Changhun Lee

Thank you for your answer. The warmup option was the answer to question 1. Meanwhile, can I get an answer or hint for question 2? It's an error that is...

All logs and related necessary information are summarized in the following link: https://sweetsour.notion.site/Bolt-9eea4d1a73694203a64b26f21b4e8cb6 I've been debugging this issue a bit more and I'm guessing it's a MemoryReuseOptimizer related issue. [https://github.com/huawei-noah/bolt/blob/master/model_tools/include/OPOptimizers/MemoryReuseOptimizer.hpp](url)...

> 2. this is caused by bolt's onnx model converter, https://github.com/huawei-noah/bolt/blob/master/model_tools/src/onnx/onnx_adaptee.h, we map _C = A * B_ to Scale operator, we assume that Scale operator's weight is tensor B,...

hi, did you solve your problem? I am facing the same issue.

I have the same issue, haven't found a solution yet.

I think I just found a solution to this problem, seeing #174 I'm working on iteration 200 and it works well so far. I hope this helps :)

I used train2017 of COCO dataset, I'm not sure whether hard negative samples are contained. I guess all the images in train2017 have at least one annotation.

I only changed these in main.py: to solve memory issue from line 151 ```python ## If your machine cannot load all images into memory, you should use ## this one...

I changed utils.py and losses seem fine.  g_init result is below  train_50.png result is this  I think the training now goes well. I will upload the final...

I'm using tensorlayor 1.8.0 now. The current version is 1.10.1. I'm not sure if my change causes other well-worked people to not working.. Because my tensorlayer version is not the...