What are the differences between a pytorch and tensorflow tensor?

1

In the example below TF and PT operate on different channels, what is the reasoning behind this? is the order of the data different in TF than that of PT?

pt_tensor = torch.rand((5,80,256))
tf_tensor = tf.random.uniform((5,80, 256))

tf_conv = tf.keras.layers.Conv1D(128,3)
pt_conv = torch.nn.Conv1d(80, 128,3)

tf_conv(tf_tensor).shape # shape = TensorShape([5, 78, 128]) 

pt_conv(pt_tensor).shape # shape = torch.Size([5, 128, 254])

How are tensors stored? Are PT tensor stored as batch_size + [in_hight, in_width] and TF tensors stores as batch_size + [in_width, in_height]?

2

The difference is not in the way tf and pytorch store tensors it is the fact that their convolutional layers output different shapes. In tensorflow the conv1d layers have an output of (batch size, new steps, filters) while in pytorch the output of conv1d is shaped (batch size, filters, new steps). This is what makes the difference not the tensors themselves.