EfficientDet (Scalable and Efficient Object Detection) implementation in Keras and Tensorflow

Last update: Dec 19, 2022

Overview

EfficientDet

This is an implementation of EfficientDet for object detection on Keras and Tensorflow. The project is based on the official implementation google/automl, fizyr/keras-retinanet and the qubvel/efficientnet.

About pretrained weights

The pretrained EfficientNet weights on imagenet are downloaded from Callidior/keras-applications/releases
The pretrained EfficientDet weights on coco are converted from the official release google/automl.

Thanks for their hard work. This project is released under the Apache License. Please take their licenses into consideration too when use this project.

Updates

[03/21/2020] Synchronize with the official implementation. google/automl
[03/05/2020] Anchor free version. The accuracy is a little lower, but it's faster and smaller.For details, please refer to xuannianz/SAPD
[02/20/2020] Support quadrangle detection. For details, please refer to README_quad

Train

build dataset

Pascal VOC
- Download VOC2007 and VOC2012, copy all image files from VOC2007 to VOC2012.
- Append VOC2007 train.txt to VOC2012 trainval.txt.
- Overwrite VOC2012 val.txt by VOC2007 val.txt.
MSCOCO 2017
- Download images and annotations of coco 2017
- Copy all images into datasets/coco/images, all annotations into datasets/coco/annotations
Other types please refer to fizyr/keras-retinanet)

train

STEP1: python3 train.py --snapshot imagenet --phi {0, 1, 2, 3, 4, 5, 6} --gpu 0 --random-transform --compute-val-loss --freeze-backbone --batch-size 32 --steps 1000 pascal|coco datasets/VOC2012|datasets/coco to start training. The init lr is 1e-3.
STEP2: python3 train.py --snapshot xxx.h5 --phi {0, 1, 2, 3, 4, 5, 6} --gpu 0 --random-transform --compute-val-loss --freeze-bn --batch-size 4 --steps 10000 pascal|coco datasets/VOC2012|datasets/coco to start training when val mAP can not increase during STEP1. The init lr is 1e-4 and decays to 1e-5 when val mAP keeps dropping down.

Evaluate

PASCAL VOC
- python3 eval/common.py to evaluate pascal model by specifying model path there.
- The best evaluation results (score_threshold=0.01, mAP₅₀) on VOC2007 test are:
phi 0 1

w/o weighted 0.8029

w/ weighted 0.7892
MSCOCO
- python3 eval/coco.py to evaluate coco model by specifying model path there.
phi mAP

0 0.334 weights, results

1 0.393 weights, results

2 0.424 weights, results

3 0.454 weights, results

4 0.483 weights, results

phi	0	1
w/o weighted		0.8029
w/ weighted	0.7892

phi	mAP
0	0.334 weights, results
1	0.393 weights, results
2	0.424 weights, results
3	0.454 weights, results
4	0.483 weights, results

Test

python3 inference.py to test your image by specifying image path and model path there.

Comments

CSV dataset loading error

Thank you for your great work.

I constructed my own dataset with csv file like under

filename, xmin, ymin, xmax, ymax, class_name ...

training looks like working well, but there are too many warning messages like under

UserWarning: Image with id 745 (shape (896, 896, 3)) contains no valid boxes after transform image.shape

b0 backbone is more often show the message, and b3 backbone has just few message Can I know what it means?
wontfix

opened by kboseong 25
The difference of tensorflow.keras.model.Model() and keras.model.Model()

Thank you very much for your contribution and sharing. There is a question puzzled me. Why does tensorflow.keras.model.Model() work in model.py(build_regress_head() and build_class_head()), not keras.model.Model()? Is there any difference between them? Looking forward to your answer. Thank you very much.
wontfix

opened by GithubAbner 20
No module named 'utils.compute_overlap'

Hello, firstly thank you for the great work.

I am having trouble starting training. I get this error:

-- No module named 'utils.compute_overlap' --

I have the keras-retinanet running perfectly on my machine.

