This is a tensorflow-based rotation detection benchmark, also called AlphaRotate.

Last update: Jan 05, 2023

Related tags

Deep Learning RotationDetection

Overview

AlphaRotate: A Rotation Detection Benchmark using TensorFlow

Abstract

AlphaRotate is maintained by Xue Yang with Shanghai Jiao Tong University supervised by Prof. Junchi Yan.

Papers and codes related to remote sensing/aerial image detection: DOTA-DOAI .

Techniques:

The above-mentioned rotation detectors are all modified based on the following horizontal detectors:

Faster RCNN: TF code
R-FCN: TF code
FPN: TF code1 , TF code2 (Deprecated)
Cascade RCNN: TF code
Cascade FPN RCNN: TF code
RetinaNet: TF code
RefineDet: MxNet code
FCOS: TF code , MxNet code

Projects

Latest Performance

DOTA (Task1)

Baseline

Backbone	Neck	Training/test dataset	Data Augmentation	Epoch	NMS
ResNet50_v1d 600->800	FPN	trainval/test	×	13 (AP50) or 17 (AP50:95) is enough for baseline (default is 13)	gpu nms (slightly worse <1% than cpu nms but faster)

Method	Baseline	DOTA1.0	DOTA1.5	DOTA2.0	Model	Anchor	Angle Pred.	Reg. Loss	Angle Range	Configs
-	RetinaNet-R	67.25	56.50	42.04	Baidu Drive (bi8b)	R	Reg. (∆⍬)	smooth L1	[-90,0)	dota1.0, dota1.5, dota2.0
-	RetinaNet-H	64.17	56.10	43.06	Baidu Drive (bi8b)	H	Reg. (∆⍬)	smooth L1	[-90,90)	dota1.0, dota1.5, dota2.0
-	RetinaNet-H	65.33	57.21	44.58	Baidu Drive (bi8b)	H	Reg. (sin⍬, cos⍬)	smooth L1	[-90,90)	dota1.0, dota1.5, dota2.0
-	RetinaNet-H	65.73	58.87	44.16	Baidu Drive (bi8b)	H	Reg. (∆⍬)	smooth L1	[-90,0)	dota1.0, dota1.5, dota2.0
IoU-Smooth L1	RetinaNet-H	66.99	59.17	46.31	Baidu Drive (qcvc)	H	Reg. (∆⍬)	iou-smooth L1	[-90,0)	dota1.0, dota1.5, dota2.0
RIDet	RetinaNet-H	66.06	58.91	45.35	Baidu Drive (njjv)	H	Quad.	hungarian loss	-	dota1.0, dota1.5, dota2.0
RSDet	RetinaNet-H	67.27	61.42	46.71	Baidu Drive (2a1f)	H	Quad.	modulated loss	-	dota1.0, dota1.5, dota2.0
CSL	RetinaNet-H	67.38	58.55	43.34	Baidu Drive (sdbb)	H	Cls.: Gaussian (r=1, w=10)	smooth L1	[-90,90)	dota1.0, dota1.5, dota2.0
DCL	RetinaNet-H	67.39	59.38	45.46	Baidu Drive (m7pq)	H	Cls.: BCL (w=180/256)	smooth L1	[-90,90)	dota1.0, dota1.5, dota2.0
-	FCOS	67.69	61.05	48.10	Baidu Drive (pic4)	-	Quad	smooth L1	-	dota1.0, dota1.5, dota2.0
RSDet++	FCOS	67.91	62.18	48.81	Baidu Drive (8ww5)	-	Quad	modulated loss	-	dota1.0, dota1.5 dota2.0
GWD	RetinaNet-H	68.93	60.03	46.65	Baidu Drive (7g5a)	H	Reg. (∆⍬)	gwd	[-90,0)	dota1.0, dota1.5, dota2.0
GWD + SWA	RetinaNet-H	69.92	60.60	47.63	Baidu Drive (qcn0)	H	Reg. (∆⍬)	gwd	[-90,0)	dota1.0, dota1.5, dota2.0
BCD	RetinaNet-H	71.23	60.78	47.48	Baidu Drive (0puk)	H	Reg. (∆⍬)	bcd	[-90,0)	dota1.0, dota1.5, dota2.0
KLD	RetinaNet-H	71.28	62.50	47.69	Baidu Drive (o6rv)	H	Reg. (∆⍬)	kld	[-90,0)	dota1.0, dota1.5, dota2.0
KFIoU	RetinaNet-H	70.64	62.71	48.04	Baidu Drive (o72o)	H	Reg. (∆⍬)	kf	[-90,0)	dota1.0, dota1.5, dota2.0
R³Det	RetinaNet-H	70.66	62.91	48.43	Baidu Drive (n9mv)	H->R	Reg. (∆⍬)	smooth L1	[-90,0)	dota1.0, dota1.5, dota2.0
DCL	R³Det	71.21	61.98	48.71	Baidu Drive (eg2s)	H->R	Cls.: BCL (w=180/256)	iou-smooth L1	[-90,0)->[-90,90)	dota1.0, dota1.5, dota2.0
GWD	R³Det	71.56	63.22	49.25	Baidu Drive (jb6e)	H->R	Reg. (∆⍬)	smooth L1->gwd	[-90,0)	dota1.0, dota1.5, dota2.0
BCD	R³Det	72.22	63.53	49.71	Baidu Drive (v60g)	H->R	Reg. (∆⍬)	bcd	[-90,0)	dota1.0, dota1.5, dota2.0
KLD	R³Det	71.73	65.18	50.90	Baidu Drive (tq7f)	H->R	Reg. (∆⍬)	kld	[-90,0)	dota1.0, dota1.5, dota2.0
KFIoU	R³Det	72.28	64.69	50.41	Baidu Drive (u77v)	H->R	Reg. (∆⍬)	kf	[-90,0)	dota1.0, dota1.5, dota2.0
-	R²CNN (Faster-RCNN)	72.27	66.45	52.35	Baidu Drive (02s5)	H->R	Reg. (∆⍬)	smooth L1	[-90,0)	dota1.0, dota1.5 dota2.0

SOTA

Method	Backbone	DOTA1.0	Model	MS	Data Augmentation	Epoch	Configs
R²CNN-BCD	ResNet152_v1d-FPN	79.54	Baidu Drive (h2u1)	√	√	34	dota1.0
RetinaNet-BCD	ResNet152_v1d-FPN	78.52	Baidu Drive (0puk)	√	√	51	dota1.0
R³Det-BCD	ResNet50_v1d-FPN	79.08	Baidu Drive (v60g)	√	√	51	dota1.0
R³Det-BCD	ResNet152_v1d-FPN	79.95	Baidu Drive (v60g)	√	√	51	dota1.0

Note:

Single GPU training: SAVE_WEIGHTS_INTE = iter_epoch * 1 (DOTA1.0: iter_epoch=27000, DOTA1.5: iter_epoch=32000, DOTA2.0: iter_epoch=40000)
Multi-GPU training (better): SAVE_WEIGHTS_INTE = iter_epoch * 2

Installation

Manual configuration

pip install -r requirements.txt
pip install -v -e .  # or "python setup.py develop"

Or, you can simply install AlphaRotate with the following command:

pip install alpharotate

Docker

docker images: yangxue2docker/yx-tf-det:tensorflow1.13.1-cuda10-gpu-py3

Note: For 30xx series graphics cards, I recommend this blog to install tf1.xx, or download image from tensorflow-release-notes according to your development environment, e.g. nvcr.io/nvidia/tensorflow:20.11-tf1-py3

Download Model

Pretrain weights

Download a pretrain weight you need from the following three options, and then put it to $PATH_ROOT/dataloader/pretrained_weights.

MxNet pretrain weights (recommend in this repo, default in NET_NAME): resnet_v1d, resnet_v1b, refer to gluon2TF.

Tensorflow pretrain weights: resnet50_v1, resnet101_v1, resnet152_v1, efficientnet, mobilenet_v2, darknet53 (Baidu Drive (1jg2), Google Drive).
Pytorch pretrain weights, refer to pretrain_zoo.py and Others.

