RuntimeError: CUDA out of memory. Tried to allocate 1.32 GiB (GPU 0; 7.92 GiB total capacity; 5.68 GiB already allocated; 1.22 GiB free; 192.30 MiB cached)

doc-analysis / TableBank

TableBank: A Benchmark Dataset for Table Detection and Recognition

Apache License 2.0

987 stars 139 forks source link

RuntimeError: CUDA out of memory. Tried to allocate 1.32 GiB (GPU 0; 7.92 GiB total capacity; 5.68 GiB already allocated; 1.22 GiB free; 192.30 MiB cached) #15

Open xuyuhui666 opened 4 years ago

xuyuhui666 commented 4 years ago

My commands : python train.py -model_type img -data data/demo -save_model demo-model -gpu_ranks 0 -batch_size 4 -learning_rate 0.1 -word_vec_size 80 -encoder_type brnn -image_channel_size 3

My GPU breaks while running to the 10000 steps of 100000

My batch_size sets 4 ,as 20 defined can not run

liminghao1630 commented 4 years ago

What size is your GPU memory? Try to use a smaller batch size.