What could be done?

Regards!
wontfix

opened by nicholasguimaraes 17
Output of scores variable using inference.py is -1 for the entire list of scores

Hello @xuannianz , @km23630 , I am training the code for a task with two classes, but the code is unable to detect an image, it is giving -1 scores to all.

I am using the following script for training the model.

python train.py --snapshot imagenet --phi 1 --gpu 0 --random-transform --freeze-backbone --epochs 10 --batch-size 8 --steps 100 csv /work/traffic_dataset/train_labels_eff.csv /work/traffic_dataset/class_name_to_ID.csv

I have made all necessary changes as RetinaNet as mentioned and RetinaNet works fine for me. Also, a normal coco models weights which were trained using EfficientDet also works, just that my own model.h5 file is not working

opened by init-22 16
No module named 'utils.compute_overlap'

Hi, When I try to run the train.py, I got error saying no module named 'utils.compute_overlap'. It's weird that there is a 'compute_overlap.pyx' file in 'utils' forlder. Should we just rename the suffix as 'py' and use this file?
wontfix

opened by KaggleAlbertaAI 14
The loss is very low,but the mAP is 0 when training on my own datasets.

I am training on my own datasets using the code of April version,the loss is very low than previous version, but the mAP is always 0. Using the same config,Feb. code version has a high loss, but mAP is not zero. How can I solve the problem
wontfix

opened by xinlnix 13
import error in windows: ModuleNotFoundError: No module named 'utils.compute_overlap'

from utils.compute_overlap import compute_overlap When I run this import statement in windows, I get ModuleNotFoundError: No module named 'utils.compute_overlap'. How to fix this error?
wontfix

opened by 2696120622 12
How to test "custum csv model"?

I understand that the "inference.py" file is a test file for PASCAL VOC data.

How can I use inference.py for my csv data?

Similarly, in /eval/commom.py it is difficult to evaluate csv data.

Thanks.
wontfix

opened by JooHyungSon 11
I face the same problem after using the latest code.

I face the same problem after using the latest code @ csv mode. The training process seems no problem. however there's no inference result. (no matter how I try ) could any one give some suggestion about the no inference at all phenomena?

step1: python train.py --snapshot imagenet --phi 0 --gpu 0,1 --random-transform --freeze-backbone --compute-val-loss --batch-size 2 --steps 200 csv D:\wordG.csv D:\wordG.txt --val-annotations-path D:\wordG.csv

step2:

python train.py --snapshot checkpoints\2020-06-19\csv_50_0.0043_0.7948.h5 --phi 0 --gpu 0,1 --random-transform --freeze-bn --compute-val-loss --batch-size 2 --steps 200 csv D:\wordG.csv D:\wordG.txt --val-annotations-path D:\wordG.csv

Epoch 00042: saving model to checkpoints/2020-06-19\csv_42_0.0081_0.2341.h5 200/200 [==============================] - 168s 840ms/step - loss: 0.0081 - classification_loss: 0.0021 - regression_loss: 0.0059 - val_loss: 0.2341 - val_classification_loss: 0.2016 - val_regression_loss: 0.0326 Epoch 43/50 199/200 [============================>.] - ETA: 0s - loss: 0.0065 - classification_loss: 0.0013 - regression_loss: 0.0052Epoch 1/50 245/200 [====================================] - 24s 99ms/step - loss: 0.2023 - classification_loss: 0.2089 - regression_loss: 0.0304 Running network: 100% (489 of 489) |##############################################################################################| Elapsed Time: 0:00:26 Time: 0:00:26 Parsing annotations: 100% (489 of 489) |##########################################################################################| Elapsed Time: 0:00:00 Time: 0:00:00 num_fp=34253.0, num_tp=2745.0 199 instances of class 0 with average precision: 0.8843 136 instances of class 1 with average precision: 0.8379 204 instances of class 2 with average precision: 0.9671 267 instances of class 3 with average precision: 0.9180 78 instances of class 4 with average precision: 0.7325 417 instances of class 5 with average precision: 0.9871 184 instances of class 6 with average precision: 1.0000 72 instances of class 7 with average precision: 1.0000 2 instances of class 8 with average precision: 1.0000 498 instances of class 9 with average precision: 0.9989 23 instances of class A with average precision: 0.0855 340 instances of class C with average precision: 0.9917 23 instances of class K with average precision: 1.0000 23 instances of class L with average precision: 1.0000 320 instances of class R with average precision: 0.9190 2 instances of class T with average precision: 1.0000 1 instances of class U with average precision: 1.0000 1 instances of class V with average precision: 1.0000 1 instances of class X with average precision: 0.0048 mAP: 0.8593

