Evaluate multiple checkpoints. #2643
Closed
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Can one of the admins verify this patch? |
unnecessary variable assignment in loop
* Adding logging utils * restore utils * delete old file * update inputs and docstrings * make /official a python module * remove /utils directory * Update readme for python path setting * Change readme texts
adding deeplab in readme.md file under models/research
Some python files under models/research, it is wrong to use "Rather then" instead of "Rather than" in comments.
We can directly get `batch_size` by `images.get_shape()[0]` in `inference` method, since maybe we will not use `cifar.inputs` method to build the input.
Fix comment typos under models/research
replace `FLAGS.batch_size` by `images.get_shape()[0]`
…flow#3576) * Remove cd and checkout * Updating comment
* Adding logging utils * restore utils * delete old file * update inputs and docstrings * Update import and fix typos * Fix formatting and comments * Update tests
* Internal change.
PiperOrigin-RevId: 187042423
* Internal change.
PiperOrigin-RevId: 187072380
* Opensource float and eight-bit fixed-point mobilenet_v1 training and eval scripts.
PiperOrigin-RevId: 187106140
* Initial check-in for Mobilenet V2
PiperOrigin-RevId: 187213595
* Allow configuring batch normalization decay and epsilon in MobileNet v1
PiperOrigin-RevId: 187425294
* Allow overriding NASNet model HParams.
This is a change to the API that will allow users to pass in their own configs
to the building functions, which should make these APIs much more customizable
for end-user cases.
This change removes the use_aux_head argument from the model construction
functions, which is no longer necessary given that the use_aux_head option is
configurable in the model config. For example, for the mobile ImageNet model,
the auxiliary head can be disabled using:
config = nasnet.mobile_imagenet_config()
config.set_hparam('use_aux_head', 0)
logits, endpoints = nasnet.build_nasnet_mobile(
inputs, num_classes, config=config)
PiperOrigin-RevId: 188617685
* Automated g4 rollback of changelist 188617685
PiperOrigin-RevId: 188619139
* Removes spurious comment
The current schema contains the entity information about model and train data metadata, as well as machine config. Future change will contain benchmark metric. The json schema can be used to create bigquery table. A sample table can be found in https://bigquery.cloud.google.com/table/tf-benchmark-dashboard:test_benchmark.benchmark_run.
Create groups of arg parsers and convert the official resnet model to the new arg parsers.
restore --version flag in resnet parser
1. Added Tensorflow version information. 2. Added environment variables. 3. Fix typo for hyperparameters. 4. Added cloud related information.
* Removing dependency on tf.test * New lines
Add data schema for the benchmark run in Bigquery.
Adrrei
requested review from
a team,
MarkDaoust,
OriolVinyals,
YknZhu,
joel-shor,
karmel,
lamberta,
lukaszkaiser,
markomernick,
nirum,
nmjohn,
ofirnachum,
peterjliu,
plakal,
protoget,
rsepassi,
sguada,
sherrym,
shlens,
tfboyd,
theraysmith,
vincentvanhoucke,
waterson and
zffchen
as code owners
|
Thanks for your pull request. It looks like this may be your first contribution to a Google open source project (if not, look below for help). Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). 📝 Please visit https://cla.developers.google.com/ to sign. Once you've signed (or fixed any issues), please reply here (e.g. What to do if you already signed the CLAIndividual signers
Corporate signers
|
|
Hi, thanks for taking the time to make a PR. But we can't submit this like this. It looks like you replayed master on top of your PR, instead of the other way around (?). Probably the easiest thing to do now to get a submittable PR is to copy your branch ( |
|
Sorry, this was unintended. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
51 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
It may occasionally not be possible to evaluate the various models from start (first checkpoint) to finish (last checkpoint) while simultaneously training the model (limited resources). I've added a new flag, 'eval_from_ckpt', which when set will evaluate all checkpoints from and including the specified one.
Example usage:
python C:/.../object_detection/eval.py \ --logtostderr \ --pipeline_config_path=C:/.../models/name.config \ --eval_dir=C:/.../testing \ --checkpoint_dir=C:/.../training \ --eval_from_ckpt=840In this case, all checkpoints from checkpoint 840 to 'latest_checkpoint' will be evaluated.