enforce RGB24 as a reading format (will crash before ffmpeg fix) * permute the dimensions to return (RGB x H x W) * Changing the return type to std::tuple<torch::Tensor, double> as opposed to tensor list * Adjusting tests for the new return type * remove unnecessary jitter * clangangangang * Metadata return changes (pytorch#1) * remove implicit calls to set a current stream (pytorch#2) * Adding new tests to check the accuracy of the seek * cleanup debugging statements * Addressing PR comments * addressing Francisco's comments * CLANG build formatting * Updated testing to test against pyav for the video tensor reads * Formatting * remove pyav from pip deps and add it to conda build * add pyav and ffmeped to conda builds * Formatting? * Setting up linter once and for all hopefully * Testing pyav * Fix to 8.0.0 * Try 6.2.0 * See what happens with av from pip * Remove FFMPEG blocker * What is going on? * More tests * Forgot something * unblocker * Check if cache is messing up with things * Now try with different ffmpeg * Now try with different ffmpeg * Testing pyav * Fix to 8.0.0 * Try 6.2.0 * See what happens with av from pip * What is going on? * More tests * Forgot something * Check if cache is messing up with things * Now try with different ffmpeg * Now try with different ffmpeg * Do not install av * Test with ffmpeg 4.2 * clean up video tests * cleaning up the tests a bit to better test partial reading * arrgh linter * Forgot the av test * forgot av test * checkout build files from master * revert circleci * addressing Franciscos comments * addressing Franciscos comments * Ignore ffmpeg in travis Co-authored-by: Francisco Massa <fvsmassa@gmail.com> Co-authored-by: Edgar Andrés Margffoy Tuay <andfoy@gmail.com>

* adding base files * setup modification to actually build the thing * video api constructor registration * FAIL metadata * FAIL update for QS * revert * debugging with Victor * adding base files * setup modification to actually build the thing * video api constructor registration * FAIL metadata * FAIL update for QS * revert * debugging with Victor * metadata registration works * API build next * test * Merge change * formatting parameters to avoid the segfault * next now works on a video * make size of the output tensor format dependent * Make next work on audio stream only as well * refactoring the _setCurrentStream param * Fixing the last frame return and sensor * todo docs * Formatting * cleanup and comments * introducing new tests for the API * cleanup * Comment out unnecesary format (will add following FFMPEG fix) * Reformat parsing function * removing the seek bug `get_decoder_params` * Removing unnecessary code/variables * enforce RGB24 as a reading format (will crash before ffmpeg fix) * permute the dimensions to return (RGB x H x W) * Changing the return type to std::tuple<torch::Tensor, double> as opposed to tensor list * Adjusting tests for the new return type * remove unnecessary jitter * clangangangang * Metadata return changes (#1) * remove implicit calls to set a current stream (pytorch#2) * Adding new tests to check the accuracy of the seek * cleanup debugging statements * adding base files * setup modification to actually build the thing * video api constructor registration * FAIL metadata * FAIL update for QS * revert * debugging with Victor * adding base files * video api constructor registration * FAIL metadata * FAIL update for QS * revert * debugging with Victor * metadata registration works * API build next * test * Merge change * formatting parameters to avoid the segfault * next now works on a video * make size of the output tensor format dependent * Make next work on audio stream only as well * refactoring the _setCurrentStream param * Fixing the last frame return and sensor * todo docs * Formatting * cleanup and comments * introducing new tests for the API * cleanup * Comment out unnecesary format (will add following FFMPEG fix) * Reformat parsing function * removing the seek bug `get_decoder_params` * Removing unnecessary code/variables * enforce RGB24 as a reading format (will crash before ffmpeg fix) * permute the dimensions to return (RGB x H x W) * Changing the return type to std::tuple<torch::Tensor, double> as opposed to tensor list * Adjusting tests for the new return type * remove unnecessary jitter * clangangangang * Metadata return changes (#1) * remove implicit calls to set a current stream (pytorch#2) * Adding new tests to check the accuracy of the seek * cleanup debugging statements * Addressing PR comments * addressing Francisco's comments * CLANG build formatting * Updated testing to test against pyav for the video tensor reads * Formatting * remove pyav from pip deps and add it to conda build * add pyav and ffmeped to conda builds * Formatting? * Setting up linter once and for all hopefully * Testing pyav * Fix to 8.0.0 * Try 6.2.0 * See what happens with av from pip * Remove FFMPEG blocker * What is going on? * More tests * Forgot something * unblocker * Check if cache is messing up with things * Now try with different ffmpeg * Now try with different ffmpeg * Testing pyav * Fix to 8.0.0 * Try 6.2.0 * See what happens with av from pip * What is going on? * More tests * Forgot something * Check if cache is messing up with things * Now try with different ffmpeg * Now try with different ffmpeg * Do not install av * Test with ffmpeg 4.2 * clean up video tests * cleaning up the tests a bit to better test partial reading * arrgh linter * Forgot the av test * forgot av test * checkout build files from master * revert circleci * addressing Franciscos comments * addressing Franciscos comments * Ignore ffmpeg in travis Co-authored-by: Francisco Massa <fvsmassa@gmail.com> Co-authored-by: Edgar Andrés Margffoy Tuay <andfoy@gmail.com>