Epoch 00043: saving model to checkpoints/2020-06-19\csv_43_0.0065_0.2393.h5 200/200 [==============================] - 168s 841ms/step - loss: 0.0065 - classification_loss: 0.0013 - regression_loss: 0.0052 - val_loss: 0.2393 - val_classification_loss: 0.2089 - val_regression_loss: 0.0304 Epoch 44/50 104/200 [==============>...............] - ETA: 56s - loss: 0.0054 - classification_loss: 7.3843e-04 - regression_loss: 0.0046Traceback (most recent call last):.

Originally posted by @fiyerowei in https://github.com/xuannianz/EfficientDet/issues/117#issuecomment-646406922
wontfix

opened by fiyerowei 10
how to design anchor ratios and scales?

wanna train on custom dataset, using default coco anchor settings, the big target can detect while small target always miss.

Did I miss something in such situation?
wontfix

opened by jinfagang 10
mscoco pretrained weights uncorrect！

I downloaded the mscoco pretrained weights (d0, d1 and d2), and test with the script inference.py. The output scores are all very small, around 0.01. I found that the model can output different scores with the same input and model weights. I guess there is something wrong in the pretrained weights, and the script inference.py can not load all model weights correctly. Can you check this please?
wontfix

opened by luckycallor 10
Some advice about license compliance

Hello, such a nice repository benefits me a lot and so kind of you to make it open source!

Question There’s some possible legal issues on the license of your repository when you combine numerous third-party packages. For instance, random, argparse and datetime you imported are licensed with Python Software Foundation License, Python Software Foundation License and Zope Public License (ZPL 2.1), respectively. However, the Apache License of your repository are less strict than above package licenses on some terms, which has violated the whole license compatibility in your repository and may bring legal and financial risks.

Advice You can select another proper license for your repository, or write a custom license with license exception if some license terms couldn’t be summed up consistently.

Best wishes!

opened by Ashley123456789 0
Bump pillow from 6.2.0 to 9.3.0
Bumps pillow from 6.2.0 to 9.3.0.

Release notes

Sourced from pillow's releases.

9.3.0

https://pillow.readthedocs.io/en/stable/releasenotes/9.3.0.html

Changes

Initialize libtiff buffer when saving #6699 [@radarhere]

Limit SAMPLESPERPIXEL to avoid runtime DOS #6700 [@wiredfool]

Inline fname2char to fix memory leak #6329 [@nulano]

Fix memory leaks related to text features #6330 [@nulano]

Use double quotes for version check on old CPython on Windows #6695 [@hugovk]

GHA: replace deprecated set-output command with GITHUB_OUTPUT file #6697 [@nulano]

Remove backup implementation of Round for Windows platforms #6693 [@cgohlke]

Upload fribidi.dll to GitHub Actions #6532 [@nulano]

Fixed set_variation_by_name offset #6445 [@radarhere]

Windows build improvements #6562 [@nulano]

Fix malloc in _imagingft.c:font_setvaraxes #6690 [@cgohlke]

Only use ASCII characters in C source file #6691 [@cgohlke]

