Skip to content
Snippets Groups Projects

Compare revisions

Changes are shown as if the source revision was being merged into the target revision. Learn more about comparing revisions.

Source

Select target project
No results found

Target

Select target project
  • Archana_Badagi/food-round2
  • eric_a_scuccimarra/food-round2
  • joel_joseph/food-round2
  • darthgera123/food-round2
  • reshmarameshbabu/food-round2
  • nikhil_rayaprolu/food-round2
6 results
Show changes
Commits on Source (140)
40 additional commits have been omitted to prevent performance issues.
Expand all Hide whitespace changes
Inline Side-by-side
Showing
with 1218 additions and 134 deletions
.gitattributes 0 → 100644
View file @ 49243848
*.pth filter=lfs diff=lfs merge=lfs -text
.github/CONTRIBUTING.md
View file @ 49243848
......@@ -29,7 +29,25 @@ We use the following tools for linting and formatting:
Style configurations of yapf and isort can be found in [.style.yapf](../.style.yapf) and [.isort.cfg](../.isort.cfg).
We use [pre-commit hook](https://pre-commit.com/) that checks and formats for `flake8`, `yapf`, `isort`, `trailing whitespaces`,
fixes `end-of-files`, sorts `requirments.txt` automatically on every commit.
The config for a pre-commit hook is stored in [.pre-commit-config](../.pre-commit-config.yaml).
After you clone the repository, you will need to install initialize pre-commit hook.
```
pip install -U pre-commit
```
From the repository folder
```
pre-commit install
```
After this on every commit check code linters and formatter will be enforced.
>Before you create a PR, make sure that your code lints and is formatted by yapf.
### C++ and CUDA
We follow the [Google C++ Style Guide](https://google.github.io/styleguide/cppguide.html).
\ No newline at end of file
We follow the [Google C++ Style Guide](https://google.github.io/styleguide/cppguide.html).
.github/ISSUE_TEMPLATE/config.yml 0 → 100644
View file @ 49243848
blank_issues_enabled: false
.github/ISSUE_TEMPLATE/error-report.md
View file @ 49243848
......@@ -25,13 +25,11 @@ A placeholder for the command.
3. What dataset did you use?
**Environment**
- OS: [e.g., Ubuntu 16.04.6]
- GCC [e.g., 5.4.0]
- PyTorch version [e.g., 1.1.0]
- How you installed PyTorch [e.g., pip, conda, source]
- GPU model [e.g., 1080Ti, V100]
- CUDA and CUDNN version
- [optional] Other information that may be related (such as `$PATH`, `$LD_LIBRARY_PATH`, `$PYTHONPATH`, etc.)
1. Please run `python tools/collect_env.py` to collect necessary environment infomation and paste it here.
2. You may add addition that may be helpful for locating the problem, such as
- How you installed PyTorch [e.g., pip, conda, source]
- Other environment variables that may be related (such as `$PATH`, `$LD_LIBRARY_PATH`, `$PYTHONPATH`, etc.)
**Error traceback**
If applicable, paste the error trackback here.
......
.gitignore
View file @ 49243848
......@@ -116,5 +116,3 @@ data
*.log.json
work_dirs/
# Pytorch
*.pth
.isort.cfg
View file @ 49243848
[isort]
line_length = 79
multi_line_output = 0
known_standard_library = setuptools
known_first_party = mmdet
known_third_party = mmcv,numpy,matplotlib,pycocotools,six,seaborn,terminaltables,torch,torchvision
known_third_party = Cython,asynctest,cv2,matplotlib,mmcv,numpy,pycocotools,robustness_eval,roi_align,roi_pool,seaborn,six,terminaltables,torch,torchvision
no_lines_before = STDLIB,LOCALFOLDER
default_section = THIRDPARTY
\ No newline at end of file
default_section = THIRDPARTY
.pre-commit-config.yaml 0 → 100644
View file @ 49243848
repos:
- repo: https://github.com/asottile/seed-isort-config
rev: v1.9.3
hooks:
- id: seed-isort-config
- repo: https://github.com/pre-commit/mirrors-isort
rev: v4.3.21
hooks:
- id: isort
- repo: https://github.com/pre-commit/mirrors-yapf
rev: v0.29.0
hooks:
- id: yapf
- repo: https://github.com/pre-commit/pre-commit-hooks
rev: v2.4.0
hooks:
- id: flake8
- id: trailing-whitespace
- id: check-yaml
- id: end-of-file-fixer
- id: requirements-txt-fixer
.travis.yml
View file @ 49243848
dist: xenial
dist: bionic # ubuntu 18.04
language: python
python:
......@@ -6,7 +6,8 @@ python:
- "3.6"
- "3.7"
env: CUDA=9.2.148-1 CUDA_SHORT=9.2 UBUNTU_VERSION=ubuntu1604
env: CUDA=10.1.105-1 CUDA_SHORT=10.1 UBUNTU_VERSION=ubuntu1804 FORCE_CUDA=1
cache: pip
# Ref to CUDA installation in Travis: https://github.com/jeremad/cuda-travis
before_install:
......@@ -23,17 +24,20 @@ before_install:
- PATH=${CUDA_HOME}/bin:${PATH}
install:
- pip install Cython
- pip install Pillow==6.2.2 # remove this line when torchvision>=0.5
- pip install Cython torch==1.2 torchvision==0.4.0 # TODO: fix CI for pytorch>1.2
- pip install "git+https://github.com/cocodataset/cocoapi.git#subdirectory=PythonAPI"
- pip install -r requirements.txt
- pip install -r tests/requirements.txt
script:
before_script:
- flake8 .
- isort -rc --check-only --diff mmdet/ tools/ tests/
- yapf -r -d --style .style.yapf mmdet/ tools/ tests/
- yapf -r -d --style .style.yapf mmdet/ tools/ tests/ configs/
script:
- python setup.py check -m -s
- python setup.py build_ext --inplace
- coverage run --source mmdet -m py.test tests -v --doctest-modules
- coverage run --source mmdet -m py.test -v --xdoctest-modules tests mmdet
after_success:
- coverage report
\ No newline at end of file
- coverage report
Dockerfile 0 → 100644
View file @ 49243848
ARG PYTORCH="1.1.0"
ARG CUDA="10.0"
ARG CUDNN="7.5"
FROM pytorch/pytorch:${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel
RUN apt-get update && apt-get install -y libglib2.0-0 libsm6 libxrender-dev libxext6 \
&& apt-get clean \
&& rm -rf /var/lib/apt/lists/*
ENV DEBIAN_FRONTEND=noninteractive
RUN apt-get update && apt-get install -y \
build-essential \
bzip2 \
cmake \
curl \
git \
g++ \
libboost-all-dev \
pkg-config \
rsync \
software-properties-common \
sudo \
tar \
timidity \
unzip \
wget \
locales \
zlib1g-dev \
python3-dev \
python3 \
python3-pip \
python3-tk \
libjpeg-dev \
libpng-dev
# Python3
RUN pip3 install pip --upgrade
RUN pip3 install utm cython aicrowd_api timeout_decorator \
numpy \
aicrowd-repo2docker \
pillow
RUN pip3 install git+https://github.com/AIcrowd/coco.git#subdirectory=PythonAPI
RUN conda install cython -y && conda clean --all
RUN git clone --branch v1.0rc1 https://github.com/open-mmlab/mmdetection.git /mmdetection
WORKDIR /mmdetection
RUN pip install --no-cache-dir -e .
RUN python3.6 -m pip install aicrowd_api aicrowd-repo2docker
# Unicode support:
RUN locale-gen en_US.UTF-8
ENV LANG en_US.UTF-8
ENV LANGUAGE en_US:en
ENV LC_ALL en_US.UTF-8
# Enables X11 sharing and creates user home directory
ENV USER_NAME aicrowd
ENV HOME_DIR /home/$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 *
README.md
View file @ 49243848
This diff is collapsed.
aicrowd.json 0 → 100644
View file @ 49243848
{
"challenge_id" : "aicrowd-food-recognition-challenge",
"grader_id": "aicrowd-food-recognition-challenge",
"authors" : ["nikhil13prs"],
"description" : "Food Recognition Challenge Submission",
"license" : "MIT",
"gpu": true
}
aicrowd_helpers.py 0 → 100644
View file @ 49243848
#!/usr/bin/env python
import aicrowd_api
import os
########################################################################
# Instatiate Event Notifier
########################################################################
aicrowd_events = aicrowd_api.events.AIcrowdEvents()
def execution_start():
########################################################################
# Register Evaluation Start event
########################################################################
aicrowd_events.register_event(
event_type=aicrowd_events.AICROWD_EVENT_INFO,
message="execution_started",
payload={ #Arbitrary Payload
"event_type": "food_recognition_challenge:execution_started"
}
)
def execution_progress(progress_payload):
image_ids = progress_payload["image_ids"]
########################################################################
# Register Evaluation Progress event
########################################################################
aicrowd_events.register_event(
event_type=aicrowd_events.AICROWD_EVENT_INFO,
message="execution_progress",
payload={ #Arbitrary Payload
"event_type": "food_recognition_challenge:execution_progress",
"image_ids" : image_ids
}
)
def execution_success(payload):
predictions_output_path = payload["predictions_output_path"]
########################################################################
# Register Evaluation Complete event
########################################################################
expected_output_path = os.getenv("AICROWD_PREDICTIONS_OUTPUT_PATH", False)
if expected_output_path != predictions_output_path:
raise Exception("Please write the output to the path specified in the environment variable : AICROWD_PREDICTIONS_OUTPUT_PATH instead of {}".format(predictions_output_path))
aicrowd_events.register_event(
event_type=aicrowd_events.AICROWD_EVENT_SUCCESS,
message="execution_success",
payload={ #Arbitrary Payload
"event_type": "food_recognition_challenge:execution_success",
"predictions_output_path" : predictions_output_path
},
blocking=True
)
def execution_error(error):
########################################################################
# Register Evaluation Complete event
########################################################################
aicrowd_events.register_event(
event_type=aicrowd_events.AICROWD_EVENT_ERROR,
message="execution_error",
payload={ #Arbitrary Payload
"event_type": "food_recognition_challenge:execution_error",
"error" : error
},
blocking=True
)
all_categories.json 0 → 100644
View file @ 49243848
[
{
"id": 2578,
"name": "water",
"name_readable": "Water",
"supercategory": "food"
},
{
"id": 2939,
"name": "pizza-margherita-baked",
"name_readable": "Pizza, Margherita, baked",
"supercategory": "food"
},
{
"id": 1085,
"name": "broccoli",
"name_readable": "Broccoli",
"supercategory": "food"
},
{
"id": 1040,
"name": "salad-leaf-salad-green",
"name_readable": "Salad, leaf / salad, green",
"supercategory": "food"
},
{
"id": 1070,
"name": "zucchini",
"name_readable": "Zucchini",
