Performance issues in java_predict_client/src/main/proto/tensorflow/tools/quantization/quantize_graph.py(P2)
DLPerf opened this issue · 0 comments
DLPerf commented
Hello,I found a performance issue in the definition of quantize_weight_eightbit ,
java_predict_client/src/main/proto/tensorflow/tools/quantization/quantize_graph.py,
sess = tf.Session() was repeatedly called in for n in quantize_weight_eightbit and was not closed.
I think it will increase the efficiency and avoid out of memory if you close this session after using it.
Here are two files to support this issue,support1 and support2
Looking forward to your reply. Btw, I am very glad to create a PR to fix it if you are too busy.