Release Python GIL when converting images using matrix operations #6418 [@hmaarrfk]

Added ExifTags enums #6630 [@radarhere]

Do not modify previous frame when calculating delta in PNG #6683 [@radarhere]

Added support for reading BMP images with RLE4 compression #6674 [@npjg]

Decode JPEG compressed BLP1 data in original mode #6678 [@radarhere]

pylint warnings #6659 [@marksmayo]

Added GPS TIFF tag info #6661 [@radarhere]

Added conversion between RGB/RGBA/RGBX and LAB #6647 [@radarhere]

Do not attempt normalization if mode is already normal #6644 [@radarhere]

Fixed seeking to an L frame in a GIF #6576 [@radarhere]

Consider all frames when selecting mode for PNG save_all #6610 [@radarhere]

Don't reassign crc on ChunkStream close #6627 [@radarhere]

Raise a warning if NumPy failed to raise an error during conversion #6594 [@radarhere]

Only read a maximum of 100 bytes at a time in IMT header #6623 [@radarhere]

Show all frames in ImageShow #6611 [@radarhere]

Allow FLI palette chunk to not be first #6626 [@radarhere]

If first GIF frame has transparency for RGB_ALWAYS loading strategy, use RGBA mode #6592 [@radarhere]

Round box position to integer when pasting embedded color #6517 [@radarhere]

Removed EXIF prefix when saving WebP #6582 [@radarhere]

Pad IM palette to 768 bytes when saving #6579 [@radarhere]

Added DDS BC6H reading #6449 [@ShadelessFox]

Added support for opening WhiteIsZero 16-bit integer TIFF images #6642 [@JayWiz]

Raise an error when allocating translucent color to RGB palette #6654 [@jsbueno]

Moved mode check outside of loops #6650 [@radarhere]

Added reading of TIFF child images #6569 [@radarhere]

Improved ImageOps palette handling #6596 [@PososikTeam]

Defer parsing of palette into colors #6567 [@radarhere]

Apply transparency to P images in ImageTk.PhotoImage #6559 [@radarhere]

Use rounding in ImageOps contain() and pad() #6522 [@bibinhashley]

Fixed GIF remapping to palette with duplicate entries #6548 [@radarhere]

Allow remap_palette() to return an image with less than 256 palette entries #6543 [@radarhere]

Corrected BMP and TGA palette size when saving #6500 [@radarhere]

... (truncated)

Changelog

Sourced from pillow's changelog.

9.3.0 (2022-10-29)

Limit SAMPLESPERPIXEL to avoid runtime DOS #6700 [wiredfool]

Initialize libtiff buffer when saving #6699 [radarhere]

Inline fname2char to fix memory leak #6329 [nulano]

Fix memory leaks related to text features #6330 [nulano]

Use double quotes for version check on old CPython on Windows #6695 [hugovk]

Remove backup implementation of Round for Windows platforms #6693 [cgohlke]

Fixed set_variation_by_name offset #6445 [radarhere]

Fix malloc in _imagingft.c:font_setvaraxes #6690 [cgohlke]

Release Python GIL when converting images using matrix operations #6418 [hmaarrfk]

Added ExifTags enums #6630 [radarhere]

Do not modify previous frame when calculating delta in PNG #6683 [radarhere]

Added support for reading BMP images with RLE4 compression #6674 [npjg, radarhere]

Decode JPEG compressed BLP1 data in original mode #6678 [radarhere]

Added GPS TIFF tag info #6661 [radarhere]

Added conversion between RGB/RGBA/RGBX and LAB #6647 [radarhere]

Do not attempt normalization if mode is already normal #6644 [radarhere]

... (truncated)

Commits

d594f4c Update CHANGES.rst [ci skip]