"supercategory": "food"
},
{
"id": 2022,
"name": "egg",
"name_readable": "Egg",
"supercategory": "food"
},
{
"id": 2053,
"name": "butter",
"name_readable": "Butter",
"supercategory": "food"
},
{
"id": 1566,
"name": "bread-white",
"name_readable": "Bread, white",
"supercategory": "food"
},
{
"id": 1151,
"name": "apple",
"name_readable": "Apple",
"supercategory": "food"
},
{
"id": 2131,
"name": "dark-chocolate",
"name_readable": "Dark chocolate",
"supercategory": "food"
},
{
"id": 2521,
"name": "white-coffee-with-caffeine",
"name_readable": "White coffee, with caffeine",
"supercategory": "food"
},
{
"id": 1068,
"name": "sweet-pepper",
"name_readable": "Sweet pepper",
"supercategory": "food"
},
{
"id": 1026,
"name": "mixed-salad-chopped-without-sauce",
"name_readable": "Mixed salad (chopped without sauce)",
"supercategory": "food"
},
{
"id": 2738,
"name": "tomato-sauce",
"name_readable": "Tomato sauce",
"supercategory": "food"
},
{
"id": 1565,
"name": "bread-wholemeal",
"name_readable": "Bread, wholemeal",
"supercategory": "food"
},
{
"id": 2512,
"name": "coffee-with-caffeine",
"name_readable": "Coffee, with caffeine",
"supercategory": "food"
},
{
"id": 1061,
"name": "cucumber",
"name_readable": "Cucumber",
"supercategory": "food"
},
{
"id": 1311,
"name": "cheese",
"name_readable": "Cheese",
"supercategory": "food"
},
{
"id": 1505,
"name": "pasta-spaghetti",
"name_readable": "Pasta, spaghetti",
"supercategory": "food"
},
{
"id": 1468,
"name": "rice",
"name_readable": "Rice",
"supercategory": "food"
},
{
"id": 1967,
"name": "salmon",
"name_readable": "Salmon",
"supercategory": "food"
},
{
"id": 1078,
"name": "carrot",
"name_readable": "Carrot",
"supercategory": "food"
},
{
"id": 1116,
"name": "onion",
"name_readable": "Onion",
"supercategory": "food"
},
{
"id": 1022,
"name": "mixed-vegetables",
"name_readable": "Mixed vegetables",
"supercategory": "food"
},
{
"id": 2504,
"name": "espresso-with-caffeine",
"name_readable": "Espresso, with caffeine",
"supercategory": "food"
},
{
"id": 1154,
"name": "banana",
"name_readable": "Banana",
"supercategory": "food"
},
{
"id": 1163,
"name": "strawberries",
"name_readable": "Strawberries",
"supercategory": "food"
},
{
"id": 2750,
"name": "mayonnaise",
"name_readable": "Mayonnaise",
"supercategory": "food"
},
{
"id": 1210,
"name": "almonds",
"name_readable": "Almonds",
"supercategory": "food"
},
{
"id": 2620,
"name": "wine-white",
"name_readable": "Wine, white",
"supercategory": "food"
},
{
"id": 1310,
"name": "hard-cheese",
"name_readable": "Hard cheese",
"supercategory": "food"
},
{
"id": 1893,
"name": "ham-raw",
"name_readable": "Ham, raw",
"supercategory": "food"
},
{
"id": 1069,
"name": "tomato",
"name_readable": "Tomato",
"supercategory": "food"
},
{
"id": 1058,
"name": "french-beans",
"name_readable": "French beans",
"supercategory": "food"
},
{
"id": 1180,
"name": "mandarine",
"name_readable": "Mandarine",
"supercategory": "food"
},
{
"id": 2618,
"name": "wine-red",
"name_readable": "Wine, red",
"supercategory": "food"
},
{
"id": 1010,
"name": "potatoes-steamed",
"name_readable": "Potatoes steamed",
"supercategory": "food"
},
{
"id": 1588,
"name": "croissant",
"name_readable": "Croissant",
"supercategory": "food"
},
{
"id": 1879,
"name": "salami",
"name_readable": "Salami",
"supercategory": "food"
},
{
"id": 3080,
"name": "boisson-au-glucose-50g",
"name_readable": "Boisson au glucose 50g",
"supercategory": "food"
},
{
"id": 2388,
"name": "biscuits",
"name_readable": "Biscuits",
"supercategory": "food"
},
{
"id": 1108,
"name": "corn",
"name_readable": "Corn",
"supercategory": "food"
},
{
"id": 1032,
"name": "leaf-spinach",
"name_readable": "Leaf spinach",
"supercategory": "food"
},
{
"id": 2099,
