GitLab

* make_grid should not avoid DBZ by adding eps

While this doesn't matter in most cases where the images is quantized to [0,255] afterwards, it still is not a faithful de-normalization. It is a simple change to make it use clamp instead.

* fix max/min shadowing

* Add modulation input for DeformConv2D

* lint

* Patch for GPU CI

* Remove bad cache on CI

I.e. put all file system altering operations under `if __name__ == "__main__":`

* style: Added annotation typing for shufflenet

* fix: Removed duplicate type hint

* refactor: Removed un-necessary import

* fix: Fixed constructor typing

* style: Added black formatting on depthwise_conv

* style: Fixed stage typing in shufflenet

* initial docstring

* Revert "initial docstring"

This reverts commit 2bf68ca26e58096885901da0cfa330530974e731.

* revert the formatting changes

* clear up per Victor's comment

* Addressing PR comments
Co-authored-by: Bruno Korbar <korbar@vggdev9.vggdev.cluster>

* style: Added annotation typing for densenet

* fix: Fixed import

* refactor: Removed un-necessary import

* fix: Fixed constructor typing

* chore: Updated mypy.ini

* fix: Fixed tuple typing

* style: Ignored some mypy errors

* style: Fixed typing

* fix: Added missing constructor typing

- fixed problem with error computation between results
- refactored tensor cast for resize
- fixed round usage

* changes to value error

* fixes it :)

* simpler fix

* Simplify the ACCEPT=True logic in assertExpected().

* Separate the expected filename estimation from assertExpected

* Unflatten expected values.

* Assert for duplicate scores if primary check fails.

* Remove custom exceptions for algorithms and add a compact function for shrinking large ouputs.

* Removing unused variables.

* Add warning and comments.

* Re-enable all autocast unit-test for detection and marking the tests as skipped in partial validation.

* Move test skip at the end.

* Changing the warning message.

* Simplify the ACCEPT=True logic in assertExpected().

* Separate the expected filename estimation from assertExpected

* removing the tab?

* initial commit

* Addressing Victor's comments
Co-authored-by: vfdev <vfdev.5@gmail.com>

* Make read_file accept unicode strings on Windows

* More fixes

* Remove definitions from source files

* Move string definitions to header

* Add checks

* Fix comments

* Update macro

* Fix comments

* Fix lint

* include windows header

* Change func signature in header

* Use from_blob

* Fix fread calls

* Fix clang format

* Fix missing return

* Avoid copy

* Overwriting FrozenBN eps=0.0 if pretrained=True for detection models.

* Moving the method to detection utils and adding comments.

* Making all model constructors explicit.

* formatting.

* [WIP] Update ref example video classification

* [WIP] Updated video classification ref example

* Replaced mem format conversion functions by classes

* Modified the example to conform with the new DICT return.

* adding better stream documentation to examples

* Clearing up some documentation as a result of a feedback

* Formatting mostly

* Addressing Victor's comments.

* addressing fmassas comments

* remove unnecessary tab
Co-authored-by: Bruno Korbar <korbar@vggdev9.vggdev.cluster>
Co-authored-by: vfdev <vfdev.5@gmail.com>

* Moving Autocast mtest in RoiOpTester.

* Adding autocast test on DeformConvTester.

* Adding autocast test on NMSTester.

* Fixing styles.

* Fixing types.

* Dispatcher + Autocast.

* + Autograd.

* Formating.

* Clean up and refactor PSROIPool implementation:
- Remove primitive const declaration from method names.
- Using references when possible.
- Fix variable naming.

* Restore include headers.

* New line at end of file.

* Resolving conflict, final cleanup, ordering method consistently across files.

* Fixing types.

* Dispatcher + Autocast.

* + Autograd.

* Formating.

* Fixing return casting with autocast.

* Clean up and refactor ROIPool implementation:
- Remove primitive const declaration from method names.
- Using references when possible.

* Restore include headers.

* New line at end of file.

* Clean up and refactor ROIAlign implementation:
- Remove primitive const declaration from method names.
- Passing as const ref instead of value where possible.
- Remove unnecessary headers.

* Adding back include for cpu.

* Restore include headers.

* Fixing types.

* Dispatcher + Autocast.

* + Autograd.

* Clean up and refactor PSROIAlign implementation:
- Remove primitive const declaration from method names.
- Using references when possible.
- Sync naming of internal methods with other ops.

* Restoring names of internal methods to avoid conflicts.

* Restore include headers.

* Clean up and refactor DeformConv implementation:
- Remove primitive const declaration from method names.
- Passing as const ref instead of value where possible.
- Aligning method names between cpu and cuda.

* Adding newline.

* Adding back include for cpu.

* Restoring method names of private methods to avoid conflicts.

* Restore include headers.

* Change default eps value of FrozenBN.

* Update the unit-tests.`

* Update the expected values.

* Revert the expected value and use original eps=0 value for flaky tests.

* Post init change of eps.

* Styles.

* Clean up and refactor ROIAlign implementation:
- Remove primitive const declaration from method names.
- Remove unnecessary headers.
- Aligning method names between cpu and cuda.

* Adding back include for cpu.

* Restoring method names of private methods to avoid conflicts.

* Restore include headers.

- Replaced tuple creation by one acceptable by majority of compilers

Adds classification data and links to the class libraries.
Co-authored-by: Brian Johnson <brianjo@fb.com>

* README: add recommended PyTorch version for v0.8.0

* PyTorch v1.7.0 is now released

This was a mistake since version suffix should always be appended
Signed-off-by: Eli Uriegas <eliuriegas@fb.com>
(cherry picked from commit 6631b74db7cf8aebee8af196b4c65b1fce220baa)
Signed-off-by: Eli Uriegas <eliuriegas@fb.com>

- fixed bug with Resize and size as single int

* Splitting tuples of stride, padding and dilation of DeformConv.

* Fixing types.

* Dispatcher + Autocast.

* + Autograd.

* Moving contiguous() convertions away dispatcher and into the implementations.

* Removing rvalue references.

* style: Added annotation typing for vgg

* fix: Fixed annotation typing

* refactor: Removed un-necessary import

* fix: Added missing annotation for kwargs

* fix: Fixed constructor typing

* refactor: Refactored typing to minize changes

* refactor: Refactored typing cast

* fix: Fixed module list typing

* add a README for training object detection models

* replaced np.asarray with np.array to avoid warning messages

* added data-path for flexibility

* fixed a typo

* Minor refactoring based on static analysis on the code of models:
- Convert unnecessary value parameter to constant reference.
- Use move to avoid unnecessary copies.
- Eliminate unused include.

* Replace moves with const references.

* Fixing formatting.

* Remove explicit declaration on constructors.

- Remove unnecessary return.

- Replace deprecated string.h with cstring.
- Switch to nullptr.