909dc64 9.3.0 version bump

1a51ce7 Merge pull request #6699 from hugovk/security-libtiff_buffer

2444cdd Merge pull request #6700 from hugovk/security-samples_per_pixel-sec

744f455 Added release notes

0846bfa Add to release notes

799a6a0 Fix linting

00b25fd Hide UserWarning in logs

05b175e Tighter test case

13f2c5a Prevent DOS with large SAMPLESPERPIXEL in Tiff IFD

Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

@dependabot rebase will rebase this PR

@dependabot recreate will recreate this PR, overwriting any edits that have been made to it

@dependabot merge will merge this PR after your CI passes on it

@dependabot squash and merge will squash and merge this PR after your CI passes on it

@dependabot cancel merge will cancel a previously requested merge and block automerging

@dependabot reopen will reopen this PR if it is closed

@dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually

@dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)

@dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)

@dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

@dependabot use these labels will set the current labels as the default for future PRs for this repo and language

@dependabot use these reviewers will set the current reviewers as the default for future PRs for this repo and language

@dependabot use these assignees will set the current assignees as the default for future PRs for this repo and language

@dependabot use this milestone will set the current milestone as the default for future PRs for this repo and language

You can disable automated security fix PRs for this repo from the Security Alerts page.

wontfix dependencies
opened by dependabot[bot] 1
Bump tensorflow-gpu from 1.15.0 to 2.9.3
Bumps tensorflow-gpu from 1.15.0 to 2.9.3.

Release notes

Sourced from tensorflow-gpu's releases.

TensorFlow 2.9.3

Release 2.9.3

This release introduces several vulnerability fixes:

Fixes an overflow in tf.keras.losses.poisson (CVE-2022-41887)

Fixes a heap OOB failure in ThreadUnsafeUnigramCandidateSampler caused by missing validation (CVE-2022-41880)

Fixes a segfault in ndarray_tensor_bridge (CVE-2022-41884)

Fixes an overflow in FusedResizeAndPadConv2D (CVE-2022-41885)

Fixes a overflow in ImageProjectiveTransformV2 (CVE-2022-41886)

Fixes an FPE in tf.image.generate_bounding_box_proposals on GPU (CVE-2022-41888)

Fixes a segfault in pywrap_tfe_src caused by invalid attributes (CVE-2022-41889)

Fixes a CHECK fail in BCast (CVE-2022-41890)

Fixes a segfault in TensorListConcat (CVE-2022-41891)

Fixes a CHECK_EQ fail in TensorListResize (CVE-2022-41893)

Fixes an overflow in CONV_3D_TRANSPOSE on TFLite (CVE-2022-41894)

Fixes a heap OOB in MirrorPadGrad (CVE-2022-41895)

Fixes a crash in Mfcc (CVE-2022-41896)

Fixes a heap OOB in FractionalMaxPoolGrad (CVE-2022-41897)

Fixes a CHECK fail in SparseFillEmptyRowsGrad (CVE-2022-41898)

Fixes a CHECK fail in SdcaOptimizer (CVE-2022-41899)

Fixes a heap OOB in FractionalAvgPool and FractionalMaxPool(CVE-2022-41900)

Fixes a CHECK_EQ in SparseMatrixNNZ (CVE-2022-41901)

Fixes an OOB write in grappler (CVE-2022-41902)

Fixes a overflow in ResizeNearestNeighborGrad (CVE-2022-41907)

Fixes a CHECK fail in PyFunc (CVE-2022-41908)

Fixes a segfault in CompositeTensorVariantToComponents (CVE-2022-41909)

Fixes a invalid char to bool conversion in printing a tensor (CVE-2022-41911)

Fixes a heap overflow in QuantizeAndDequantizeV2 (CVE-2022-41910)

Fixes a CHECK failure in SobolSample via missing validation (CVE-2022-35935)

Fixes a CHECK fail in TensorListScatter and TensorListScatterV2 in eager mode (CVE-2022-35935)

TensorFlow 2.9.2

Release 2.9.2

This releases introduces several vulnerability fixes:

Fixes a CHECK failure in tf.reshape caused by overflows (CVE-2022-35934)

