Skip to content

S
seminar-breakout
Commit 26321ae5 authored by Yuxin Wu's avatar Yuxin Wu
Browse files
Options

update travis

parent d3f11e3f
Show whitespace changes
Inline Side-by-side
Showing with 26 additions and 27 deletions
.travis.yml
View file @ 26321ae5
......@@ -22,28 +22,29 @@ matrix:
python: 2.7
env: TF_VERSION=1.3.0 TF_TYPE=release
- os: linux
python: 3.5
python: 3.6
env: TF_VERSION=1.3.0 TF_TYPE=release
- os: linux
python: 2.7
env: TF_VERSION=1.9.0 TF_TYPE=release
env: TF_VERSION=1.10.0 TF_TYPE=release
- os: linux
python: 3.5
env: TF_VERSION=1.9.0 TF_TYPE=release PYPI=true
python: 3.6
env: TF_VERSION=1.10.0 TF_TYPE=release PYPI=true
- os: linux
python: 2.7
env: TF_TYPE=nightly
- os: linux
python: 3.5
python: 3.6
env: TF_TYPE=nightly
allow_failures:
- env: TF_TYPE=nightly
install:
- pip install -U pip # the pip version on travis is too old
- pip install flake8 scikit-image opencv-python lmdb h5py pyarrow msgpack
- pip install flake8 scikit-image opencv-python lmdb h5py msgpack
- pip install .
# check that dataflow can be imported alone
- python -c "import pyarrow"
- python -c "import tensorpack.dataflow"
- ./tests/install-tensorflow.sh
......@@ -58,7 +59,7 @@ before_script:
script:
- flake8 .
- if [[ $TRAVIS_PYTHON_VERSION == '3.5' ]]; then cd examples && flake8 .; fi # some examples are py3 only
- if [[ $TRAVIS_PYTHON_VERSION == '3.6' ]]; then cd examples && flake8 .; fi # some examples are py3 only
- mkdir -p $HOME/tensorpack_data
- export TENSORPACK_DATASET=$HOME/tensorpack_data
- $TRAVIS_BUILD_DIR/tests/run-tests.sh
......@@ -90,7 +91,7 @@ deploy:
tags: true
branch: master
repo: tensorpack/tensorpack
python: "3.5"
python: "3.6"
condition: "$PYPI = true"
- provider: pypi
......@@ -103,5 +104,5 @@ deploy:
on:
branch: test-travis
repo: tensorpack/tensorpack
python: "3.5"
python: "3.6"
condition: "$PYPI = true"
examples/FasterRCNN/README.md
View file @ 26321ae5
......@@ -73,15 +73,15 @@ MaskRCNN results contain both box and mask mAP.
| Backbone | mAP<br/>(box;mask) | Detectron mAP <sup>[1](#ft1)</sup><br/> (box;mask) | Time on 8 V100s | Configurations <br/> (click to expand) |
| - | - | - | - | - |
| R50-C4 | 33.8 | | 18h | <details><summary>super quick</summary>`MODE_MASK=False FRCNN.BATCH_PER_IM=64`<br/>`PREPROC.SHORT_EDGE_SIZE=600 PREPROC.MAX_SIZE=1024`<br/>`TRAIN.LR_SCHEDULE=[150000,230000,280000]` </details> |
| R50-C4 | 37.1 | 36.5 | 44h | <details><summary>standard</summary>`MODE_MASK=False` </details> |
| R50-FPN | 37.5 | 37.9 | 30h | <details><summary>standard</summary>`MODE_MASK=False MODE_FPN=True` </details> |
| R50-C4 | 38.5;33.7 [:arrow_down:](http://models.tensorpack.com/FasterRCNN/COCO-R50C4-MaskRCNN-Standard.npz) | 37.8;32.8 | 49h | <details><summary>standard</summary>`MODE_MASK=True` </details> |
| R50-FPN | 38.8;35.4 [:arrow_down:](http://models.tensorpack.com/FasterRCNN/COCO-R50FPN-MaskRCNN-Standard.npz) | 38.6;34.5 | 32h | <details><summary>standard</summary>`MODE_MASK=True MODE_FPN=True` </details> |
| R50-FPN | 39.8;35.5 | 39.5;34.4<sup>[2](#ft2)</sup> | 34h | <details><summary>standard+ConvGNHead</summary>`MODE_MASK=True MODE_FPN=True`<br/>`FPN.FRCNN_HEAD_FUNC=fastrcnn_4conv1fc_gn_head` </details> |
| R50-FPN | 40.3;36.4 [:arrow_down:](http://models.tensorpack.com/FasterRCNN/COCO-R50FPN-MaskRCNN-StandardGN.npz) | 40.3;35.7 | 44h | <details><summary>standard+GN</summary>`MODE_MASK=True MODE_FPN=True`<br/>`FPN.NORM=GN BACKBONE.NORM=GN`<br/>`FPN.FRCNN_HEAD_FUNC=fastrcnn_4conv1fc_gn_head`<br/>`FPN.MRCNN_HEAD_FUNC=maskrcnn_up4conv_gn_head` |
| R101-C4 | 41.7;35.5 [:arrow_down:](http://models.tensorpack.com/FasterRCNN/COCO-R101C4-MaskRCNN-Standard.npz) | | 63h | <details><summary>standard</summary>`MODE_MASK=True `<br/>`BACKBONE.RESNET_NUM_BLOCK=[3,4,23,3]` </details> |
| R101-FPN | 40.7;36.9 [:arrow_down:](http://models.tensorpack.com/FasterRCNN/COCO-R101FPN-MaskRCNN-Standard.npz) | 40.9;36.4 | 40h | <details><summary>standard</summary>`MODE_MASK=True MODE_FPN=True`<br/>`BACKBONE.RESNET_NUM_BLOCK=[3,4,23,3]` </details> |
| R50-C4 | 33.1 | | 18h | <details><summary>super quick</summary>`MODE_MASK=False FRCNN.BATCH_PER_IM=64`<br/>`PREPROC.SHORT_EDGE_SIZE=600 PREPROC.MAX_SIZE=1024`<br/>`TRAIN.LR_SCHEDULE=[150000,230000,280000]` </details> |
| R50-C4 | 36.6 | 36.5 | 44h | <details><summary>standard</summary>`MODE_MASK=False` </details> |
| R50-FPN | 37.4 | 37.9 | 30h | <details><summary>standard</summary>`MODE_MASK=False MODE_FPN=True` </details> |
| R50-C4 | 37.8;33.1 [:arrow_down:](http://models.tensorpack.com/FasterRCNN/COCO-R50C4-MaskRCNN-Standard.npz) | 37.8;32.8 | 49h | <details><summary>standard</summary>`MODE_MASK=True` </details> |
| R50-FPN | 38.2;34.9 [:arrow_down:](http://models.tensorpack.com/FasterRCNN/COCO-R50FPN-MaskRCNN-Standard.npz) | 38.6;34.5 | 32h | <details><summary>standard</summary>`MODE_MASK=True MODE_FPN=True` </details> |
| R50-FPN | 39.5;35.2 | 39.5;34.4<sup>[2](#ft2)</sup> | 34h | <details><summary>standard+ConvGNHead</summary>`MODE_MASK=True MODE_FPN=True`<br/>`FPN.FRCNN_HEAD_FUNC=fastrcnn_4conv1fc_gn_head` </details> |
| R50-FPN | 40.0;36.1 [:arrow_down:](http://models.tensorpack.com/FasterRCNN/COCO-R50FPN-MaskRCNN-StandardGN.npz) | 40.3;35.7 | 44h | <details><summary>standard+GN</summary>`MODE_MASK=True MODE_FPN=True`<br/>`FPN.NORM=GN BACKBONE.NORM=GN`<br/>`FPN.FRCNN_HEAD_FUNC=fastrcnn_4conv1fc_gn_head`<br/>`FPN.MRCNN_HEAD_FUNC=maskrcnn_up4conv_gn_head` |
| R101-C4 | 40.8;35.1 [:arrow_down:](http://models.tensorpack.com/FasterRCNN/COCO-R101C4-MaskRCNN-Standard.npz) | | 63h | <details><summary>standard</summary>`MODE_MASK=True `<br/>`BACKBONE.RESNET_NUM_BLOCK=[3,4,23,3]` </details> |
| R101-FPN | 40.4;36.6 [:arrow_down:](http://models.tensorpack.com/FasterRCNN/COCO-R101FPN-MaskRCNN-Standard.npz) | 40.9;36.4 | 40h | <details><summary>standard</summary>`MODE_MASK=True MODE_FPN=True`<br/>`BACKBONE.RESNET_NUM_BLOCK=[3,4,23,3]` </details> |
<a id="ft1">1</a>: Here we comapre models that have identical training & inference cost between the two implementation. However their numbers are different due to many small implementation details.
