I’m working on an image segmentation task and trying to use a pre-trained Swin Transformer Large (Swin-L) encoder for the feature extraction backbone. The code runs perfectly on a CPU in Colab. However, when switching to a TPU, it throws the error shown below.

I’m working on an image segmentation task and trying to use a pre-trained Swin Transformer Large (Swin-L) encoder for the feature extraction backbone. The code runs perfectly on a CPU in Colab. However, when switching to a TPU, it throws the error shown below.

I’m working on an image segmentation task and trying to use a pre-trained Swin Transformer Large (Swin-L) encoder for the feature extraction backbone. The code runs perfectly on a CPU in Colab. However, when switching to a TPU, it throws the error shown below.

I’m working on an image segmentation task and trying to use a pre-trained Swin Transformer Large (Swin-L) encoder for the feature extraction backbone. The code runs perfectly on a CPU in Colab. However, when switching to a TPU, it throws the error shown below.

I’m working on an image segmentation task and trying to use a pre-trained Swin Transformer Large (Swin-L) encoder for the feature extraction backbone. The code runs perfectly on a CPU in Colab. However, when switching to a TPU, it throws the error shown below.

I’m working on an image segmentation task and trying to use a pre-trained Swin Transformer Large (Swin-L) encoder for the feature extraction backbone. The code runs perfectly on a CPU in Colab. However, when switching to a TPU, it throws the error shown below.

class BatchedDataset(tf.keras.utils.PyDataSet):