I am using TensorRT in order to quantize a DNN for object detection called “Pixor”.
I am using Python3 + Tensorflow 1.12 + TensorRT 3.0.2
The quantization work fine for me. However, I want to generate and read the calibration table in order to understand if my calibration dataset is good enough or not.
I want to ask also if i can generate the histograms of activation as shown in these slides?
Thank you in advance,
Unfortunately, we have not made public the details of the calibration table. We are always listening to community feedback and please stay tuned for future announcements.
Hello. Thanks for your answer,
However, I found the following python code in NVIDIA tutorial to extract the TensorRT calibration table after the calibration is done:
for n in trt_graph.node:
if n.op == “TRTEngineOp”:
print(“Node: %s, %s” % (n.op, n.name.replace("/", “")))
with tf.gfile.GFile("%s.calib_table" % (n.name.replace("/", "”)), ‘wb’) as f:
This code generates a file for each node in the trt_graph. However, I can’t read it!
I get something like this:
Can you please explain how to read these files?