# coding=utf-8
# Copyright 2025 The HuggingFace Inc. team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Fast Image processor class for MobileNetV2."""

from typing import List, Optional, Tuple

from ...image_processing_utils_fast import BaseImageProcessorFast
from ...image_utils import IMAGENET_STANDARD_MEAN, IMAGENET_STANDARD_STD, PILImageResampling
from ...utils import auto_docstring, is_torch_available, is_torch_tensor


if is_torch_available():
    import torch


@auto_docstring
class MobileNetV2ImageProcessorFast(BaseImageProcessorFast):
    resample = PILImageResampling.BILINEAR
    image_mean = IMAGENET_STANDARD_MEAN
    image_std = IMAGENET_STANDARD_STD
    size = {"shortest_edge": 256}
    default_to_square = False
    crop_size = {"height": 224, "width": 224}
    do_resize = True
    do_center_crop = True
    do_rescale = True
    do_normalize = True
    do_convert_rgb = None

    def post_process_semantic_segmentation(self, outputs, target_sizes: Optional[List[Tuple]] = None):
        """
        Converts the output of [`MobileNetV2ForSemanticSegmentation`] into semantic segmentation maps. Only supports PyTorch.

        Args:
            outputs ([`MobileNetV2ForSemanticSegmentation`]):
                Raw outputs of the model.
            target_sizes (`List[Tuple]` of length `batch_size`, *optional*):
                List of tuples corresponding to the requested final size (height, width) of each prediction. If unset,
                predictions will not be resized.

        Returns:
            semantic_segmentation: `List[torch.Tensor]` of length `batch_size`, where each item is a semantic
            segmentation map of shape (height, width) corresponding to the target_sizes entry (if `target_sizes` is
            specified). Each entry of each `torch.Tensor` correspond to a semantic class id.
        """
        # TODO: add support for other frameworks
        logits = outputs.logits

        # Resize logits and compute semantic segmentation maps
        if target_sizes is not None:
            if len(logits) != len(target_sizes):
                raise ValueError(
                    "Make sure that you pass in as many target sizes as the batch dimension of the logits"
                )

            if is_torch_tensor(target_sizes):
                target_sizes = target_sizes.numpy()

            semantic_segmentation = []

            for idx in range(len(logits)):
                resized_logits = torch.nn.functional.interpolate(
                    logits[idx].unsqueeze(dim=0), size=target_sizes[idx], mode="bilinear", align_corners=False
                )
                semantic_map = resized_logits[0].argmax(dim=0)
                semantic_segmentation.append(semantic_map)
        else:
            semantic_segmentation = logits.argmax(dim=1)
            semantic_segmentation = [semantic_segmentation[i] for i in range(semantic_segmentation.shape[0])]

        return semantic_segmentation


__all__ = ["MobileNetV2ImageProcessorFast"]