Light--

谢谢分享！ 1. 你提供的这个工具，全部内容只有一个 .py 文件？ 2. 在这个文件里面，没有看到multiprocessing之类的多进程调用？请问是如何实现的多进程并发？ 3. 能提供一个最小的使用样例么（或者完整的实际使用样例），比如在mnist什么的上面使用Pytorch调一下参数。就是一个完整的样例，能够复现的。里面包括训练集、验证集的加载等等 4. 如果模型是分布式（Pytorch DDP）的，这种情况下怎么使用这个工具去调参？有什么不同吗？ 5. 提供了random search功能吗？怎么使用？

如题

the code cannot run on RTX2080TI

2

i dont know why, and i tried many combinations of ubuntu version+cuda and cudnn, all failed... i only have 2080TI ...

where are the original directories ...?

1

E.g. configs/toy_experiments

Baidu Yun files are broken, how to re-generate the files?

4

I download the tsn_feature files for **many times** from the link you provided: https://pan.baidu.com/s/19GI3_-uZbd_XynUO6g-8YQ (i also tried the google drive download link, but will be abruptly ended every time) but...

i ran the code with the downloaded dataset and model weights, but the results are far from the README stated: the hamming_loss=0.405 not 0.1395 total_correctly_predicted/400. = 0.02 not 0.54 also...

error: IndexError: invalid index to scalar variable.

2

$ python Run.py output: ``` Traceback (most recent call last): File "Run.py", line 201, in main() File "Run.py", line 137, in main detections = yolo.detect(yolo_img) File "code/3D-BoundingBox-master/yolo/yolo.py", line 34, in...

驱动精灵单文件版、360手机助手等等都试过了 华为畅玩4X移动版 TL00

cuda out of memory even batch_size = 2

1

hi, i modified the input size to receive 112x112 and fc layer, but always get out of memory after running.... The locations I modified in the code are as follows:...

csv_mean_100/v_t_D9MYkEPEo.csv' does not exist

8

``` $ python3.6 main.py --mode train train subset video numbers: 9649 validation subset video numbers: 4728 /home/user/.local/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:100: UserWarning: Detected call of `lr_scheduler.step()` before `optimizer.step()`. In PyTorch 1.1.0 and later, you...