Fixing lint in giou_loss.py

… to conform with non-quantized countertpart filenames (#77037) Summary: X-link: pytorch/pytorch#77037 Names of analogous files in quantized directory (previously snake case) were inconsistent with their non-quantized filename counterparts (pascal case). This is the first of a series of PRs that changes all files in quantized (and sub-directories) dir to have pascal case. `aten/src/ATen/native/quantized/qconv_unpack.cpp` has not been renamed yet because (for reasons currently unknown) after making the name change, `import torch` produces the below error (`qlinear_unpack.cpp` renaming also seems to fail some phabricator CI tests for similar reasons). We suspect that these may be undefined errors and will revisit naming these files in a future PR. ``` terminate called after throwing an instance of 'c10::Error' what(): Type c10::intrusive_ptr<ConvPackedParamsBase<2> > could not be converted to any of the known types. Exception raised from operator() at ../aten/src/ATen/core/jit_type.h:1735 (most recent call first): frame #0: c10::Error::Error(c10::SourceLocation, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >) + 0x55 (0x7f26745c0c65 in /data/users/dzdang/pytorch/torch/lib/libc10.so) frame #1: c10::detail::torchCheckFail(char const*, char const*, unsigned int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) + 0xb1 (0x7f26745bdcd1 in /data/users/dzdang/pytorch/torch/lib/libc10.so) frame #2: <unknown function> + 0x1494e24 (0x7f2663b14e24 in /data/users/dzdang/pytorch/torch/lib/libtorch_cpu.so) frame #3: <unknown function> + 0xfed0bc (0x7f266366d0bc in /data/users/dzdang/pytorch/torch/lib/libtorch_cpu.so) frame #4: c10::detail::infer_schema::make_function_schema(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >&&, c10::ArrayRef<c10::detail::infer_schema::ArgumentDef>, c10::ArrayRef<c10::detail::infer_schema::ArgumentDef>) + 0x5a (0x7f266366d71a in /data/users/dzdang/pytorch/torch/lib/libtorch_cpu.so) frame #5: c10::detail::infer_schema::make_function_schema(c10::ArrayRef<c10::detail::infer_schema::ArgumentDef>, c10::ArrayRef<c10::detail::infer_schema::ArgumentDef>) + 0x7b (0x7f266366e06b in /data/users/dzdang/pytorch/torch/lib/libtorch_cpu.so) frame #6: <unknown function> + 0x1493f32 (0x7f2663b13f32 in /data/users/dzdang/pytorch/torch/lib/libtorch_cpu.so) frame #7: <unknown function> + 0xe227dd (0x7f26634a27dd in /data/users/dzdang/pytorch/torch/lib/libtorch_cpu.so) frame #8: <unknown function> + 0x14e0a (0x7f268c934e0a in /lib64/ld-linux-x86-64.so.2) ..........................truncated............. ``` Reviewed By: malfet Differential Revision: D36862332 Pulled By: dzdang fbshipit-source-id: 598c36656b4e71f906d940e7ff19ecf82d43031d

