Commit a43dff4d authored by nikhil_rayaprolu's avatar nikhil_rayaprolu
Browse files

Initial commit

parents
*.h5 filter=lfs diff=lfs merge=lfs -text
# Data files and directories common in repo root
datasets/
logs/
results/
temp/
test/
ngrok
*.ipynb
data/*
*.h5
# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class
# Distribution / packaging
.Python
env/
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
*.egg-info/
.installed.cfg
*.egg
# Installer logs
pip-log.txt
pip-delete-this-directory.txt
# VS Studio Code
.vscode
# PyCharm
.idea/
# Dropbox
.dropbox.attr
# Jupyter Notebook
.ipynb_checkpoints
# pyenv
.python-version
# dotenv
.env
# virtualenv
.venv
venv/
ENV/
FROM nvidia/cuda:10.0-cudnn7-runtime-ubuntu18.04
ENV DEBIAN_FRONTEND=noninteractive
RUN apt-get update && apt-get install -y \
build-essential \
bzip2 \
cmake \
curl \
git \
g++ \
libboost-all-dev \
pkg-config \
rsync \
software-properties-common \
sudo \
tar \
timidity \
unzip \
wget \
locales \
zlib1g-dev \
python3-dev \
python3 \
python3-pip \
python3-tk \
libjpeg-dev \
libpng-dev
# Python3
RUN pip3 install pip --upgrade
RUN pip3 install cython aicrowd_api timeout_decorator \
numpy \
matplotlib \
aicrowd-repo2docker \
pillow
RUN pip3 install git+https://github.com/AIcrowd/coco.git#subdirectory=PythonAPI
RUN pip3 install tensorflow-gpu
# Unicode support:
RUN locale-gen en_US.UTF-8
ENV LANG en_US.UTF-8
ENV LANGUAGE en_US:en
ENV LC_ALL en_US.UTF-8
# Enables X11 sharing and creates user home directory
ENV USER_NAME aicrowd
ENV HOME_DIR /home/$USER_NAME
#
# Replace HOST_UID/HOST_GUID with your user / group id (needed for X11)
ENV HOST_UID 1000
ENV HOST_GID 1000
RUN export uid=${HOST_UID} gid=${HOST_GID} && \
mkdir -p ${HOME_DIR} && \
echo "$USER_NAME:x:${uid}:${gid}:$USER_NAME,,,:$HOME_DIR:/bin/bash" >> /etc/passwd && \
echo "$USER_NAME:x:${uid}:" >> /etc/group && \
echo "$USER_NAME ALL=(ALL) NOPASSWD: ALL" > /etc/sudoers.d/$USER_NAME && \
chmod 0440 /etc/sudoers.d/$USER_NAME && \
chown ${uid}:${gid} -R ${HOME_DIR}
USER ${USER_NAME}
WORKDIR ${HOME_DIR}
COPY . .
RUN sudo chown ${HOST_UID}:${HOST_GID} -R *
RUN sudo chmod 775 -R *
\ No newline at end of file
Mask R-CNN
The MIT License (MIT)
Copyright (c) 2017 Matterport, Inc.
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in
all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
THE SOFTWARE.
include README.md
include LICENSE
include requirements.txt
\ No newline at end of file
![CrowdAI-Logo](https://github.com/crowdAI/crowdai/raw/master/app/assets/images/misc/crowdai-logo-smile.svg?sanitize=true)
# crowdAI Mapping Challenge : Baseline
This repository contains the details of implementation of the Baseline submission using [Mask RCNN](https://arxiv.org/abs/1703.06870) which obtains a score of `[AP(IoU=0.5)=0.697 ; AR(IoU=0.5)=0.479]` for the [crowdAI Mapping Challenge](https://www.crowdai.org/challenges/mapping-challenge).
# Installation
```
git clone https://github.com/crowdai/crowdai-mapping-challenge-mask-rcnn
cd crowdai-mapping-challenge-mask-rcnn
# Please ensure that you use python3.6
pip install -r requirements.txt
python setup.py install
```
# Notebooks
Please follow the instructions on the relevant notebooks for the training, prediction and submissions.
* [Training](Training.ipynb)
* [Prediction and Submission](Prediction-and-Submission.ipynb)
(_pre-trained weights for baseline submission included_)
# Results
![sample_predictions](images/predictions.png)
# Citation
```
@misc{crowdAIMappingChallengeBaseline2018,
author = {Mohanty, Sharada Prasanna},
title = {CrowdAI Mapping Challenge 2018 : Baseline with Mask RCNN},
year = {2018},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/crowdai/crowdai-mapping-challenge-mask-rcnn}},
commit = {bac1cf19adbc9d078122c6933da6f808c4ee590d}
}
```
# Acknowledgements
This repository heavily reuses code from the amazing [tensorflow Mask RCNN implementation](https://github.com/matterport/Mask_RCNN) by [@waleedka](https://github.com/waleedka/).
