MabinogiX
MabinogiX
I have some variable saved from crnn-pytorch, which runs on gpu and uses warp-ctc. Then I use those variables in my code, I can run it on cpu and the...
/root/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH/THMath.h: In function ‘TH_polevlf’: /root/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH/THMath.h:142:3: error: ‘for’ loop initial declarations are only allowed in C99 mode for (size_t i = 0; i
你好，我在用书中的方法使用 DataLoader 类时发现了一些问题： 1. 经过多次测试我发现，使用方法： ``` dataiter = iter(dataloader) batch_datas, batch_labesl = next(dataiter) ``` 生成的迭代器只能遍历一次数据，之后会自动生成异常 `StopIteration` 然后停止，这个最好能在文档中注明一下，以及希望能提供一个循环遍历数据的方法。 2. 我发现在执行命令： ``` dataiter = iter(dataloader) ``` 时，程序会在整个数据集上执行 dataset.\_\_getitem\_\_ 函数。例如数据库中有100个数据，则会对这100个数据依次执行\_\_getitem\_\_。不知道这样做的原因是为什么？如果我dataset中有10万个数据，那岂不是要对10万个数据都执行一遍？
### System information * Operating system: win10 * Compiler version: VS 2015 * CMake version: 3.10.1 * CMake arguments: * Relevant libraries/versions (e.g. CUDA): cuda 8.0 ### CMake summary output...
I am using matlab 2017a and matconvnet-1.0-beta20. When I execute `run_experiment`, after loading `imdb_video`, I encounter this problem: ``` loading imdb video... construct network Reference to non-existent field 'dilate'. Error...
Hi, I am trying to reproduce the siamfc net with pytorch. I have built the whole net, but I encounter some difficulty in building loss function. I always get a...
I have created a file in lua: ``` local z = torch.Tensor(3,4,5) torch.save('tmp.t7', z) ``` When I read it in python, I get nothing: ``` import torchfile tmp = torchfile.load('tmp.t7')...
I have run the example in Generating an Input File and I got this error. Traceback (most recent call last): File "D:/Jupyter-notebook/ASE/test.py", line 123, in parser.parse() File "D:\catmap\catmap\parsers\table_parser.py", line 60,...
zoom_rang=(0.1, 0.1) means that the ranges of new image's axes are 10 percent of old one, which is too 'close'. 