Keras implementation of Deeplab v3+ with pretrained weights

Overview

Keras implementation of Deeplabv3+

This repo is not longer maintained. I won't respond to issues but will merge PR
DeepLab is a state-of-art deep learning model for semantic image segmentation.

Model is based on the original TF frozen graph. It is possible to load pretrained weights into this model. Weights are directly imported from original TF checkpoint.

Segmentation results of original TF model. Output Stride = 8




Segmentation results of this repo model with loaded weights and OS = 8
Results are identical to the TF model




Segmentation results of this repo model with loaded weights and OS = 16
Results are still good




How to get labels

Model will return tensor of shape (batch_size, height, width, num_classes). To obtain labels, you need to apply argmax to logits at exit layer. Example of predicting on image1.jpg:

import numpy as np
from PIL import Image
from matplotlib import pyplot as plt

from model import Deeplabv3

# Generates labels using most basic setup.  Supports various image sizes.  Returns image labels in same format
# as original image.  Normalization matches MobileNetV2

trained_image_width=512 
mean_subtraction_value=127.5
image = np.array(Image.open('imgs/image1.jpg'))

# resize to max dimension of images from training dataset
w, h, _ = image.shape
ratio = float(trained_image_width) / np.max([w, h])
resized_image = np.array(Image.fromarray(image.astype('uint8')).resize((int(ratio * h), int(ratio * w))))

# apply normalization for trained dataset images
resized_image = (resized_image / mean_subtraction_value) - 1.

# pad array to square image to match training images
pad_x = int(trained_image_width - resized_image.shape[0])
pad_y = int(trained_image_width - resized_image.shape[1])
resized_image = np.pad(resized_image, ((0, pad_x), (0, pad_y), (0, 0)), mode='constant')

# make prediction
deeplab_model = Deeplabv3()
res = deeplab_model.predict(np.expand_dims(resized_image, 0))
labels = np.argmax(res.squeeze(), -1)

# remove padding and resize back to original image
if pad_x > 0:
    labels = labels[:-pad_x]
if pad_y > 0:
    labels = labels[:, :-pad_y]
labels = np.array(Image.fromarray(labels.astype('uint8')).resize((h, w)))

plt.imshow(labels)
plt.waitforbuttonpress()

How to use this model with custom input shape and custom number of classes

from model import Deeplabv3
deeplab_model = Deeplabv3(input_shape=(384, 384, 3), classes=4#or you can use None as shape
deeplab_model = Deeplabv3(input_shape=(None, None, 3), classes=4)

After that you will get a usual Keras model which you can train using .fit and .fit_generator methods.

How to train this model

Useful parameters can be found in the original repository.

Important notes:

  1. This model doesn’t provide default weight decay, user needs to add it themselves.
  2. Due to huge memory use with OS=8, Xception backbone should be trained with OS=16 and only inferenced with OS=8.
  3. User can freeze feature extractor for Xception backbone (first 356 layers) and only fine-tune decoder. Right now (March 2019), there is a problem with finetuning Keras models with BN. You can read more about it here.

Known issues

This model can be retrained check this notebook. Finetuning is tricky and difficult because of the confusion between training and trainable in Keras. See this issue for a discussion and possible alternatives.

How to load model

In order to load model after using model.save() use this code:

from model import relu6
deeplab_model = load_model('example.h5')

Xception vs MobileNetv2

There are 2 available backbones. Xception backbone is more accurate, but has 25 times more parameters than MobileNetv2.

For MobileNetv2 there are pretrained weights only for alpha=1. However, you can initiate model with different values of alpha.

Requirement

The latest vesrion of this repo uses TF Keras, so you only need TF 2.0+ installed
tensorflow-gpu==2.0.0a0
CUDA==9.0


If you want to use older version, use following commands:

git clone https://github.com/bonlime/keras-deeplab-v3-plus/
cd keras-deeplab-v3-plus/
git checkout 714a6b7d1a069a07547c5c08282f1a706db92e20

tensorflow-gpu==1.13
Keras==2.2.4

Comments
  • Performance degradation

    Performance degradation

    Hi,

    I'm using the converted pretrain-weights to measure mIoU and observed 10% drop. Could you sure you measurement results, did you still get 84% mIoU on PASCAL using the transferred model and weights?

    Thanks

    opened by baoruxiao 13
  • Is dialtion_rate useful in keras DepthwiseConv2D layer ?

    Is dialtion_rate useful in keras DepthwiseConv2D layer ?