Many thanks to all the contributors of that project.
You are encouraged to checkout [https://github.com/matterport/Mask_RCNN](https://github.com/matterport/Mask_RCNN) for documentation on many other aspects of this code.
# Author
Sharada Mohanty [sharada.mohanty@epfl.ch](sharada.mohanty@epfl.ch)
{
"challenge_id" : "aicrowd-food-recognition-challenge",
"grader_id": "aicrowd-food-recognition-challenge",
"authors" : ["aicrowd-user"],
"description" : "Food Recognition Challenge Submission",
"license" : "MIT",
"gpu": true
}
\ No newline at end of file
This image diff could not be displayed because it is too large. You can view the blob instead.
"""
Mask R-CNN
Configurations and data loading code for MS COCO.
Copyright (c) 2017 Matterport, Inc.
Licensed under the MIT License (see LICENSE for details)
Written by Waleed Abdulla
------------------------------------------------------------
Usage: import the module (see Jupyter notebooks for examples), or run from
the command line as such:
# Train a new model starting from pre-trained COCO weights
python3 coco.py train --dataset=/path/to/coco/ --model=coco
# Train a new model starting from ImageNet weights
python3 coco.py train --dataset=/path/to/coco/ --model=imagenet
# Continue training a model that you had trained earlier
python3 coco.py train --dataset=/path/to/coco/ --model=/path/to/weights.h5
# Continue training the last model you trained
python3 coco.py train --dataset=/path/to/coco/ --model=last
# Run COCO evaluatoin on the last model you trained
python3 coco.py evaluate --dataset=/path/to/coco/ --model=last
"""
import os
import time
import numpy as np
# Download and install the Python COCO tools from https://github.com/waleedka/coco
#
# pip install git+https://github.com/waleedka/coco.git#subdirectory=PythonAPI
#
# That's a fork from the original https://github.com/pdollar/coco with a bug
# fix for Python 3.
# I submitted a pull request https://github.com/cocodataset/cocoapi/pull/50
# If the PR is merged then use the original repo.
# Note: Edit PythonAPI/Makefile and replace "python" with "python3".
from pycocotools.coco import COCO
from pycocotools.cocoeval import COCOeval
from pycocotools import mask as maskUtils
import zipfile
import urllib.request
import shutil
from mrcnn.config import Config
import mrcnn.utils as utils
import mrcnn.model as modellib
# Root directory of the project
ROOT_DIR = os.getcwd()
# Path to trained weights file
COCO_MODEL_PATH = os.path.join(ROOT_DIR, "mask_rcnn_coco.h5")
# Directory to save logs and model checkpoints, if not provided
# through the command line argument --logs
DEFAULT_LOGS_DIR = os.path.join(ROOT_DIR, "logs")
DEFAULT_DATASET_YEAR = "2014"
############################################################
# Configurations
############################################################
class CocoConfig(Config):
"""Configuration for training on MS COCO.
Derives from the base Config class and overrides values specific
to the COCO dataset.
"""
# Give the configuration a recognizable name
NAME = "coco"
# We use a GPU with 12GB memory, which can fit two images.
# Adjust down if you use a smaller GPU.
IMAGES_PER_GPU = 2
# Uncomment to train on 8 GPUs (default is 1)
# GPU_COUNT = 8
# Number of classes (including background)
NUM_CLASSES = 1 + 80 # COCO has 80 classes
############################################################
# Dataset
############################################################
class CocoDataset(utils.Dataset):
def load_coco(self, dataset_dir, subset, year=DEFAULT_DATASET_YEAR, class_ids=None,
class_map=None, return_coco=False, auto_download=False):
"""Load a subset of the COCO dataset.
dataset_dir: The root directory of the COCO dataset.
subset: What to load (train, val, minival, valminusminival)
year: What dataset year to load (2014, 2017) as a string, not an integer
class_ids: If provided, only loads images that have the given classes.
class_map: TODO: Not implemented yet. Supports maping classes from
different datasets to the same class ID.
return_coco: If True, returns the COCO object.
auto_download: Automatically download and unzip MS-COCO images and annotations
"""
if auto_download is True:
self.auto_download(dataset_dir, subset, year)
coco = COCO("{}/annotations/instances_{}{}.json".format(dataset_dir, subset, year))
if subset == "minival" or subset == "valminusminival":
subset = "val"
image_dir = "{}/{}{}".format(dataset_dir, subset, year)
# Load all classes or a subset?
if not class_ids:
# All classes
class_ids = sorted(coco.getCatIds())
# All images or a subset?
if class_ids:
image_ids = []
for id in class_ids:
image_ids.extend(list(coco.getImgIds(catIds=[id])))
# Remove duplicates
image_ids = list(set(image_ids))
else:
# All images
image_ids = list(coco.imgs.keys())
# Add classes
for i in class_ids:
self.add_class("coco", i, coco.loadCats(i)[0]["name"])
# Add images
for i in image_ids:
self.add_image(
"coco", image_id=i,
path=os.path.join(image_dir, coco.imgs[i]['file_name']),
width=coco.imgs[i]["width"],
height=coco.imgs[i]["height"],
annotations=coco.loadAnns(coco.getAnnIds(
imgIds=[i], catIds=class_ids, iscrowd=None)))
if return_coco:
return coco
def auto_download(self, dataDir, dataType, dataYear):
"""Download the COCO dataset/annotations if requested.
dataDir: The root directory of the COCO dataset.
dataType: What to load (train, val, minival, valminusminival)
dataYear: What dataset year to load (2014, 2017) as a string, not an integer
Note:
For 2014, use "train", "val", "minival", or "valminusminival"
For 2017, only "train" and "val" annotations are available
"""
# Setup paths and file names
if dataType == "minival" or dataType == "valminusminival":
imgDir = "{}/{}{}".format(dataDir, "val", dataYear)
imgZipFile = "{}/{}{}.zip".format(dataDir, "val", dataYear)
imgURL = "http://images.cocodataset.org/zips/{}{}.zip".format("val", dataYear)
else:
imgDir = "{}/{}{}".format(dataDir, dataType, dataYear)
imgZipFile = "{}/{}{}.zip".format(dataDir, dataType, dataYear)
imgURL = "http://images.cocodataset.org/zips/{}{}.zip".format(dataType, dataYear)
# print("Image paths:"); print(imgDir); print(imgZipFile); print(imgURL)
# Create main folder if it doesn't exist yet
if not os.path.exists(dataDir):
os.makedirs(dataDir)
# Download images if not available locally
if not os.path.exists(imgDir):
os.makedirs(imgDir)
print("Downloading images to " + imgZipFile + " ...")
with urllib.request.urlopen(imgURL) as resp, open(imgZipFile, 'wb') as out:
shutil.copyfileobj(resp, out)
print("... done downloading.")
print("Unzipping " + imgZipFile)
with zipfile.ZipFile(imgZipFile, "r") as zip_ref:
zip_ref.extractall(dataDir)
print("... done unzipping")
print("Will use images in " + imgDir)
# Setup annotations data paths
annDir = "{}/annotations".format(dataDir)
if dataType == "minival":
annZipFile = "{}/instances_minival2014.json.zip".format(dataDir)
annFile = "{}/instances_minival2014.json".format(annDir)
annURL = "https://dl.dropboxusercontent.com/s/o43o90bna78omob/instances_minival2014.json.zip?dl=0"
unZipDir = annDir
elif dataType == "valminusminival":
annZipFile = "{}/instances_valminusminival2014.json.zip".format(dataDir)
annFile = "{}/instances_valminusminival2014.json".format(annDir)
annURL = "https://dl.dropboxusercontent.com/s/s3tw5zcg7395368/instances_valminusminival2014.json.zip?dl=0"
unZipDir = annDir
else:
annZipFile = "{}/annotations_trainval{}.zip".format(dataDir, dataYear)
annFile = "{}/instances_{}{}.json".format(annDir, dataType, dataYear)
annURL = "http://images.cocodataset.org/annotations/annotations_trainval{}.zip".format(dataYear)
unZipDir = dataDir
# print("Annotations paths:"); print(annDir); print(annFile); print(annZipFile); print(annURL)
# Download annotations if not available locally
if not os.path.exists(annDir):
os.makedirs(annDir)
if not os.path.exists(annFile):
if not os.path.exists(annZipFile):
print("Downloading zipped annotations to " + annZipFile + " ...")
with urllib.request.urlopen(annURL) as resp, open(annZipFile, 'wb') as out:
shutil.copyfileobj(resp, out)
print("... done downloading.")
print("Unzipping " + annZipFile)
with zipfile.ZipFile(annZipFile, "r") as zip_ref:
zip_ref.extractall(unZipDir)
print("... done unzipping")
print("Will use annotations in " + annFile)
def load_mask(self, image_id):
"""Load instance masks for the given image.
Different datasets use different ways to store masks. This
function converts the different mask format to one format
in the form of a bitmap [height, width, instances].
Returns:
masks: A bool array of shape [height, width, instance count] with
one mask per instance.
class_ids: a 1D array of class IDs of the instance masks.
"""
# If not a COCO image, delegate to parent class.
image_info = self.image_info[image_id]
if image_info["source"] != "coco":
return super(CocoDataset, self).load_mask(image_id)
instance_masks = []
class_ids = []
annotations = self.image_info[image_id]["annotations"]
# Build mask of shape [height, width, instance_count] and list
# of class IDs that correspond to each channel of the mask.
for annotation in annotations:
class_id = self.map_source_class_id(
"coco.{}".format(annotation['category_id']))
if class_id:
m = self.annToMask(annotation, image_info["height"],
image_info["width"])
# Some objects are so small that they're less than 1 pixel area
# and end up rounded out. Skip those objects.
if m.max() < 1:
continue
# Is it a crowd? If so, use a negative class ID.
if annotation['iscrowd']:
# Use negative class ID for crowds
class_id *= -1
# For crowd masks, annToMask() sometimes returns a mask
# smaller than the given dimensions. If so, resize it.
if m.shape[0] != image_info["height"] or m.shape[1] != image_info["width"]:
m = np.ones([image_info["height"], image_info["width"]], dtype=bool)
instance_masks.append(m)
class_ids.append(class_id)
# Pack instance masks into an array
if class_ids:
mask = np.stack(instance_masks, axis=2)
class_ids = np.array(class_ids, dtype=np.int32)
return mask, class_ids
else:
# Call super class to return an empty mask
return super(CocoDataset, self).load_mask(image_id)
def image_reference(self, image_id):
"""Return a link to the image in the COCO Website."""
info = self.image_info[image_id]
if info["source"] == "coco":
return "http://cocodataset.org/#explore?id={}".format(info["id"])
else:
super(CocoDataset, self).image_reference(image_id)
# The following two functions are from pycocotools with a few changes.
def annToRLE(self, ann, height, width):
"""
Convert annotation which can be polygons, uncompressed RLE to RLE.
:return: binary mask (numpy 2D array)
"""
segm = ann['segmentation']
if isinstance(segm, list):
# polygon -- a single object might consist of multiple parts
# we merge all parts into one mask rle code
rles = maskUtils.frPyObjects(segm, height, width)
rle = maskUtils.merge(rles)
elif isinstance(segm['counts'], list):
# uncompressed RLE
rle = maskUtils.frPyObjects(segm, height, width)
else:
# rle
rle = ann['segmentation']
return rle
def annToMask(self, ann, height, width):
"""
Convert annotation which can be polygons, uncompressed RLE, or RLE to binary mask.
:return: binary mask (numpy 2D array)
"""
rle = self.annToRLE(ann, height, width)
m = maskUtils.decode(rle)
return m
############################################################
# COCO Evaluation
############################################################
def build_coco_results(dataset, image_ids, rois, class_ids, scores, masks):
"""Arrange resutls to match COCO specs in http://cocodataset.org/#format
"""
# If no results, return an empty list
if rois is None:
return []
results = []
for image_id in image_ids:
# Loop through detections
for i in range(rois.shape[0]):
class_id = class_ids[i]
score = scores[i]
bbox = np.around(rois[i], 1)
mask = masks[:, :, i]
result = {
"image_id": image_id,
"category_id": dataset.get_source_class_id(class_id, "coco"),
"bbox": [bbox[1], bbox[0], bbox[3] - bbox[1], bbox[2] - bbox[0]],
"score": score,
"segmentation": maskUtils.encode(np.asfortranarray(mask))
}
results.append(result)
return results
def evaluate_coco(model, dataset, coco, eval_type="bbox", limit=0, image_ids=None):
"""Runs official COCO evaluation.
dataset: A Dataset object with valiadtion data
eval_type: "bbox" or "segm" for bounding box or segmentation evaluation
limit: if not 0, it's the number of images to use for evaluation
"""
# Pick COCO images from the dataset
image_ids = image_ids or dataset.image_ids
# Limit to a subset
if limit:
image_ids = image_ids[:limit]
# Get corresponding COCO image IDs.
coco_image_ids = [dataset.image_info[id]["id"] for id in image_ids]
t_prediction = 0
t_start = time.time()
results = []
for i, image_id in enumerate(image_ids):
# Load image
image = dataset.load_image(image_id)
# Run detection
t = time.time()
r = model.detect([image], verbose=0)[0]
t_prediction += (time.time() - t)
# Convert results to COCO format
image_results = build_coco_results(dataset, coco_image_ids[i:i + 1],
r["rois"], r["class_ids"],
r["scores"], r["masks"])
results.extend(image_results)
# Load results. This modifies results with additional attributes.
coco_results = coco.loadRes(results)
# Evaluate
cocoEval = COCOeval(coco, coco_results, eval_type)
cocoEval.params.imgIds = coco_image_ids
cocoEval.evaluate()
cocoEval.accumulate()
cocoEval.summarize()
print("Prediction time: {}. Average {}/image".format(
t_prediction, t_prediction / len(image_ids)))
print("Total time: ", time.time() - t_start)
############################################################