Tiny yolo v3 Training Error

[tmsor7]

trafficstars

When I try to training this program using tiny yolo v3 (net_type=tiny), I got the under messages.

train.py

Instructions for updating: Use standard file APIs to check for files with this prefix. 0%| | 0/39782 [00:00<?, ?it/s]2020-08-26 16:00:13.648868: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudnn.so.7 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: 2 root error(s) found. (0) Invalid argument: Incompatible shapes: [2,18,18,3,4] vs. [2,36,36,3,4] [[{{node define_loss/bigger_box_loss/logistic_loss_2/mul}}]] [[define_loss/prob_loss/add/_69]] (1) Invalid argument: Incompatible shapes: [2,18,18,3,4] vs. [2,36,36,3,4] [[{{node define_loss/bigger_box_loss/logistic_loss_2/mul}}]] 0 successful operations. 0 derived errors ignored.

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/media/sl/train.py", line 261, in YoloTrain(net_type).train() File "/media/sl/train.py", line 201, in train self.trainable: True,}) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 950, in run run_metadata_ptr) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1173, in _run feed_dict_tensor, options, run_metadata) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1350, in _do_run run_metadata) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1370, in _do_call raise type(e)(node_def, op, message) tensorflow.python.framework.errors_impl.InvalidArgumentError: 2 root error(s) found. (0) Invalid argument: Incompatible shapes: [2,18,18,3,4] vs. [2,36,36,3,4] [[node define_loss/bigger_box_loss/logistic_loss_2/mul (defined at media/sl/core/yolov3_tiny.py:197) ]] [[define_loss/prob_loss/add/_69]] (1) Invalid argument: Incompatible shapes: [2,18,18,3,4] vs. [2,36,36,3,4] [[node define_loss/bigger_box_loss/logistic_loss_2/mul (defined at media/sl/core/yolov3_tiny.py:197) ]] 0 successful operations. 0 derived errors ignored.

Plz check my problems

[highhand31]

I've got the same error when using "tiny"!!

[avBuffer]

Hey all, Thanks, could you mind telling which net type selecting on backbone, such as darknet53 or mobilenet?