[Frontend][TFLite] Fix fully_connected converter when batch size is not 1

[trevor-m]

The fully_connected converter used the shapes from the TFLite model to reshape the data tensor. However, the TFLite model shapes do not reflect those provided by the data_shape parameter in from_tflite(). The TFLite model shape input_tensor.tensor.ShapeAsNumpy() will give a batch size of 1 because the TFLite model obviously doesn't know about the data_shape dict the user provided to the relay importer.

For this particular op, the reshape can always be set to (-1, n_units) without needing to calculate a batch size.

For inceptionv4, without this PR we would incorrectly compute a batch size of 1 adding this reshape from %515: (4, 1, 1, 1536) to %516: (1, 1536). This ultimately causes the model output to become (1, 1001) instead of (4, 1001)

  ..
  %515 = nn.avg_pool2d(%514, pool_size=[8, 8], padding=[0, 0, 0, 0], layout="NHWC") /* ty=Tensor[(4, 1, 1, 1536), float32] */;                                          
  %516 = reshape(%515, meta[relay.Constant][0] /* ty=Tensor[(2), int32] */ /* ty=Tensor[(2), int32] */, newshape=[1, 1536]) /* ty=Tensor[(1, 1536), float32] */;
  %517 = nn.dense(%516, %v_param_299, units=None) /* ty=Tensor[(1, 1001), float32] */;                                                                                  
  %518 = nn.bias_add(%517, %v_param_300) /* ty=Tensor[(1, 1001), float32] */;                        
  nn.softmax(%518, axis=1) /* ty=Tensor[(1, 1001), float32] */                                                                                                          
} 

Btw, should the reshape op have some validation to prevent reshapes where the numbers of elements don't match? (4, 1, 1, 1536) -> (1, 1536) shouldn't be valid.

[FrozenGene]

I think we could add some check in bool ReshapeRel function

[anijain2305]

LGTM. We should follow up with a check in ReshapeRel as you and Zhao suggested.

[FrozenGene]

@trevor-m @anijain2305 Thank you. This pr is merged now.