Merged commit includes the following changes:
196161788 by Zhichao Lu: Add eval_on_train_steps parameter. Since the number of samples in train dataset is usually different to the number of samples in the eval dataset. -- 196151742 by Zhichao Lu: Add an optional random sampling process for SSD meta arch and update mean stddev coder to use default std dev when corresponding tensor is not added to boxlist field. -- 196148940 by Zhichao Lu: Release ssdlite mobilenet v2 coco trained model. -- 196058528 by Zhichao Lu: Apply FPN feature map generation before we add additional layers on top of resnet feature extractor. -- 195818367 by Zhichao Lu: Add support for exporting detection keypoints. -- 195745420 by Zhichao Lu: Introduce include_metrics_per_category option to Object Detection eval_config. -- 195734733 by Zhichao Lu: Rename SSDLite config to be more explicit. -- 195717383 by Zhichao Lu: Add quantized training to object_detection. -- 195683542 by Zhichao Lu: Fix documentation for the interaction of fine_tune_checkpoint_type and load_all_detection_checkpoint_vars interaction. -- 195668233 by Zhichao Lu: Using batch size from params dictionary if present. -- 195570173 by Zhichao Lu: A few fixes to get new estimator API eval to match legacy detection eval binary by (1) plumbing `is_crowd` annotations through to COCO evaluator, (2) setting the `sloppy` flag in tf.contrib.data.parallel_interleave based on whether shuffling is enabled, and (3) saving the original image instead of the resized original image, which allows for small/medium/large mAP metrics to be properly computed. -- 195316756 by Zhichao Lu: Internal change -- PiperOrigin-RevId: 196161788
Showing
想要评论请 注册 或 登录