    Hi, I read the document and found dialtion_rate seems not a hyperparameter in DepthwiseConv2D layer. But you used it in your model x = DepthwiseConv2D((kernel_size, kernel_size), strides=(stride, stride), dilation_rate=(rate, rate)

    I made a toy example to check this:

    model=Sequential()
    model.add(DepthwiseConv2D(3,strides=1,padding='valid',depth_multiplier=2,\
                              dilation_rate=(2,2),input_shape=(9,9,3))) 
    model.summary()
    

    Output:

    _________________________________________________________________
    Layer (type)                 Output Shape              Param #   
    =================================================================
    depthwise_conv2d_6 (Depthwis (None, 7, 7, 6)           60        
    =================================================================
    Total params: 60
    Trainable params: 60
    Non-trainable params: 0
    _________________________________________________________________
    

    If dilation_rate is useful in DepthwiseConv2D , I think Output shape should be (5,5,6) not (7,7,6)

    My English is pretty limited, plz don't mind

    opened by Pofatoezil 10
  • About the softmax layer & label process?

    About the softmax layer & label process?

    Hi, bonlime, Thanks for your work! It helps me a lot! But I have two questions in my training process:

    1. I found there is no 'softmax' on the last layer of the Deeplabv3() model. Is it right if I use model.fit() directly after model=Deeplabv3() without any other process? Or could you please tell me where to use the 'softmax' layer?

    2. In the training image input process, how to correctly deal with labels? In my previous segmentation projects, the training and prediction steps usually operate on single-channel pngs labels, where the value of each pixel corresponds to the class label (for example, 0-21 for the Pascal dataset). Is this project the same as that?

    I'm looking forward to your reply. Thanks!

    opened by YanZhiyuan0918 10
  • The right way of pre-processing for input?

    The right way of pre-processing for input?

    image We use the first img as input, and resize it from (427, 640, 3) to (512, 512, 3), and normalize it from [0,255] to [0,1]. image As below, the output of OS=16 is normal, image

    but the output of OS=8 is worse.

    I can not figure out that, so I think my pre-processiong(such as normalizing) is wrong.

    opened by munanning 9
  • compatibility with tensorflow < 2.0

    compatibility with tensorflow < 2.0

    Hi, as I have cuda 9.0 in Ubuntu 16.04, so tensorflow 2.0 is not an option (tensorflow 1.12 installed instead). when I run the code:

    from model import Deeplabv3 'model=Deeplabv3(input_shape=(None,None,3), backbone='xception',OS=8)I got an error:AttributeError: module 'tensorflow._api.v1.image' has no attribute 'resize'`

    How can I resolve this so that I can run the code in tensorlow 1.120 ? many thanks

    opened by tsing90 7
  • image-level pooling

    image-level pooling

    Hello,

    I checked your code, I think the image-level pooling was not correctly implemented. because it is not computing the global average pooling.

    https://github.com/bonlime/keras-deeplab-v3-plus/blob/master/model.py#L437

    I checked this code: https://github.com/tensorflow/models/blob/4a0ee4a29dd7e4b6e0135ccf6857f4dc58d71a90/research/deeplab/model.py#L397 and Reference are here ref 52 from original paper (https://arxiv.org/pdf/1506.04579.pdf):

    Exploiting the FCN architecture, ParsetNet can directly use global average pooling from the final (or any) feature map, resulting in the feature of the whole image, and use it as context.

    In implementation, this is accomplished by unpooling the context vector and appending the resulting feature map with the standard feature map.

    Specifically, we use global average pooling and pool the context features from the last layer or any layer if that is desired.

    opened by emedinac 7
  • Does the model have errors?

    Does the model have errors?

    When I use fit, it says Error when checking target: expected bilinear_upsampling_2 to have shape (512, 512, 2) but got array with shape (512, 512, 3) ps: My input image.shape is (512,512,3)

    opened by Taylor-Rose 6
  • How can I run the video module to achieve real-time detection?

    How can I run the video module to achieve real-time detection?

    Hello I want to know the speed of deeplabv3+ ,and I try to run that: from keras.preprocessing.image import ImageDataGenerator, array_to_img, img_to_array, load_img from matplotlib import pyplot as plt import cv2 # used for resize. if you dont have it, use anything else import numpy as np from model import Deeplabv3 deeplab_model = Deeplabv3() def detect_video(deeplab_model): import cv2 vid = cv2.VideoCapture(0) if not vid.isOpened(): raise IOError("Couldn't open webcam or video") accum_time = 10 curr_fps = 10 fps = "20" prev_time = timer() while True: return_value, frame = vid.read() res = deeplab_model.predict(frame)

    	result = array_to_img(res)
        curr_time = timer()
        exec_time = curr_time - prev_time
        prev_time = curr_time
        accum_time = accum_time + exec_time
        curr_fps = curr_fps + 1
        if accum_time > 1:
            accum_time = accum_time - 1
            fps = "FPS: " + str(curr_fps)
            curr_fps = 0
        cv2.putText(result, text=fps, org=(3, 15), fontFace=cv2.FONT_HERSHEY_SIMPLEX,
                    fontScale=0.50, color=(255, 0, 0), thickness=2)
        cv2.namedWindow("result", cv2.WINDOW_NORMAL)
        cv2.imshow("result", result)
        if cv2.waitKey(1) & 0xFF == ord('q'):
            break
    deeplab_model.close_session()
    

    detect_video(deeplab_model)

    but it doesn't work! I thank I need your help thanks.

    opened by ll1214 6
  • How can i get each label's coordinates on segmentation map?

    How can i get each label's coordinates on segmentation map?

    import numpy as np
    from PIL import Image
    from matplotlib import pyplot as plt
    
    from model import Deeplabv3
    
    # Generates labels using most basic setup.  Supports various image sizes.  Returns image labels in same format
    # as original image.  Normalization matches MobileNetV2
    
    trained_image_width=512 
    mean_subtraction_value=127.5
    image = np.array(Image.open('imgs/image1.jpg'))
    
    # resize to max dimension of images from training dataset
    w, h, _ = image.shape
    ratio = float(trained_image_width) / np.max([w, h])
    resized_image = np.array(Image.fromarray(image.astype('uint8')).resize((int(ratio * h), int(ratio * w))))
    
    # apply normalization for trained dataset images
    resized_image = (resized_image / mean_subtraction_value) - 1.
    
    # pad array to square image to match training images
    pad_x = int(trained_image_width - resized_image.shape[0])
    pad_y = int(trained_image_width - resized_image.shape[1])
    resized_image = np.pad(resized_image, ((0, pad_x), (0, pad_y), (0, 0)), mode='constant')
    
    # make prediction
    deeplab_model = Deeplabv3()
    res = deeplab_model.predict(np.expand_dims(resized_image, 0))
    labels = np.argmax(res.squeeze(), -1)
    
    # remove padding and resize back to original image
    if pad_x > 0:
        labels = labels[:-pad_x]
    if pad_y > 0:
        labels = labels[:, :-pad_y]
    labels = np.array(Image.fromarray(labels.astype('uint8')).resize((h, w)))
    
    plt.imshow(labels)
    plt.show()
    

    I run this code and get segmentation map But, I want to get result like https://github.com/bonlime/keras-deeplab-v3-plus/blob/master/imgs/seg_results2.png and each label's coordinates on image. How can i do that?

    opened by Baek2back 5
  • Make model.py compatible with Python 3 and switch to tf.image.resize()

    Make model.py compatible with Python 3 and switch to tf.image.resize()

    • make model.py compatible with Python 3 by changing [tensor].shape to [tensor].shape.as_list()
    • move away from tf.compat.v1.image.resize() due to "resize method is not implemented" error.
    • use tf.image.resize() instead because it now supports align_corners=True.
    opened by yanfengliu 5
  • Custom Dataset: Number of Classes

    Custom Dataset: Number of Classes

    Should num_classes take into account the background class. For example, if I have 3 foreground classes that I have masks for and a background class that I don't care about and don't have a mask for, should my num_classes be 3?

    opened by ad12 5
  • Bump pillow from 6.0.0 to 9.3.0

    Bump pillow from 6.0.0 to 9.3.0

    Bumps pillow from 6.0.0 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

    ... (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

    Dependabot compatibility score

    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.

    dependencies 
    opened by dependabot[bot] 0
  • Bump tensorflow from 2.5.0rc0 to 2.9.3

    Bump tensorflow from 2.5.0rc0 to 2.9.3

    Bumps tensorflow from 2.5.0rc0 to 2.9.3.

    Release notes

    Sourced from tensorflow's releases.

    TensorFlow 2.9.3

    Release 2.9.3

    This release introduces several vulnerability fixes:

    TensorFlow 2.9.2

    Release 2.9.2

    This releases introduces several vulnerability fixes:

    ... (truncated)

    Changelog

    Sourced from tensorflow's changelog.

    Release 2.9.3

    This release introduces several vulnerability fixes:

    Release 2.8.4

    This release introduces several vulnerability fixes:

    ... (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 compatibility score

    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.

    dependencies 
    opened by dependabot[bot] 0
  • Citation in Journal

    Citation in Journal

    I would like to cite this repository in a journal paper I'm currently writing as I have used most of the code here. I have already included the reference to the original DeepLabV3+ paper, but I also want to include this repository. What is the best way to cite it? Thanks!

    opened by pedrogalher 1
  • Model not learning anything

    Model not learning anything

    Hi I'm training DeepLabV3+ Mobilenet backbone on my custom dataset. My Dataset has 1 class. My Model architecture looks like:

    deeplab_model = Deeplabv3(input_shape=(512, 512, 3), classes=2,activation='softmax') deeplab_model.compile(optimizer='adam', loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),metrics='accuracy']) deeplab_model.fit(...)

    My Loss is not reducing and the output is all black. My mask is of the shape (512,512) Someone, please guide me what to do? Any help would be great.

    opened by anmol4210 1
  • AttributeError: 'int' object has no attribute 'value'

    AttributeError: 'int' object has no attribute 'value'

    I copy and run this code(and copy images and model.py) :

    from matplotlib import pyplot as plt import cv2 # used for resize. if you dont have it, use anything else import numpy as np from model import Deeplabv3 img = plt.imread("imgs/image1.jpg") print(img.shape) w, h, _ = img.shape ratio = 512. / np.max([w,h]) resized = cv2.resize(img,(int(ratioh),int(ratiow))) resized = resized / 127.5 - 1. new_deeplab_model = Deeplabv3(input_shape=(512,512,3), OS=16)

    pad_x = int(512 - resized.shape[0]) resized2 = np.pad(resized,((0,pad_x),(0,0),(0,0)), mode='constant') res = new_deeplab_model.predict(np.expand_dims(resized2,0)) res_old = old_deeplab_model.predict(np.expand_dims(resized2,0)) labels = np.argmax(res.squeeze(),-1) labels_old = np.argmax(res_old.squeeze(),-1) plt.imshow(labels[:-pad_x]) plt.show() plt.imshow(labels_old[:-pad_x]) plt.show() `

    but I get this error =>

    ERROR:root:An unexpected error occurred while tokenizing input The following traceback may be corrupted or invalid The error message is: ('EOF in multi-line string', (1, 2))


    TypeError Traceback (most recent call last) in () 26 # make prediction 27 deeplab_model = Deeplabv3() ---> 28 res = deeplab_model.predict(np.expand_dims(resized_image, 0)) 29 labels = np.argmax(res.squeeze(), -1) 30

    10 frames /usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs) 966 func_graph: A FuncGraph object to destroy. func_graph is unusable 967 after this function. --> 968 """ 969 # TODO(b/115366440): Delete this method when a custom OrderedDict is added. 970 # Clearing captures using clear() leaves some cycles around.

    TypeError: in user code:

    TypeError: tf__predict_function() missing 8 required positional arguments: 'x', 'batch_size', 'verbose', 'steps', 'callbacks', 'max_queue_size', 'workers', and 'use_multiprocessing'
    
    opened by alikarimi120 1
Releases(1.2)
Owner
Emil Zakirov. MIPT & Skoltech. Computer Vision Engineer.
An implementation of Deep Forest 2021.2.1.

Deep Forest (DF) 21 DF21 is an implementation of Deep Forest 2021.2.1. It is designed to have the following advantages: Powerful: Better accuracy than

LAMDA Group, Nanjing University 795 Jan 03, 2023
A simple approach to emable dense segmentation with ViT.

