Skip to content
Projects
Groups
Snippets
Help
Loading...
Help
Support
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
S
seminar-breakout
Project overview
Project overview
Details
Activity
Releases
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Issues
0
Issues
0
List
Boards
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Analytics
Analytics
CI / CD
Repository
Value Stream
Wiki
Wiki
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
Shashank Suhas
seminar-breakout
Commits
bf94458d
Commit
bf94458d
authored
Nov 14, 2017
by
Yuxin Wu
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
[FasterRCNN] update docs
parent
dafdabf8
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
8 additions
and
4 deletions
+8
-4
examples/FasterRCNN/NOTES.md
examples/FasterRCNN/NOTES.md
+6
-2
examples/FasterRCNN/README.md
examples/FasterRCNN/README.md
+2
-2
No files found.
examples/FasterRCNN/NOTES.md
View file @
bf94458d
...
@@ -21,10 +21,14 @@ This is a minimal implementation that simply contains these files:
...
@@ -21,10 +21,14 @@ This is a minimal implementation that simply contains these files:
<p
align=
"center"
>
<img
src=
"https://user-images.githubusercontent.com/1381301/31527740-2f1b38ce-af84-11e7-8de1-628e90089826.png"
>
</p>
<p
align=
"center"
>
<img
src=
"https://user-images.githubusercontent.com/1381301/31527740-2f1b38ce-af84-11e7-8de1-628e90089826.png"
>
</p>
3.
Inference is not quite fast, because either you disable convolution autotune and end up with
3.
We use ROIAlign, and because of (3),
`tf.image.crop_and_resize`
is NOT ROIAlign.
4.
Inference is not quite fast, because either you disable convolution autotune and end up with
a slow convolution algorithm, or you spend more time on autotune.
a slow convolution algorithm, or you spend more time on autotune.
This is a general problem of TensorFlow when running against variable-sized input.
This is a general problem of TensorFlow when running against variable-sized input.
4.
In Faster-RCNN, BatchNorm statistics are not supposed to be updated during fine-tuning.
5.
We only support single image per GPU for now.
6.
Because of (4), BatchNorm statistics are not supposed to be updated during fine-tuning.
This specific kind of BatchNorm will need
[
my kernel
](
https://github.com/tensorflow/tensorflow/pull/12580
)
This specific kind of BatchNorm will need
[
my kernel
](
https://github.com/tensorflow/tensorflow/pull/12580
)
which is included since TF 1.4. If using an earlier version of TF, it will be either slow or wrong.
which is included since TF 1.4. If using an earlier version of TF, it will be either slow or wrong.
examples/FasterRCNN/README.md
View file @
bf94458d
# Faster-RCNN on COCO
# Faster-RCNN on COCO
This example aims to provide a minimal (
<1000
lines) multi-GPU implementation of ResNet50-Faster-RCNN on COCO.
This example aims to provide a minimal (
1.2k
lines) multi-GPU implementation of ResNet50-Faster-RCNN on COCO.
## Dependencies
## Dependencies
+
TensorFlow >
1.4.0 (use tf-nightly-gpu for now)
+
TensorFlow >
= 1.4.0
+
Install
[
pycocotools
](
https://github.com/pdollar/coco/tree/master/PythonAPI/pycocotools
)
, OpenCV.
+
Install
[
pycocotools
](
https://github.com/pdollar/coco/tree/master/PythonAPI/pycocotools
)
, OpenCV.
+
Pre-trained
[
ResNet50 model
](
https://goo.gl/6XjK9V
)
from tensorpack model zoo.
+
Pre-trained
[
ResNet50 model
](
https://goo.gl/6XjK9V
)
from tensorpack model zoo.
+
COCO data. It assumes the following directory structure:
+
COCO data. It assumes the following directory structure:
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment