Skip to content

S
seminar-breakout
Commit 708e07b0 authored by Yuxin Wu's avatar Yuxin Wu
Browse files
Options

update docs

parent 443cb84d
Show whitespace changes
Inline Side-by-side
Showing with 29 additions and 28 deletions
docs/conf.py
View file @ 708e07b0
......@@ -380,6 +380,7 @@ _DEPRECATED_NAMES = set([
'prediction_incorrect', 'huber_loss',
# internal only
'SessionUpdate',
'apply_default_prefetch',
'average_grads',
'aggregate_grads',
......
docs/tutorial/inference.md
View file @ 708e07b0
......@@ -21,10 +21,14 @@ You can use this predicate to choose a different code path in inference mode.
## Inference After Training
Tensorpack is a training interface -- it doesn't care what happened after training.
It saves models to standard checkpoint format.
So you can build the graph for inference, load the checkpoint, and then use whatever deployment methods TensorFlow supports.
But you'll need to read TF docs and __do it on your own__.
Tensorpack is a training interface -- __it doesn't care what happened after training__.
You have everything needed for inference or model diagnosis after
training:
1. The trained weights: tensorpack saves them in standard TF checkpoint format.
2. The model: you've already written it yourself with TF symbolic functions.
Therefore, you can build the graph for inference, load the checkpoint, and then use whatever deployment methods TensorFlow supports.
And you'll need to read TF docs and __do it on your own__.
### Don't Use Training Metagraph for Inference
......
docs/tutorial/save-load.md
View file @ 708e07b0
......@@ -8,8 +8,11 @@ in TensorFlow checkpoint format.
A TF checkpoint typically includes a `.data-xxxxx` file and a `.index` file.
Both are necessary.
`tf.train.NewCheckpointReader` is the best tool to parse TensorFlow checkpoint.
We have two example scripts to demo its usage, but read [TF docs](https://www.tensorflow.org/api_docs/python/tf/train/NewCheckpointReader) for details.
`tf.train.NewCheckpointReader` is the offical tool to parse TensorFlow checkpoint.
Read [TF docs](https://www.tensorflow.org/api_docs/python/tf/train/NewCheckpointReader) for details.
Tensorpack also provides some small tools to work with checkpoints, see
[documentation](../modules/tfutils.html#tensorpack.tfutils.varmanip.load_chkpt_vars)
for details.
[scripts/ls-checkpoint.py](../scripts/ls-checkpoint.py)
demos how to print all variables and their shapes in a checkpoint.
......
examples/FasterRCNN/README.md
View file @ 708e07b0
......@@ -79,15 +79,15 @@ MaskRCNN results contain both box and mask mAP.
| - | - | - | - | - |
| 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 | 38.2;33.3 [: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 | 38.5;35.2 [: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 | 39.1;35.2 | 38.6;34.5 | 32h | <details><summary>better params</summary>`MODE_MASK=True MODE_FPN=True`<br/>`TEST.RESULT_SCORE_THRESH=1e-4`<br/>`FRCNN.BBOX_REG_WEIGHTS=[20,20,10,10]` </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;36.2 [: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 | 41.4;35.2 [: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> |
| R101-FPN | 41.1;36.6 [:arrow_down:](http://models.tensorpack.com/FasterRCNN/COCO-R101FPN-MaskRCNN-BetterParams.npz) | 40.9;36.4 | 40h | <details><summary>better params</summary>`MODE_MASK=True MODE_FPN=True`<br/>`BACKBONE.RESNET_NUM_BLOCK=[3,4,23,3]`<br/>`TEST.RESULT_SCORE_THRESH=1e-4`<br/>`FRCNN.BBOX_REG_WEIGHTS=[20,20,10,10]` </details> |
| R50-FPN | 37.4 | 37.9 | 29h | <details><summary>standard</summary>`MODE_MASK=False MODE_FPN=True` </details> |
| R50-C4 | 38.2;33.3 [:arrow_down:](http://models.tensorpack.com/FasterRCNN/COCO-R50C4-MaskRCNN-Standard.npz) | 37.8;32.8 | 49h | <details><summary>standard</summary>this is the default </details> |
| R50-FPN | 38.5;35.2 [:arrow_down:](http://models.tensorpack.com/FasterRCNN/COCO-R50FPN-MaskRCNN-Standard.npz) | 38.6;34.5 | 30h | <details><summary>standard</summary>`MODE_FPN=True` </details> |
| R50-FPN | 42.0;36.3 | | 41h | <details><summary>+Cascade</summary>`MODE_FPN=True FPN.CASCADE=True` </details> |
| R50-FPN | 39.5;35.2 | 39.5;34.4<sup>[2](#ft2)</sup> | 33h | <details><summary>+ConvGNHead</summary>`MODE_FPN=True`<br/>`FPN.FRCNN_HEAD_FUNC=fastrcnn_4conv1fc_gn_head` </details> |
| R50-FPN | 40.0;36.2 [:arrow_down:](http://models.tensorpack.com/FasterRCNN/COCO-R50FPN-MaskRCNN-StandardGN.npz) | 40.3;35.7 | 40h | <details><summary>+GN</summary>`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 | 41.4;35.2 [:arrow_down:](http://models.tensorpack.com/FasterRCNN/COCO-R101C4-MaskRCNN-Standard.npz) | | 60h | <details><summary>standard</summary>`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 | 38h | <details><summary>standard</summary>`MODE_FPN=True`<br/>`BACKBONE.RESNET_NUM_BLOCK=[3,4,23,3]` </details> |
| R101-FPN | 41.1;36.6 [:arrow_down:](http://models.tensorpack.com/FasterRCNN/COCO-R101FPN-MaskRCNN-BetterParams.npz) | 40.9;36.4 | 38h | <details><summary>better params</summary>`MODE_FPN=True`<br/>`BACKBONE.RESNET_NUM_BLOCK=[3,4,23,3]`<br/>`TEST.RESULT_SCORE_THRESH=1e-4`<br/>`FRCNN.BBOX_REG_WEIGHTS=[20,20,10,10]` </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.
......
tensorpack/tfutils/varmanip.py
View file @ 708e07b0
# -*- coding: utf-8 -*-
# File: varmanip.py
import six
import os
import pprint
import tensorflow as tf
import numpy as np
from ..utils.develop import deprecated
from ..utils import logger
from .common import get_op_tensor_name
......@@ -50,7 +48,7 @@ class SessionUpdate(object):
@staticmethod
def load_value_to_var(var, val, strict=False):
"""
Call `var.load(val)` with the default session.
Call `var.load(val)` with the default session, with some type checks.
Args:
var (tf.Variable):
......@@ -111,7 +109,7 @@ class SessionUpdate(object):
def dump_session_params(path):
"""
Dump value of all TRAINABLE + MODEL variables to a dict, and save as
npz format (loadable by :class:`DictRestore`).
npz format (loadable by :func:`sessinit.get_model_loader`).
Args:
path(str): the file name to save the parameters. Must ends with npz.
......@@ -203,11 +201,6 @@ def load_chkpt_vars(model_path):
return result
@deprecated("Renamed to 'load_chkpt_vars!'", "2018-04-20")
def dump_chkpt_vars(model_path):
return load_chkpt_vars(model_path)
def is_training_name(name):
"""
**Guess** if this variable is only used in training.
......
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