TOLL97
TOLL97
Hello there. What is the numpy version of the study? My computer always prompts that numpy（ numpy-1.18.1） is missing various libraries. such as: `Traceback (most recent call last): File "D:/a_zhy/object_detection/simple-faster-rcnn-pytorch-master/train.py",...
In the paper [D4RL](https://arxiv.org/pdf/2004.07219.pdf), there are many figures (e.g., Figure 4 and Figure 5) about the trajectories visited in the Maze2D domain. These figures are useful for discussion and research,...
模型成功使用tools/train.py训练， 但是运行tools/eval.py报错。 运行代码： ``` ‘%cd ~ %cd PaddleDetection/ !export CUDA_VISIBLE_DEVICES=0 !python -u tools/eval.py -c configs/yolov3_darknet_voc.yml \ -o weights=output/yolov3_darknet_voc/model_final/model_final \’ ``` 出错信息如下： ``` /home/aistudio /home/aistudio/PaddleDetection 2020-03-17 19:17:51,257-INFO: 555 samples in file...
可否把yml文件里面模型的超参数的设计原则，设计方案阐述一下（可以使用yolov3或faster r-cnn建立一个demo，详细说明各个参数的**作用，取值范围，实际取值对模型的影响**等等）。
Hello: We want to collect more data based on this dataset. Can you elaborate on the role of each file in the training and validation files and the tutorial on...
Hello: Very outstanding work! Can you provide a tutorial on fine-tuning based on the Open-Sora-Plan v1.0.0 model? Thank you so much!
Hello: When training on several GPUs, it seems that one model will generate multiple model log paths. `booster` doesn't support generating only one model log now?
Hello: I set up some extra layers and split the network layers into two sets with different learning rates. But something went wrong when saving the model. ` booster.save_optimizer(optimizer, os.path.join(save_dir,...
Hello. Medium uses 1M samples from a policy trained to approximately 1/3 the performance of the expert. Medium-Replay uses the replay buffer of a policy trained up to the performance...
Hello. The FTG outputs foot position targets for each leg. The output of FTG is a three-dimensional vector. However, the definition of FTG is just a one-dimensional vector with respect...