"name": "jam",
"name_readable": "Jam",
"supercategory": "food"
},
{
"id": 2530,
"name": "tea-green",
"name_readable": "Tea, green",
"supercategory": "food"
},
{
"id": 1013,
"name": "chips-french-fries",
"name_readable": "Chips, french fries",
"supercategory": "food"
},
{
"id": 1323,
"name": "parmesan",
"name_readable": "Parmesan",
"supercategory": "food"
},
{
"id": 2634,
"name": "beer",
"name_readable": "Beer",
"supercategory": "food"
},
{
"id": 1056,
"name": "avocado",
"name_readable": "Avocado",
"supercategory": "food"
},
{
"id": 1520,
"name": "bread-french-white-flour",
"name_readable": "Bread, French (white flour)",
"supercategory": "food"
},
{
"id": 1788,
"name": "chicken",
"name_readable": "Chicken",
"supercategory": "food"
},
{
"id": 1352,
"name": "soft-cheese",
"name_readable": "Soft cheese",
"supercategory": "food"
},
{
"id": 2498,
"name": "tea",
"name_readable": "Tea",
"supercategory": "food"
},
{
"id": 2711,
"name": "sauce-savoury",
"name_readable": "Sauce (savoury)",
"supercategory": "food"
},
{
"id": 2103,
"name": "honey",
"name_readable": "Honey",
"supercategory": "food"
},
{
"id": 1554,
"name": "bread-whole-wheat",
"name_readable": "Bread, whole wheat",
"supercategory": "food"
},
{
"id": 1556,
"name": "bread-sourdough",
"name_readable": "Bread, sourdough",
"supercategory": "food"
},
{
"id": 1307,
"name": "gruyere",
"name_readable": "Gruyère",
"supercategory": "food"
},
{
"id": 1060,
"name": "pickle",
"name_readable": "Pickle",
"supercategory": "food"
},
{
"id": 1220,
"name": "mixed-nuts",
"name_readable": "Mixed nuts",
"supercategory": "food"
},
{
"id": 2580,
"name": "water-mineral",
"name_readable": "Water, mineral",
"supercategory": "food"
}
]
build.sh 0 → 100644
View file @ 49243848
#!/bin/bash
docker build -t $IMAGE_NAME
\ No newline at end of file
configs/albu_example/mask_rcnn_r50_fpn_1x.py 0 → 100644
View file @ 49243848
# model settings
model = dict(
type='MaskRCNN',
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch'),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_scales=[8],
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[4, 8, 16, 32, 64],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='SharedFCBBoxHead',
num_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=81,
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=False,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
mask_head=dict(
type='FCNMaskHead',
num_convs=4,
in_channels=256,
conv_out_channels=256,
num_classes=81,
loss_mask=dict(
type='CrossEntropyLoss', use_mask=True, loss_weight=1.0)))
# model training and testing settings
train_cfg = dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=2000,
max_num=2000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False))
test_cfg = dict(
rpn=dict(
nms_across_levels=False,
nms_pre=1000,
nms_post=1000,
max_num=1000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100,
mask_thr_binary=0.5))
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
albu_train_transforms = [
dict(
type='ShiftScaleRotate',
shift_limit=0.0625,
scale_limit=0.0,
rotate_limit=0,
interpolation=1,
p=0.5),
dict(
type='RandomBrightnessContrast',
brightness_limit=[0.1, 0.3],
contrast_limit=[0.1, 0.3],
p=0.2),
dict(
type='OneOf',
transforms=[
dict(
type='RGBShift',
r_shift_limit=10,
g_shift_limit=10,
b_shift_limit=10,
p=1.0),
dict(
type='HueSaturationValue',
hue_shift_limit=20,
sat_shift_limit=30,
val_shift_limit=20,
p=1.0)
],
p=0.1),
dict(type='JpegCompression', quality_lower=85, quality_upper=95, p=0.2),
dict(type='ChannelShuffle', p=0.1),
dict(
type='OneOf',
transforms=[
dict(type='Blur', blur_limit=3, p=1.0),
dict(type='MedianBlur', blur_limit=3, p=1.0)
],
p=0.1),
]
