The Tensorflow, Keras implementation of U-net, V-net, U-net++, UNET 3+, Attention U-net, R2U-net, ResUnet-a, U^2-Net, TransUNET, and Swin-UNET with optional ImageNet-trained backbones.
I have a 6 class semantic segmentation problem. I am trying to use SwinUNet as follows
models.swin_unet_2d((512, 512, 3), filter_num_begin=64, n_labels=6, depth=4, stack_num_down=2, stack_num_up=2, patch_size=(2, 2), num_heads=[4, 8, 8, 8], window_size=[4, 2, 2, 2], num_mlp=512, output_activation='Softmax', shift_window=True, name='swin_unet')
But getting below error
ResourceExhaustedError: 2 root error(s) found.
(0) Resource exhausted: OOM when allocating tensor with shape[8,65536,64] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
[[node swin_unet_model/swin_transformer_block_15/name1_norm2/batchnorm/mul_2 (defined at /opt/conda/lib/python3.7/site-packages/keras_unet_collection/transformer_layers.py:623) ]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.
(1) Resource exhausted: OOM when allocating tensor with shape[8,65536,64] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
[[node swin_unet_model/swin_transformer_block_15/name1_norm2/batchnorm/mul_2 (defined at /opt/conda/lib/python3.7/site-packages/keras_unet_collection/transformer_layers.py:623) ]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.
I have a 6 class semantic segmentation problem. I am trying to use SwinUNet as follows
models.swin_unet_2d((512, 512, 3), filter_num_begin=64, n_labels=6, depth=4, stack_num_down=2, stack_num_up=2, patch_size=(2, 2), num_heads=[4, 8, 8, 8], window_size=[4, 2, 2, 2], num_mlp=512, output_activation='Softmax', shift_window=True, name='swin_unet')
But getting below error
ResourceExhaustedError: 2 root error(s) found. (0) Resource exhausted: OOM when allocating tensor with shape[8,65536,64] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc [[node swin_unet_model/swin_transformer_block_15/name1_norm2/batchnorm/mul_2 (defined at /opt/conda/lib/python3.7/site-packages/keras_unet_collection/transformer_layers.py:623) ]] Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.
(1) Resource exhausted: OOM when allocating tensor with shape[8,65536,64] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc [[node swin_unet_model/swin_transformer_block_15/name1_norm2/batchnorm/mul_2 (defined at /opt/conda/lib/python3.7/site-packages/keras_unet_collection/transformer_layers.py:623) ]] Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.
0 successful operations. 0 derived errors ignored. [Op:__inference_train_function_152577]
Function call stack: train_function -> train_function ` Please help.