tf_to_trt_image_classification
tf_to_trt_image_classification copied to clipboard
Converting to frozen graph failed on Jetson TX2
When I run the scripts/models_to_frozen_graphs.py script, I got below error ion Jetson TX2. Any comment: ... 018-03-13 18:52:01.449359: I tensorflow/core/common_runtime/bfc_allocator.cc:684] Sum Total of in-use chunks: 152.63MiB 2018-03-13 18:52:01.449608: I tensorflow/core/common_runtime/bfc_allocator.cc:686] Stats: Limit: 374509568 InUse: 160042752 MaxInUse: 271571968 NumAllocs: 10753 MaxAllocSize: 107122688
2018-03-13 18:52:01.449952: W tensorflow/core/common_runtime/bfc_allocator.cc:277] __xxx__*************__________________________________________
Traceback (most recent call last):
File "scripts/models_to_frozen_graphs.py", line 63, in
We have encountered out-of-memory before on the TX2 when running the batch conversion script (scripts/models_to_frozen_graphs.py) immediately after performing the other installation steps.
Could you try restarting the Jetson TX2 and report back the results of running the above script?
I had the same problem and it disappeared after restarting Jetson TX2 as you suggested.