Fixes a CHECK failure in SobolSample caused by missing validation (CVE-2022-35935)

Fixes an OOB read in Gather_nd op in TF Lite (CVE-2022-35937)

Fixes a CHECK failure in TensorListReserve caused by missing validation (CVE-2022-35960)

Fixes an OOB write in Scatter_nd op in TF Lite (CVE-2022-35939)

Fixes an integer overflow in RaggedRangeOp (CVE-2022-35940)

Fixes a CHECK failure in AvgPoolOp (CVE-2022-35941)

Fixes a CHECK failures in UnbatchGradOp (CVE-2022-35952)

Fixes a segfault TFLite converter on per-channel quantized transposed convolutions (CVE-2022-36027)

Fixes a CHECK failures in AvgPool3DGrad (CVE-2022-35959)

Fixes a CHECK failures in FractionalAvgPoolGrad (CVE-2022-35963)

Fixes a segfault in BlockLSTMGradV2 (CVE-2022-35964)

Fixes a segfault in LowerBound and UpperBound (CVE-2022-35965)

... (truncated)

Changelog

Sourced from tensorflow-gpu's changelog.

Release 2.9.3

This release introduces several vulnerability fixes:

Fixes an overflow in tf.keras.losses.poisson (CVE-2022-41887)

Fixes a heap OOB failure in ThreadUnsafeUnigramCandidateSampler caused by missing validation (CVE-2022-41880)

Fixes a segfault in ndarray_tensor_bridge (CVE-2022-41884)

Fixes an overflow in FusedResizeAndPadConv2D (CVE-2022-41885)

Fixes a overflow in ImageProjectiveTransformV2 (CVE-2022-41886)

Fixes an FPE in tf.image.generate_bounding_box_proposals on GPU (CVE-2022-41888)

Fixes a segfault in pywrap_tfe_src caused by invalid attributes (CVE-2022-41889)

Fixes a CHECK fail in BCast (CVE-2022-41890)

Fixes a segfault in TensorListConcat (CVE-2022-41891)

Fixes a CHECK_EQ fail in TensorListResize (CVE-2022-41893)

Fixes an overflow in CONV_3D_TRANSPOSE on TFLite (CVE-2022-41894)

Fixes a heap OOB in MirrorPadGrad (CVE-2022-41895)

Fixes a crash in Mfcc (CVE-2022-41896)

Fixes a heap OOB in FractionalMaxPoolGrad (CVE-2022-41897)

Fixes a CHECK fail in SparseFillEmptyRowsGrad (CVE-2022-41898)

Fixes a CHECK fail in SdcaOptimizer (CVE-2022-41899)

Fixes a heap OOB in FractionalAvgPool and FractionalMaxPool(CVE-2022-41900)

Fixes a CHECK_EQ in SparseMatrixNNZ (CVE-2022-41901)

Fixes an OOB write in grappler (CVE-2022-41902)

Fixes a overflow in ResizeNearestNeighborGrad (CVE-2022-41907)

Fixes a CHECK fail in PyFunc (CVE-2022-41908)

Fixes a segfault in CompositeTensorVariantToComponents (CVE-2022-41909)

Fixes a invalid char to bool conversion in printing a tensor (CVE-2022-41911)

Fixes a heap overflow in QuantizeAndDequantizeV2 (CVE-2022-41910)

Fixes a CHECK failure in SobolSample via missing validation (CVE-2022-35935)

Fixes a CHECK fail in TensorListScatter and TensorListScatterV2 in eager mode (CVE-2022-35935)

Release 2.8.4

This release introduces several vulnerability fixes:

Fixes a heap OOB failure in ThreadUnsafeUnigramCandidateSampler caused by missing validation (CVE-2022-41880)

Fixes a segfault in ndarray_tensor_bridge (CVE-2022-41884)

Fixes an overflow in FusedResizeAndPadConv2D (CVE-2022-41885)

