- 23 12月, 2019 1 次提交
-
-
由 Kaipeng Deng 提交于
* split yolov3 loss
-
- 19 12月, 2019 1 次提交
-
-
由 qingqing01 提交于
* Polish Reader to simplify preprocessing logic. # sample_transforms-> make batch -> batch_transforms in Reader. * Clean some code * Imporve yolov3_r50vd_dcn_obj365_pretrained_coco 41.4 to 41.8. * Update all configs.
-
- 23 8月, 2019 1 次提交
-
-
由 Kaipeng Deng 提交于
-
- 29 7月, 2019 1 次提交
-
-
由 Kaipeng Deng 提交于
* add voc_eval and yolo_darknet_voc * add yolov3_darknet_voc in MODEL_ZOO * fix default im_size * fix MODEL_ZOO note * fix is_bbox_normalized * extract map to map_utils.py * update yolov3_dorknet_voc mixup * add yolov3_r34_voc * add yolov3_mobilenet_v1_voc * fix drop empty in VAL mode * use cfg.num_classes * assert metric valid * enable difficulty can be None * add comment for bbox_eval * num_classes in retinanet
-
- 25 7月, 2019 1 次提交
-
-
由 Kaipeng Deng 提交于
* fix infer doc and config default * refine dataset exists * fix None proc
-
- 28 6月, 2019 2 次提交
-
-
由 Kaipeng Deng 提交于
* update darknet53 pretrain link * update weights path
-
由 qingqing01 提交于
* Rename object_detection to PaddleDetection * Small fix for doc
-