LovPe
LovPe
this my caused by writing a tfrecord example when the instance number is 0, try to escape that kind of image when writing tfRecord
@Sharathnasa  ------------------------------------------------------------------------------------------ the code in red mark is the instance number, you can go into it to see the detail. i think the new version tensorflow(1.2+) will do some...
@Sharathnasa i did not use tensorflow1.1 but you can try it
@WKChung1028 **in my implementation: tf_rcnn->lib->datasets->convert_coco.py ,line 226** **but i rewrite the code so i'm not sure the are match!**
something like that add`if get_boxes.shape[0]>0` before implement **_to_tfexample_coco_raw()** function
@WKChung1028 1/make sure your tfrecord file was generated from new code 2/ i use python 3.5 with tf1.3
1/yes 2/i think is all right
@LiuPearl1 i use python3.6 and tf1.2 when solving this problem, and currently i have already give up to use this project and work on the original implementation on caffe2. i...