Jacobew

Value of the learned scale and bias vector?

1

Hi, did you check the value change of the learned scale and bias vector throughout the training process? I find the value of them change in the first few iterations...

Hi, I'm trying to reproduce the results of video-level-feature-based model (i.e., Logistic Regression, MoE), but cannot find specific hyper-parameter settings in the github repo. Do they share the same default...

Hi, will DareBlopy support VarLenFeature?

Any way to incorporate these methods in other tasks easily?

7

Hi, thanks for your excellent job! I wonder is there any way to easily incorporate this method into other multi-tasks learning pipeline? I'm still trying to understanding the formulas and...

Will you release dataset and corresponding evaluation scripts?

2

Hi, will you release dataset and corresponding evaluation scripts?

You exceeded your current quota, please check your plan and billing details.

8

### 前置确认 1. 网络能够访问openai接口 2. python 已安装：版本在 3.7 ~ 3.10 之间，依赖已安装 3. 在已有 issue 中未搜索到类似问题 4. [FAQS](https://github.com/zhayujie/chatgpt-on-wechat/wiki/FAQs) 中无类似问题 ### 问题描述 > 简要说明、截图、复现步骤等，也可以是需求或想法 config中已配置proxy端口7890端口，请问clash应该怎么设置？ 目前在这种设置下无法连接，提示You exceeded your current quota, please check...

Hi, @zyayoung I wonder why the classification scores are used to keep or discard queries in testing, but not used in training (only gt disappearance and iou are used in...

Hi, I'm trying to reproduce the results of the official video-level-feature-based model (i.e., Logistic Regression, MoE presented in Sec4.3), but cannot find specific hyper-parameter settings in the official github repo....

How to use in my own dataset?

4

Hi, how can I use DistributionBalancedLoss on my own dataset?

Hi, I've found a bug in function posterize(img, bits). See [https://github.com/poodarchu/learn_aug_for_object_detection.numpy/blob/535645b9b992fead98f7aafdf0d86d674edd0025/autoaugment_utils.py#L281](url). It should be corrected as follow: ```python def posterize(img, bits): if img.shape[0] == 0 or img.shape[1] == 0: return...