Vision Transformer Segmentation Network This implementation of ViT in pytorch uses a super simple and straight-forward way of generating an output of

HReynaud 5 Jan 03, 2023
Pytorch implementation of "Forward Thinking: Building and Training Neural Networks One Layer at a Time"

forward-thinking-pytorch Pytorch implementation of Forward Thinking: Building and Training Neural Networks One Layer at a Time Requirements Python 2.7

Kim Heecheol 65 Oct 06, 2022
Subdivision-based Mesh Convolutional Networks

Subdivision-based Mesh Convolutional Networks The official implementation of SubdivNet in our paper, Subdivion-based Mesh Convolutional Networks Requi

Zheng-Ning Liu 181 Dec 28, 2022
Automatically download the cwru data set, and then divide it into training data set and test data set

Automatically download the cwru data set, and then divide it into training data set and test data set.自动下载cwru数据集,然后分训练数据集和测试数据集

6 Jun 27, 2022
Using Convolutional Neural Networks (CNN) for Semantic Segmentation of Breast Cancer Lesions (BRCA)

Using Convolutional Neural Networks (CNN) for Semantic Segmentation of Breast Cancer Lesions (BRCA). Master's thesis documents. Bibliography, experiments and reports.

Erick Cobos 73 Dec 04, 2022
This repository contains code for the paper "Disentangling Label Distribution for Long-tailed Visual Recognition", published at CVPR' 2021

Disentangling Label Distribution for Long-tailed Visual Recognition (CVPR 2021) Arxiv link Blog post This codebase is built on Causal Norm. Install co

Hyperconnect 85 Oct 18, 2022
PyTorch implementation of Progressive Growing of GANs for Improved Quality, Stability, and Variation.

PyTorch implementation of Progressive Growing of GANs for Improved Quality, Stability, and Variation. Warning: the master branch might collapse. To ob

559 Dec 14, 2022
Facial Expression Detection In The Realtime

The human's facial expressions is very important to detect thier emotions and sentiment. It can be very efficient to use to make our computers make interviews. Furthermore, we have robots now can det

Adel El-Nabarawy 4 Mar 01, 2022
Tool for installing and updating MiSTer cores and other files

MiSTer Downloader This tool installs and updates all the cores and other extra files for your MiSTer. It also updates the menu core, the MiSTer firmwa

72 Dec 24, 2022
Simple, efficient and flexible vision toolbox for mxnet framework.

MXbox: Simple, efficient and flexible vision toolbox for mxnet framework. MXbox is a toolbox aiming to provide a general and simple interface for visi

Ligeng Zhu 31 Oct 19, 2019
MoCoPnet - Deformable 3D Convolution for Video Super-Resolution

Deformable 3D Convolution for Video Super-Resolution Pytorch implementation of l

Xinyi Ying 28 Dec 15, 2022
Implementations of paper Controlling Directions Orthogonal to a Classifier

Classifier Orthogonalization Implementations of paper Controlling Directions Orthogonal to a Classifier , ICLR 2022, Yilun Xu, Hao He, Tianxiao Shen,

Yilun Xu 33 Dec 01, 2022
Setup freqtrade/freqUI on Heroku

UNMAINTAINED - REPO MOVED TO https://github.com/p-zombie/freqtrade Creating the app git clone https://github.com/joaorafaelm/freqtrade.git && cd freqt

João 51 Aug 29, 2022
Using Random Effects to Account for High-Cardinality Categorical Features and Repeated Measures in Deep Neural Networks

LMMNN Using Random Effects to Account for High-Cardinality Categorical Features and Repeated Measures in Deep Neural Networks This is the working dire

Giora Simchoni 10 Nov 02, 2022
[CVPR'22] COAP: Learning Compositional Occupancy of People

COAP: Compositional Articulated Occupancy of People Paper | Video | Project Page This is the official implementation of the CVPR 2022 paper COAP: Lear

Marko Mihajlovic 111 Dec 11, 2022
Here we present the implementation in TensorFlow of our work about liver lesion segmentation accepted in the Machine Learning 4 Health Workshop

Detection-aided liver lesion segmentation Here we present the implementation in TensorFlow of our work about liver lesion segmentation accepted in the

Image Processing Group - BarcelonaTECH - UPC 96 Oct 26, 2022
MWPToolkit is a PyTorch-based toolkit for Math Word Problem (MWP) solving.

MWPToolkit is a PyTorch-based toolkit for Math Word Problem (MWP) solving. It is a comprehensive framework for research purpose that integrates popular MWP benchmark datasets and typical deep learnin

119 Jan 04, 2023
A Self-Supervised Contrastive Learning Framework for Aspect Detection

AspDecSSCL A Self-Supervised Contrastive Learning Framework for Aspect Detection This repository is a pytorch implementation for the following AAAI'21

Tian Shi 30 Dec 28, 2022
KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control

KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control Tomas Jakab, Richard Tucker, Ameesh Makadia, Jiajun Wu, Noah Snavely, Angjoo Ka

Tomas Jakab 87 Nov 30, 2022