lizhen2017

A process in the process pool was terminated abruptly while the future was running or pending

3

As the title, I run the script: python ../tools/embedding_plugin/performance_profile/preprocess.py --src_csv_path=train.txt --dst_csv_path=train.out.txt --normalize_dense=0 --feature_cross=0 in the official docker，but it core dumped with A process in the process pool was terminated abruptly...

a: { 1: 1 } b: { index: ${a} } c: ${b} { index: null index: { 2: 2 } } { "index": { "2": 2 } } is expected,...

Why flownet return a flow multiplied by a constant 2.5?

1

As the title. And reason why the learning rate of the bias of the convolution of the flow_scale is zero. Thanks for your help!

How can I export a optimized wide and deep model?

2

In https://software.intel.com/content/www/us/en/develop/articles/accelerate-int8-inference-performance-for-recommender-systems-with-intel-deep-learning.html, graph optimization includes the following： """ Categorical columns are optimized by removing redundant and unnecessary OPs. The left portion of Figure 2 contains the unoptimized portion of the...

WS of Deformable Convolution.

3

Have you done any experiments on DFC? I guess that both offset convolution and deformable convolution can use WS. Looking forward to your reply.