Fixes a overflow in ImageProjectiveTransformV2 (CVE-2022-41886)

Fixes an FPE in tf.image.generate_bounding_box_proposals on GPU (CVE-2022-41888)

Fixes a segfault in pywrap_tfe_src caused by invalid attributes (CVE-2022-41889)

Fixes a CHECK fail in BCast (CVE-2022-41890)

Fixes a segfault in TensorListConcat (CVE-2022-41891)

Fixes a CHECK_EQ fail in TensorListResize (CVE-2022-41893)

Fixes an overflow in CONV_3D_TRANSPOSE on TFLite (CVE-2022-41894)

Fixes a heap OOB in MirrorPadGrad (CVE-2022-41895)

Fixes a crash in Mfcc (CVE-2022-41896)

Fixes a heap OOB in FractionalMaxPoolGrad (CVE-2022-41897)

Fixes a CHECK fail in SparseFillEmptyRowsGrad (CVE-2022-41898)

Fixes a CHECK fail in SdcaOptimizer (CVE-2022-41899)

... (truncated)

Commits

a5ed5f3 Merge pull request #58584 from tensorflow/vinila21-patch-2

258f9a1 Update py_func.cc

cd27cfb Merge pull request #58580 from tensorflow-jenkins/version-numbers-2.9.3-24474

3e75385 Update version numbers to 2.9.3

bc72c39 Merge pull request #58482 from tensorflow-jenkins/relnotes-2.9.3-25695

3506c90 Update RELEASE.md

8dcb48e Update RELEASE.md

4f34ec8 Merge pull request #58576 from pak-laura/c2.99f03a9d3bafe902c1e6beb105b2f2417...

6fc67e4 Replace CHECK with returning an InternalError on failing to create python tuple

5dbe90a Merge pull request #58570 from tensorflow/r2.9-7b174a0f2e4

Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

@dependabot rebase will rebase this PR

@dependabot recreate will recreate this PR, overwriting any edits that have been made to it

@dependabot merge will merge this PR after your CI passes on it

@dependabot squash and merge will squash and merge this PR after your CI passes on it

@dependabot cancel merge will cancel a previously requested merge and block automerging

@dependabot reopen will reopen this PR if it is closed

@dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually

@dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)

@dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)

@dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

@dependabot use these labels will set the current labels as the default for future PRs for this repo and language

@dependabot use these reviewers will set the current reviewers as the default for future PRs for this repo and language

@dependabot use these assignees will set the current assignees as the default for future PRs for this repo and language

@dependabot use this milestone will set the current milestone as the default for future PRs for this repo and language

You can disable automated security fix PRs for this repo from the Security Alerts page.

wontfix dependencies
opened by dependabot[bot] 1

Owner

GitHub

A repository that shares tuning results of trained models generated by TensorFlow / Keras. Post-training quantization (Weight Quantization, Integer Quantization, Full Integer Quantization, Float16 Quantization), Quantization-aware training. TensorFlow Lite. OpenVINO. CoreML. TensorFlow.js. TF-TRT. MediaPipe. ONNX. [.tflite,.h5,.pb,saved_model,tfjs,tftrt,mlmodel,.xml/.bin, .onnx]

PINTO_model_zoo Please read the contents of the LICENSE file located directly under each folder before using the model. My model conversion scripts ar

2.4k Jan 5, 2023

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

Mask R-CNN for Object Detection and Segmentation This is an implementation of Mask R-CNN on Python 3, Keras, and TensorFlow. The model generates bound

22.5k Jan 4, 2023

This is an implementation of Googles Yogi-Optimizer in Keras (tf.keras)

Yogi-Optimizer_Keras This is an implementation of Googles Yogi-Optimizer in Keras (tf.keras) The NeurIPS-Paper can be found here: http://papers.nips.c