......
examples/FasterRCNN/config.py
View file @ 26321ae5
......@@ -157,15 +157,16 @@ _C.FPN.FRCNN_HEAD_FUNC = 'fastrcnn_2fc_head'
# choices: fastrcnn_2fc_head, fastrcnn_4conv1fc_{,gn_}head
_C.FPN.FRCNN_CONV_HEAD_DIM = 256
_C.FPN.FRCNN_FC_HEAD_DIM = 1024
_C.FPN.MRCNN_HEAD_FUNC = 'maskrcnn_up4conv_head'
# choices: maskrcnn_up4conv_{,gn_}head
_C.FPN.MRCNN_HEAD_FUNC = 'maskrcnn_up4conv_head' # choices: maskrcnn_up4conv_{,gn_}head
# Mask-RCNN
_C.MRCNN.HEAD_DIM = 256
# testing -----------------------
_C.TEST.FRCNN_NMS_THRESH = 0.5
_C.TEST.RESULT_SCORE_THRESH = 1e-4
# Smaller threshold value gives significantly better mAP. But we use 0.05 for consistency with Detectron.
_C.TEST.RESULT_SCORE_THRESH = 0.05
_C.TEST.RESULT_SCORE_THRESH_VIS = 0.3 # only visualize confident results
_C.TEST.RESULTS_PER_IM = 100
......
tensorpack/input_source/input_source.py
View file @ 26321ae5
......@@ -21,7 +21,7 @@ from ..tfutils.tower import get_current_tower_context
from ..tfutils.dependency import dependency_of_fetches
from ..utils import logger
from ..utils.concurrency import ShareSessionThread
from ..utils.develop import log_deprecated, deprecated
from ..utils.develop import deprecated
from ..callbacks.base import Callback, CallbackFactory
from ..callbacks.graph import RunOp
......@@ -520,7 +520,7 @@ class StagingInput(FeedfreeInput):
logger.info("Pre-filling StagingArea ...")
for k in range(self.nr_stage):
self.stage_op.run()
logger.info("{} element{} put into StagingArea.".format(
logger.info("{} element{} put into StagingArea on each tower.".format(
self.nr_stage, "s were" if self.nr_stage > 1 else " was"))
def _before_run(self, ctx):
......@@ -534,21 +534,18 @@ class StagingInput(FeedfreeInput):
if dependency_of_fetches(fetches, self._check_dependency_op):
return self.fetches
def __init__(self, input, towers=None, nr_stage=1, device=None):
def __init__(self, input, nr_stage=1, device=None):
"""
Args:
input (FeedfreeInput):
nr_stage: number of elements to prefetch into each StagingArea, at the beginning.
Since enqueue and dequeue are synchronized, prefetching 1 element should be sufficient.
towers: deprecated
device (str or None): if not None, place the StagingArea on a specific device. e.g., '/cpu:0'.
Otherwise, they are placed under where `get_inputs_tensors`
gets called, which could be unspecified in case of simple trainers.
"""
assert isinstance(input, FeedfreeInput), input
self._input = input
if towers is not None:
log_deprecated("StagingInput(towers=)", "Devices are handled automatically.", "2018-03-31")
self._nr_stage = nr_stage
self._areas = []
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment