search

mlpc-ucsd / LETR

(CVPR 2021 Oral) LETR: Line Segment Detection Using Transformers without Edges
Apache License 2.0
204 stars 40 forks source link

Your session crashed after using all available RAM. #3

Open huynhbaobk opened 3 years ago

huynhbaobk commented 3 years ago

I got the problem when I tried to run inference the 'second time' with same image (the first time is good). outputs = model(inputs)[0] I run the demo_letr.ipynb on colab pro (25GB RAM). I tried use torch.cuda.empty_cache() gc.collect() # garbage collection but still got this error. Thank you in advance

yix081 commented 3 years ago

can you share your colab notebook here?

marcomiglionico94 commented 2 years ago

I am having the same problem

Saoussenl commented 2 years ago

I have the same problem while running on a setup with just a CPU.

RuntimeError: [enforce fail at ..\c10\core\CPUAllocator.cpp:79] data. DefaultCPUAllocator: not enough memory: you tried to allocate 1289507328 bytes.

I think it's because the network is fully connected.

Nevertheless, please consider to check your network and try to make it lighter because most ordinary pcs don't have the capabilities to run it.