14 Sep 13, 2022

Keras udrl - Keras implementation of Upside Down Reinforcement Learning

keras_udrl Keras implementation of Upside Down Reinforcement Learning This is me

7 Jan 24, 2022

Face Mask Detection on Image and Video using tensorflow and keras

Face-Mask-Detection Face Mask Detection on Image and Video using tensorflow and keras Train Neural Network on face-mask dataset using tensorflow and k

12 Nov 11, 2022

Hybrid CenterNet - Hybrid-supervised object detection / Weakly semi-supervised object detection

Hybrid-Supervised Object Detection System Object detection system trained by hybrid-supervision/weakly semi-supervision (HSOD/WSSOD): This project is

5 Dec 10, 2022

Yolo object detection - Yolo object detection with python

How to run download required files make build_image make download Docker versio

3 Jan 26, 2022

(JMLR'19) A Python Toolbox for Scalable Outlier Detection (Anomaly Detection)

Python Outlier Detection (PyOD) Deployment & Documentation & Stats Build Status & Coverage & Maintainability & License PyOD is a comprehensive and sca

6.6k Jan 3, 2023

Si Adek Keras is software VR dangerous object detection.

Si Adek Python Keras Sistem Informasi Deteksi Benda Berbahaya Keras Python. Version 1.0 Developed by Ananda Rauf Maududi. Developed date: 24 November

1 Dec 21, 2021

Classification models 1D Zoo - Keras and TF.Keras

Classification models 1D Zoo - Keras and TF.Keras This repository contains 1D variants of popular CNN models for classification like ResNets, DenseNet

12 Jan 6, 2023

Example-custom-ml-block-keras - Custom Keras ML block example for Edge Impulse

Custom Keras ML block example for Edge Impulse This repository is an example on

8 Nov 2, 2022

MOT-Tracking-by-Detection-Pipeline - For Tracking-by-Detection format MOT (Multi Object Tracking), is it a framework that separates Detection and Tracking processes?

MOT-Tracking-by-Detection-Pipeline Tracking-by-Detection形式のMOT(Multi Object Trac

41 Nov 23, 2022

Segcache: a memory-efficient and scalable in-memory key-value cache for small objects

Segcache: a memory-efficient and scalable in-memory key-value cache for small objects This repo contains the code of Segcache described in the followi

78 Jan 7, 2023

Tensorflow 2.x implementation of Panoramic BlitzNet for object detection and semantic segmentation on indoor panoramic images.

Deep neural network for object detection and semantic segmentation on indoor panoramic images. The implementation is based on the papers:

9 Nov 24, 2022

Implementation of ConvMixer in TensorFlow and Keras

ConvMixer ConvMixer, an extremely simple model that is similar in spirit to the ViT and the even-more-basic MLP-Mixer in that it operates directly on

8 Oct 3, 2022

Implementation of ConvMixer-Patches Are All You Need? in TensorFlow and Keras

Patches Are All You Need? - ConvMixer ConvMixer, an extremely simple model that is similar in spirit to the ViT and the even-more-basic MLP-Mixer in t

8 Oct 3, 2022

Unofficial Tensorflow-Keras implementation of Fastformer based on paper [Fastformer: Additive Attention Can Be All You Need](https://arxiv.org/abs/2108.09084).

Fastformer-Keras Unofficial Tensorflow-Keras implementation of Fastformer based on paper Fastformer: Additive Attention Can Be All You Need. Tensorflo

10 Jan 30, 2022

A Keras implementation of YOLOv4 (Tensorflow backend)

keras-yolo4 请使用更完善的版本: https://github.com/miemie2013/Keras-YOLOv4 Please visit here for more complete model: https://github.com/miemie2013/Keras-YOLOv

384 Nov 29, 2022

A tensorflow/keras implementation of StyleGAN to generate images of new Pokemon.

PokeGAN A tensorflow/keras implementation of StyleGAN to generate images of new Pokemon. Dataset The model has been trained on dataset that includes 8

19 Jul 26, 2022