GeneralJing

AttributeError: 'tuple' object has no attribute 'ndimension'

3

lb.shape: (640, 1280) main() File "tools/train_aquvitae.py", line 85, in main student = Dist( File "/home/xxx/anaconda3/envs/tp/lib/python3.8/site-packages/aquvitae/dist.py", line 28, in dist return _torch_dist( File "/home/xxx/anaconda3/envs/tp/lib/python3.8/site-packages/aquvitae/dist.py", line 118, in _torch_dist loss = algo.teach_step(x,...

这个功能是针对模型的某一模块进行剪枝的吗？

2

我跑了下示例代码，发现模型大小没有变化，看了下代码，发现那个比例针对的是某一个模块，那如果要对整个网络进行剪枝是需要，每一个模块单独进行剪枝吗？不能整体进行剪枝吗？

模型是YOLO fastest的模型，转换完caffe模型后，使用detector.py进行测试的时候，报错KeyError: 'layer79-conv'，这个地方需要修改key吗

Recently, I have done some performance optimization work. i used zero copy memory in my work. but i met a strange phenomenon. I have a custom struct array, and i...

TypeError: 'NoneType' object is not iterable

2

/home/appuser/anaconda3/envs/centernet2/lib/python3.8/site-packages/torch/functional.py:568: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2228.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Traceback (most recent call...

运行报错

6

let positions = unsafeBitCast(positionsIn!.contents(), to: UnsafeMutablePointer.self) let _velocities = unsafeBitCast(velocities!.contents(), to: UnsafeMutablePointer.self) 这个是报错的位置，提示的错误信息如下： Thread 1: Fatal error: Unexpectedly found nil while unwrapping an Optional value 不太熟悉swift、metal，能告诉这个是什么问题吗？

IndexError: invalid index of a 0-dim tensor. Use `tensor.item()` in Python or `tensor.item<T>()` in C++ to convert a 0-dim tensor to a number

2

Traceback (most recent call last): File "main.py", line 152, in train(epoch) File "main.py", line 120, in train 100. * batch_idx / len(train_loader), loss.data[0])) IndexError: invalid index of a 0-dim tensor....

python main.py -sr --s 0.0001 进行稀疏训练的时候，应该是在训练的模型之后，额外再进行训练吧？不是从头进行训练吧这个地方可以解释一下吗？有点困惑