…zed directory… (#6133) * [quant][core][better-engineering] Rename files in quantized directory to conform with non-quantized countertpart filenames (#77037) Summary: X-link: pytorch/pytorch#77037 Names of analogous files in quantized directory (previously snake case) were inconsistent with their non-quantized filename counterparts (pascal case). This is the first of a series of PRs that changes all files in quantized (and sub-directories) dir to have pascal case. `aten/src/ATen/native/quantized/qconv_unpack.cpp` has not been renamed yet because (for reasons currently unknown) after making the name change, `import torch` produces the below error (`qlinear_unpack.cpp` renaming also seems to fail some phabricator CI tests for similar reasons). We suspect that these may be undefined errors and will revisit naming these files in a future PR. ``` terminate called after throwing an instance of 'c10::Error' what(): Type c10::intrusive_ptr<ConvPackedParamsBase<2> > could not be converted to any of the known types. Exception raised from operator() at ../aten/src/ATen/core/jit_type.h:1735 (most recent call first): frame #0: c10::Error::Error(c10::SourceLocation, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >) + 0x55 (0x7f26745c0c65 in /data/users/dzdang/pytorch/torch/lib/libc10.so) frame #1: c10::detail::torchCheckFail(char const*, char const*, unsigned int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) + 0xb1 (0x7f26745bdcd1 in /data/users/dzdang/pytorch/torch/lib/libc10.so) frame #2: <unknown function> + 0x1494e24 (0x7f2663b14e24 in /data/users/dzdang/pytorch/torch/lib/libtorch_cpu.so) frame #3: <unknown function> + 0xfed0bc (0x7f266366d0bc in /data/users/dzdang/pytorch/torch/lib/libtorch_cpu.so) frame #4: c10::detail::infer_schema::make_function_schema(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >&&, c10::ArrayRef<c10::detail::infer_schema::ArgumentDef>, c10::ArrayRef<c10::detail::infer_schema::ArgumentDef>) + 0x5a (0x7f266366d71a in /data/users/dzdang/pytorch/torch/lib/libtorch_cpu.so) frame #5: c10::detail::infer_schema::make_function_schema(c10::ArrayRef<c10::detail::infer_schema::ArgumentDef>, c10::ArrayRef<c10::detail::infer_schema::ArgumentDef>) + 0x7b (0x7f266366e06b in /data/users/dzdang/pytorch/torch/lib/libtorch_cpu.so) frame #6: <unknown function> + 0x1493f32 (0x7f2663b13f32 in /data/users/dzdang/pytorch/torch/lib/libtorch_cpu.so) frame #7: <unknown function> + 0xe227dd (0x7f26634a27dd in /data/users/dzdang/pytorch/torch/lib/libtorch_cpu.so) frame #8: <unknown function> + 0x14e0a (0x7f268c934e0a in /lib64/ld-linux-x86-64.so.2) ..........................truncated............. ``` Reviewed By: malfet Differential Revision: D36862332 Pulled By: dzdang fbshipit-source-id: 598c36656b4e71f906d940e7ff19ecf82d43031d * empty commit * empty commit * empty commit Co-authored-by: dzdang <dzdang@umich.edu> Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

fmassa closed this as completed Dec 6, 2018

sprt added a commit to sprt/vision that referenced this issue Dec 11, 2019

Merge pull request pytorch#2 from sprt/upstream_merge

f2031cc

Merge with upstream

adizhol mentioned this issue Dec 29, 2019

Runtime error in torchvision nms in Linux. Windows works fine #1705

Open

emericit mentioned this issue Jan 27, 2020

Illegal instruction (core dumped) with some pretrained models (but not all) #1782

Closed

jspisak mentioned this issue May 13, 2020

Added reference to the Computer Vision Best Practices repository #2203

Closed

chinglamchoi mentioned this issue Oct 2, 2020

Attempted to read a PyTorch file with version 3, but the maximum supported version for reading is 2. Your PyTorch installation may be too old. (init at ../caffe2/serialize/inline_container.cc:132) #1943

Open

fibbonnaci mentioned this issue Dec 1, 2021

[RFC] Use pretrained=True to load the best available pre-trained weights #5015

Closed

zhiqwang pushed a commit to zhiqwang/vision that referenced this issue Jan 19, 2022

Merge pull request pytorch#2 from o295/main

1f67950

Fixing lint in giou_loss.py

This was referenced Feb 22, 2022

Segfault on unloading a model #5453

Closed

Segfault on unloading a model pytorch/pytorch#73352

Open

osalpekar mentioned this issue Dec 7, 2022

Fix GHA Linux GPU Job not running tests on CUDA #6957

Closed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Pascal VOC dataset #2

Pascal VOC dataset #2

fmassa commented Nov 10, 2016

szagoruyko commented Nov 28, 2016

fmassa commented Nov 28, 2016

acgtyrant commented Apr 21, 2017

acgtyrant commented Jun 6, 2017

acgtyrant commented Jun 6, 2017

fmassa commented Dec 6, 2018

mrpositron commented Feb 15, 2019

fmassa commented Feb 15, 2019

mrpositron commented Feb 15, 2019 •

edited

Loading

Pascal VOC dataset #2

Pascal VOC dataset #2

Comments

fmassa commented Nov 10, 2016

szagoruyko commented Nov 28, 2016

fmassa commented Nov 28, 2016

acgtyrant commented Apr 21, 2017

acgtyrant commented Jun 6, 2017

acgtyrant commented Jun 6, 2017

fmassa commented Dec 6, 2018

mrpositron commented Feb 15, 2019

fmassa commented Feb 15, 2019

mrpositron commented Feb 15, 2019 • edited Loading

mrpositron commented Feb 15, 2019 •

edited

Loading