you359 / Keras-FasterRCNN

keras implementation of Faster R-CNN
MIT License
334 stars 216 forks source link

tensorflow.python.framework.errors_impl.InvalidArgumentError: slice index 14 of dimension 1 out of bounds. #59

Open saleed opened 4 years ago

saleed commented 4 years ago

when I changed the epoch to 10 and image epoch length to 1000 , i got this error:

2020-05-21 16:51:09.814678: W tensorflow/core/framework/op_kernel.cc:1502] OP_REQUIRES failed at strided_slice_op.cc:107 : Invalid argument: slice index 15 of dimension 1 out of bounds. 2020-05-21 16:51:09.814360: W tensorflow/core/framework/op_kernel.cc:1502] OP_REQUIRES failed at strided_slice_op.cc:107 : Invalid argument: slice index 7 of dimension 1 out of bounds. 2020-05-21 16:51:09.814156: W tensorflow/core/framework/op_kernel.cc:1502] OP_REQUIRES failed at strided_slice_op.cc:107 : Invalid argument: slice index 1 of dimension 1 out of bounds. 2020-05-21 16:51:09.814616: W tensorflow/core/framework/op_kernel.cc:1502] OP_REQUIRES failed at strided_slice_op.cc:107 : Invalid argument: slice index 20 of dimension 1 out of bounds. Traceback (most recent call last): File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1356, in _do_call return fn(*args) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1341, in _run_fn options, feed_dict, fetch_list, target_list, run_metadata) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1429, in _call_tf_sessionrun run_metadata) tensorflow.python.framework.errors_impl.InvalidArgumentError: slice index 14 of dimension 1 out of bounds. [[{{node roi_pooling_conv_1/strided_slice_71}}]] does anybody know what happens? thanks!

Tian-YS commented 4 years ago

Hi,did you deal with this problem?I have the same problem when i use my datasets.

and before this problem happen, it show me the mean_overlapping_bboxes == 0.

saleed commented 4 years ago

not sloved yet, I give up and use another project

Hi,did you deal with this problem?I have the same problem when i use my datasets.

and before this problem happen, it show me the mean_overlapping_bboxes == 0.

not sloved yet, I give up and use another project