Trained weights

Please download trained models by this project, then put them to $PATH_ROOT/output/pretained_weights.

Train

If you want to train your own dataset, please note:

(1) Select the detector and dataset you want to use, and mark them as #DETECTOR and #DATASET (such as #DETECTOR=retinanet and #DATASET=DOTA)
(2) Modify parameters (such as CLASS_NUM, DATASET_NAME, VERSION, etc.) in $PATH_ROOT/libs/configs/#DATASET/#DETECTOR/cfgs_xxx.py
(3) Copy $PATH_ROOT/libs/configs/#DATASET/#DETECTOR/cfgs_xxx.py to $PATH_ROOT/libs/configs/cfgs.py
(4) Add category information in $PATH_ROOT/libs/label_name_dict/label_dict.py     
(5) Add data_name to $PATH_ROOT/dataloader/dataset/read_tfrecord.py

Make tfrecord
If image is very large (such as DOTA dataset), the image needs to be cropped. Take DOTA dataset as a example:

cd $PATH_ROOT/dataloader/dataset/DOTA
python data_crop.py

If image does not need to be cropped, just convert the annotation file into xml format, refer to example.xml.

cd $PATH_ROOT/dataloader/dataset/  
python convert_data_to_tfrecord.py --root_dir='/PATH/TO/DOTA/' 
                                   --xml_dir='labeltxt'
                                   --image_dir='images'
                                   --save_name='train' 
                                   --img_format='.png' 
                                   --dataset='DOTA'

Start training

cd $PATH_ROOT/tools/#DETECTOR
python train.py

Test

For large-scale image, take DOTA dataset as a example (the output file or visualization is in $PATH_ROOT/tools/#DETECTOR/test_dota/VERSION):

cd $PATH_ROOT/tools/#DETECTOR
python test_dota.py --test_dir='/PATH/TO/IMAGES/'  
                    --gpus=0,1,2,3,4,5,6,7  
                    -ms (multi-scale testing, optional)
                    -s (visualization, optional)
                    -cn (use cpu nms, slightly better <1% than gpu nms but slower, optional)

or (recommend in this repo, better than multi-scale testing)

python test_dota_sota.py --test_dir='/PATH/TO/IMAGES/'  
                         --gpus=0,1,2,3,4,5,6,7  
                         -s (visualization, optional)
                         -cn (use cpu nms, slightly better <1% than gpu nms but slower, optional)

Notice: In order to set the breakpoint conveniently, the read and write mode of the file is' a+'. If the model of the same #VERSION needs to be tested again, the original test results need to be deleted.

For small-scale image, take HRSC2016 dataset as a example:

cd $PATH_ROOT/tools/#DETECTOR
python test_hrsc2016.py --test_dir='/PATH/TO/IMAGES/'  
                        --gpu=0
                        --image_ext='bmp'
                        --test_annotation_path='/PATH/TO/ANNOTATIONS'
                        -s (visualization, optional)

Tensorboard

cd $PATH_ROOT/output/summary
tensorboard --logdir=.

Citation

If you find our code useful for your research, please consider cite.

@article{yang2021alpharotate,
    author  = {Yang, Xue and Zhou, Yue and Yan, Junchi},
    title   = {AlphaRotate: A Rotation Detection Benchmark using TensorFlow},
    year    = {2021},
    url     = {https://github.com/yangxue0827/RotationDetection}
}

Reference

1、https://github.com/endernewton/tf-faster-rcnn
2、https://github.com/zengarden/light_head_rcnn
3、https://github.com/tensorflow/models/tree/master/research/object_detection
4、https://github.com/fizyr/keras-retinanet

Comments

"ValueError: too many values to unpack" RotationDetection/alpharotate/libs/models/detectors/scrdet/build_whole_network.py 147Line

Problem path: RotationDetection/alpharotate/libs/models/detectors/scrdet/build_whole_network.py

147 Line. feature, pa_mask = self.build_backbone(input_img_batch)

Since only one variable is returned, why store it in two variables?

It is error that "ValueError: too many values to unpack"

what is pa_mask parameter's mean and rule?

opened by sangheonEN 38
Gradient about IOU-Smooth L1 loss in SCRDet

here's the relative link

In the link I say the backward gradient will be 0 eternally.

In other point, make the |u| underivable that gradient will not be 0. But the gradient of u/|u| is not 1 anymore.

@yangxue0827 Could you please help me out? Many thanks!

opened by igo312 10
How may I use this repo for building orientation detection ?

Sorry if my question is irrelevant, but this is what I am instructed to do as an assignment. I am instructed to use this repo for detecting the orientation of various building in an image. Please guide me for the same.

opened by neutr0nStar 8
Request for model files tested on DOTA-v1.5

It is impossible to download the model files from pan Baidu for non-Chinese people.

For the sake of research transparency, can I request if ALL the model files tested on DOTA-v1.5 be uploaded to my google drive: https://drive.google.com/drive/folders/1ekgV7cGZIo27JxG1wRywQtZHKnfsaVV2?usp=sharing

opened by chandlerbing65nm 7
Alternative cloud for trained models

Hello @yangxue0827,

I cannot create a Baidu account. Could you upload the trained models in another cloud such as Dropbox, Onedrive o Google Drive? If it is not possible ... could you send me all these trained models via email? Thank you so much.

Best regards, Roberto Valle

opened by bobetocalo 7
Download Trained Model

Hello

I would like to know, where I can download the trained model (not pretrained):

"Please download trained models by this project, then put them to trained_weights."

When I go to Baidu and enter the code from here: https://github.com/yangxue0827/RotationDetection/issues/29#issuecomment-896431674 I still cannot download as some pop up comes up that I cannot read. Is there maybe any other place (Google Drive) where I can find it?

Best regards and thank you

opened by Testbild 6
Where is trained models?

Thank you for your contribution to the detection community. And I notice that “Latest: More results and trained models are available in the MODEL_ZOO.md.” in README.md，but I can’t find the “MODEL_ZOO.md”. If you could provide the trained model，words cannot express how thankful I am.

opened by 1995gatch 6
ValueError: Tried to convert 'input' to a tensor and failed. Error: None values not supported.

在跑scrnet时出现问题，打印g之后发现 $$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$ Tensor("tower_0/clip_by_norm_88:0", shape=(3, 3, 256, 256), dtype=float32, device=/device:GPU:0) $$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$ Tensor("tower_1/clip_by_norm_88:0", shape=(3, 3, 256, 256), dtype=float32, device=/device:GPU:1) $$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$ Tensor("tower_0/clip_by_norm_89:0", shape=(1, 1, 256, 1024), dtype=float32, device=/device:GPU:0) $$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$ Tensor("tower_1/clip_by_norm_89:0", shape=(1, 1, 256, 1024), dtype=float32, device=/device:GPU:1) $$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$ None

opened by xxx0320 6
关于R3det_kl的训练问题

大佬你好！想请教一下，在r3det_kl的训练过程中，使用resnet_50的pretrained weights，reg_loss一直震荡，想问问是哪一步出现了问题呢？

cfgs设置和loss图像如下。

SAVE_WEIGHTS_INTE = 27000 * 1 CLS_WEIGHT = 1.0 REG_WEIGHT = 2.0 REG_LOSS_MODE = 3 # KLD loss

opened by yanglcs 5
How to test train and test retinanet-gwd in HRSC2016 dataset?
1.i have downloaded trained models by this project, then put them to $PATH_ROOT/output/pretained_weights. the pretained_weights is resnet_v1d. 2. i have compiled .

cd $PATH_ROOT/libs/utils/cython_utils rm *.so rm *.c rm *.cpp python setup.py build_ext --inplace (or make) cd $PATH_ROOT/libs/utils/ rm *.so rm *.c rm *.cpp python setup.py build_ext --inplace

i have Copied $PATH_ROOT/libs/configs/HRSC2016/gwd/cfgs_res50_hrsc2016_gwd_v6.py to$PATH_ROOT/libs/configs/cfgs.py

the structure directory of HRSC2016 Dataset

5.when i python tools/gwd/train.py ，i got some errors.

2021-09-05 07:49:28.459600: W tensorflow/core/framework/op_kernel.cc:1651] OP_REQUIRES failed at matching_files_op.cc:49 : Not found: ../../dataloader/tfrecord; No such file or directory 2021-09-05 07:49:28.534617: W tensorflow/core/framework/op_kernel.cc:1651] OP_REQUIRES failed at matching_files_op.cc:49 : Not found: ../../dataloader/tfrecord; No such file or directory Traceback (most recent call last): File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/client/session.py", line 1365, in _do_call return fn(*args) File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/client/session.py", line 1350, in _run_fn target_list, run_metadata) File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/client/session.py", line 1443, in _call_tf_sessionrun run_metadata) tensorflow.python.framework.errors_impl.NotFoundError: ../../dataloader/tfrecord; No such file or directory [[{{node get_batch/matching_filenames/MatchingFiles}}]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "train.py", line 160, in trainer.main() File "train.py", line 155, in main self.log_printer(gwd, optimizer, global_step, tower_grads, total_loss_dict, num_gpu, graph) File "../../tools/train_base.py", line 196, in log_printer sess.run(init_op) File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/client/session.py", line 956, in run run_metadata_ptr) File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/client/session.py", line 1180, in _run feed_dict_tensor, options, run_metadata) File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/client/session.py", line 1359, in _do_run run_metadata) File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/client/session.py", line 1384, in _do_call raise type(e)(node_def, op, message) tensorflow.python.framework.errors_impl.NotFoundError: ../../dataloader/tfrecord; No such file or directory [[node get_batch/matching_filenames/MatchingFiles (defined at /usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/ops.py:1748) ]]

Original stack trace for 'get_batch/matching_filenames/MatchingFiles': File "train.py", line 160, in trainer.main() File "train.py", line 53, in main is_training=True) File "../../dataloader/dataset/read_tfrecord.py", line 115, in next_batch filename_tensorlist = tf.train.match_filenames_once(pattern) File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/training/input.py", line 76, in match_filenames_once name=name, initial_value=io_ops.matching_files(pattern), File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/gen_io_ops.py", line 464, in matching_files "MatchingFiles", pattern=pattern, name=name) File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/op_def_library.py", line 794, in _apply_op_helper op_def=op_def) File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/util/deprecation.py", line 513, in new_func return func(*args, **kwargs) File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/ops.py", line 3357, in create_op attrs, op_def, compute_device) File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/ops.py", line 3426, in _create_op_internal op_def=op_def) File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/ops.py", line 1748, in init self._traceback = tf_stack.extract_stack()

Can you help me solve this problem? i hope your reply
opened by myGithubSiki 5
为何nms没有起作用？

大佬您好，我想请教下为何nms好像没有起作用。系统是Ubuntu18.04，nms部分已经编译了。算法用的是gwd，训练和测试均能正常进行，就是有的好像经过了nms处理，有的又没有，而且训练和测试的时候我都把nms开启了

post-processing

NMS = True NMS_IOU_THRESHOLD = 0.45 MAXIMUM_DETECTIONS = 200 FILTERED_SCORE = 0.5 VIS_SCORE = 0.4

test and eval

TEST_SAVE_PATH = os.path.join(ROOT_PATH, 'tools/test_result') EVALUATE_R_DIR = os.path.join(ROOT_PATH, 'output/evaluate_result_pickle/') USE_07_METRIC = True EVAL_THRESHOLD = 0.45

训练：

测试：

opened by Chrispaoge 4
not found the implementation of indirect angle regression

Great work, thanks for sharing the project. I did not find the implementation of the indirect angle regression which is explained in your TPAMI paper. Have I missed or this part is not included in this public project? Thanks.

opened by menchael 0
Baidu signup impossible for non-chinese users, access to models possible through other apps?

Hi, Baidu doesn't accept international phone numbers so won't allow signing up. This will extremely limit the usage of your model. Have you copied your model weights in another platform such as google drive or microsoft onedrive?

Please let me know. Thank you

opened by shnamin 0

Tranfer Learning

Hello, I have a question regarding training a custom dataset.

How can I transfer learning of some specific classes from the pre-trained weights (e.g. dota) to my custom training if my custom classes are different from the pre-trained classes?

Best regards and Thank you

opened by wafa-bouzouita 1

Releases(v1.0.1)

v1.0.1(Nov 3, 2021)

support dior-r
Source code(tar.gz)
Source code(zip)
v1.0.0(Nov 3, 2021)

Basic version
Source code(tar.gz)
Source code(zip)

Owner

yangxue

Welcome academic cooperation. WeChat: yangxue-0826

GitHub Repository https://rotationdetection.readthedocs.io/

Inflated i3d network with inception backbone, weights transfered from tensorflow

I3D models transfered from Tensorflow to PyTorch This repo contains several scripts that allow to transfer the weights from the tensorflow implementat

479 Dec 08, 2022

Hyperopt for solving CIFAR-100 with a convolutional neural network (CNN) built with Keras and TensorFlow, GPU backend

Hyperopt for solving CIFAR-100 with a convolutional neural network (CNN) built with Keras and TensorFlow, GPU backend This project acts as both a tuto

103 Jul 22, 2022

NAS-Bench-x11 and the Power of Learning Curves

NAS-Bench-x11 NAS-Bench-x11 and the Power of Learning Curves Shen Yan, Colin White, Yash Savani, Frank Hutter. NeurIPS 2021. Surrogate NAS benchmarks

13 Nov 18, 2022

[CVPR 2021] Official PyTorch Implementation for "Iterative Filter Adaptive Network for Single Image Defocus Deblurring"

IFAN: Iterative Filter Adaptive Network for Single Image Defocus Deblurring Checkout for the demo (GUI/Google Colab)! The GUI version might occasional

173 Dec 30, 2022

Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021

LoFTR: Detector-Free Local Feature Matching with Transformers Project Page | Paper LoFTR: Detector-Free Local Feature Matching with Transformers Jiami

1.4k Jan 04, 2023

HiFT: Hierarchical Feature Transformer for Aerial Tracking (ICCV2021)

HiFT: Hierarchical Feature Transformer for Aerial Tracking Ziang Cao, Changhong Fu, Junjie Ye, Bowen Li, and Yiming Li Our paper is Accepted by ICCV 2

55 Nov 23, 2022

Awesome Artificial Intelligence, Machine Learning and Deep Learning as we learn it

Awesome Artificial Intelligence, Machine Learning and Deep Learning as we learn it. Study notes and a curated list of awesome resources of such topics.

1.2k Jan 07, 2023

Deep Learning Based EDM Subgenre Classification using Mel-Spectrogram and Tempogram Features"

EDM-subgenre-classifier This repository contains the code for "Deep Learning Based EDM Subgenre Classification using Mel-Spectrogram and Tempogram Fea

11 Dec 20, 2022

PyTorch implementation of CVPR 2020 paper (Reference-Based Sketch Image Colorization using Augmented-Self Reference and Dense Semantic Correspondence) and pre-trained model on ImageNet dataset

Reference-Based-Sketch-Image-Colorization-ImageNet This is a PyTorch implementation of CVPR 2020 paper (Reference-Based Sketch Image Colorization usin

11 Jul 28, 2022

Automatically replace ONNX's RandomNormal node with Constant node.

onnx-remove-random-normal This is a script to replace RandomNormal node with Constant node. Example Imagine that we have something ONNX model like the

1 Dec 11, 2021

Intelligent Video Analytics toolkit based on different inference backends.

English | 中文 OpenIVA OpenIVA is an end-to-end intelligent video analytics development toolkit based on different inference backends, designed to help

15 Oct 27, 2022

Finetuner allows one to tune the weights of any deep neural network for better embeddings on search tasks

794 Dec 31, 2022

Python3 / PyTorch implementation of the following paper: Fine-grained Semantics-aware Representation Enhancement for Self-supervisedMonocular Depth Estimation. ICCV 2021 (oral)

FSRE-Depth This is a Python3 / PyTorch implementation of FSRE-Depth, as described in the following paper: Fine-grained Semantics-aware Representation

77 Dec 28, 2022