- 13 10月, 2018 1 次提交
-
-
由 shizhiw 提交于
* Use data_dir instead of flags.FLAGS.data_dir in data_preprocessing.py. * Use data_dir instead of flags.FLAGS.data_dir in data_preprocessing.py. * Replace multiprocess pool with popen_helper.get_pool() in data_preprocessing.
-
- 12 10月, 2018 9 次提交
-
-
由 shizhiw 提交于
* Use data_dir instead of flags.FLAGS.data_dir in data_preprocessing.py. * Use data_dir instead of flags.FLAGS.data_dir in data_preprocessing.py.
-
由 shizhiw 提交于
Allow data async generation to be run as a standalone job rather than a subprocess.
-
由 shizhiw 提交于
-
由 Shawn Wang 提交于
Add comments, exit async process after waiting for flagfile for too long and make directory for data_dir in case it does not exist.
-
由 Chris Shallue 提交于
Prevents TypeError:'dict_keys' object does not support indexing
-
由 Brendan Apfeld 提交于
-
由 Shawn Wang 提交于
-
由 Shawn Wang 提交于
-
由 Shawn Wang 提交于
-
- 11 10月, 2018 4 次提交
-
-
由 Vincent Vanhoucke 提交于
bug fix and python3 compatability
-
由 Jonathan juhl 提交于
fixed bug and introduced python3 compatability
-
由 Reed 提交于
-
由 Reed 提交于
* Add --use_synthetic_data option to NCF. * Add comment to _SYNTHETIC_BATCHES_PER_EPOCH * Fix test * Hopefully fix lint issue
-
- 10 10月, 2018 2 次提交
-
-
由 Shawn Wang 提交于
-
由 Shawn Wang 提交于
-
- 09 10月, 2018 1 次提交
-
-
由 Toby Boyd 提交于
Rollback AUTOTUNE.
-
- 06 10月, 2018 2 次提交
- 05 10月, 2018 8 次提交
-
-
由 Toby Boyd 提交于
-
由 aquariusjay 提交于
Open source `Searching for Efficient Multi-Scale Architectures for Dense Image Prediction`
-
由 huihui-personal 提交于
-
由 huihui-personal 提交于
Open source checkpoints for mobilenetv2_dm05_coco_voc_trainaug and mobilenetv2_dm05_coco_voc_trainval
-
由 Matthias Winkelmann 提交于
-
由 Taylor Robie 提交于
* improve default handling for eval_batch_size * return eval_batch_size default to None * fix syntax error
-
由 Taylor Robie 提交于
* Update resnet README with new checkpoints and SavedModels * add more detail on channels_first vs channels_last * fix typo * add disclaimer about checkpoints
-
由 Taylor Robie 提交于
* set strip_default_attrs=True for SavedModel exports * specify dtype in resnet export * another dtype fix * fix another dtype issue, and set --image_bytes_as_serving_input to default to False
-
- 04 10月, 2018 4 次提交
-
-
由 derekjchow 提交于
Update installation.md
-
由 Toby Boyd 提交于
link to non-deprecated imagenet preprocessing script
-
由 Toby Boyd 提交于
-
由 Kevin Clark 提交于
Fix cvt_text citation.
-
- 03 10月, 2018 4 次提交
-
-
由 Hui Hui 提交于
Open-sourcing the checkpoint so that users could reproduce our PASCAL VOC 2012 validation set result when training on train_aug set.
-
由 Taylor Robie 提交于
* move evaluation from numpy to tensorflow fix syntax error don't use sigmoid to convert logits. there is too much precision loss. WIP: add logit metrics continue refactor of NCF evaluation fix syntax error fix bugs in eval loss calculation fix eval loss reweighting remove numpy based metric calculations fix logging hooks fix sigmoid to softmax bug fix comment catch rare PIPE error and address some PR comments * fix metric test and address PR comments * delint and fix python2 * fix test and address PR comments * extend eval to TPUs
-
由 Kevin Clark 提交于
-
由 Reed 提交于
-
- 02 10月, 2018 5 次提交
-
-
由 Joel Shor 提交于
Project import generated by Copybara.
-
由 Asim Shankar 提交于
Enabling prediction in mnist_tpu.
-
由 Aman Gupta 提交于
Some changes specific to prediction. Removing traces of expected results, as this is just prediction.
-
由 derekjchow 提交于
Update CloudML job counts in running_pets.md
-
由 derekjchow 提交于
adding note only SSD models are supported
-