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='Pad', size_divisor=32),
dict(
type='Albu',
transforms=albu_train_transforms,
bbox_params=dict(
type='BboxParams',
format='pascal_voc',
label_fields=['gt_labels'],
min_visibility=0.0,
filter_lost_elements=True),
keymap={
'img': 'image',
'gt_masks': 'masks',
'gt_bboxes': 'bboxes'
},
update_pad_shape=False,
skip_img_without_anno=True),
dict(type='Normalize', **img_norm_cfg),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks'],
meta_keys=('filename', 'ori_shape', 'img_shape', 'img_norm_cfg',
'pad_shape', 'scale_factor'))
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[8, 11])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
evaluation = dict(interval=1)
# runtime settings
total_epochs = 12
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/mask_rcnn_r50_fpn_1x'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/atss/README.md 0 → 100644
View file @ 49243848
# Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection
## Introduction
```
@article{zhang2019bridging,
title = {Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection},
author = {Zhang, Shifeng and Chi, Cheng and Yao, Yongqiang and Lei, Zhen and Li, Stan Z.},
journal = {arXiv preprint arXiv:1912.02424},
year = {2019}
}
```
## Results and Models
| Backbone | Style | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP | Download |
|:---------:|:-------:|:-------:|:--------:|:-------------------:|:--------------:|:------:|:--------:|
| R-50 | pytorch | 1x | 3.6 | 0.357 | 12.8 | 39.2 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/atss/atss_r50_fpn_1x_20200113-a7aa251e.pth)|
configs/atss/atss_r50_fpn_1x.py 0 → 100644
View file @ 49243848
# model settings
model = dict(
type='ATSS',
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch'),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
start_level=1,
add_extra_convs=True,
extra_convs_on_inputs=False,
num_outs=5),
bbox_head=dict(
type='ATSSHead',
num_classes=81,
in_channels=256,
stacked_convs=4,
feat_channels=256,
octave_base_scale=8,
scales_per_octave=1,
anchor_ratios=[1.0],
anchor_strides=[8, 16, 32, 64, 128],
target_means=[.0, .0, .0, .0],
target_stds=[0.1, 0.1, 0.2, 0.2],
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_bbox=dict(type='GIoULoss', loss_weight=2.0),
loss_centerness=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0)))
# training and testing settings
train_cfg = dict(
assigner=dict(type='ATSSAssigner', topk=9),
allowed_border=-1,
pos_weight=-1,
debug=False)
test_cfg = dict(
nms_pre=1000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.6),
max_per_img=100)
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[8, 11])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 12
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/atss_r50_fpn_1x'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/cascade_mask_rcnn_r101_fpn_1x.py
View file @ 49243848
......@@ -174,8 +174,7 @@ test_cfg = dict(
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100,
mask_thr_binary=0.5),
keep_all_stages=False)
mask_thr_binary=0.5))
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
......
configs/cascade_mask_rcnn_r50_caffe_c4_1x.py
View file @ 49243848
......@@ -176,8 +176,7 @@ test_cfg = dict(
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100,
mask_thr_binary=0.5),
keep_all_stages=False)
mask_thr_binary=0.5))
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
......
configs/cascade_mask_rcnn_r50_fpn_1x.py
View file @ 49243848
......@@ -174,8 +174,7 @@ test_cfg = dict(
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100,
mask_thr_binary=0.5),
keep_all_stages=False)
mask_thr_binary=0.5))
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
......