MCPcopy Create free account

hub / github.com/QwenLM/Qwen3-VL-Embedding / types & classes

Types & classes22 in github.com/QwenLM/Qwen3-VL-Embedding

↓ 2 callersClassMultimodalEvalDataCollator
src/evaluation/mmeb_v2/data/collator.py:7
↓ 2 callersClassQwen3VLReranker
src/models/qwen3_vl_reranker.py:74
↓ 2 callersClassRankingMetrics
src/evaluation/mmeb_v2/utils/eval_utils/metrics.py:11
↓ 1 callersClassQwen3VLEmbedder
src/models/qwen3_vl_embedding.py:160
↓ 1 callersClassQwen3VLForEmbeddingOutput
src/models/qwen3_vl_embedding.py:37
↓ 1 callersClassRandomHorizontalFlipVideo
Flip the video clip along the horizontal direction with a given probability Args: p (float): probability of the clip being flipped. D
src/evaluation/mmeb_v2/utils/vision_utils/video_transforms.py:628
↓ 1 callersClassTemporalRandomCrop
Temporally crop the given frame indices at a random location. Args: size (int): Desired length of frames will be seen in the model.
src/evaluation/mmeb_v2/utils/vision_utils/video_transforms.py:656
↓ 1 callersClassToTensorVideo
Convert tensor data type from uint8 to float, divide value by 255.0 and permute the dimensions of clip tensor
src/evaluation/mmeb_v2/utils/vision_utils/video_transforms.py:606
↓ 1 callersClassUCFCenterCropVideo
First scale to the specified size in equal proportion to the short edge, then center cropping
src/evaluation/mmeb_v2/utils/vision_utils/video_transforms.py:490
ClassAutoEvalPairDataset
src/evaluation/mmeb_v2/data/datasets/base_eval_dataset.py:31
ClassCenterCropResizeVideo
First use the short side for cropping length, center crop video, then resize to the specified size
src/evaluation/mmeb_v2/utils/vision_utils/video_transforms.py:452
ClassCenterCropVideo
src/evaluation/mmeb_v2/utils/vision_utils/video_transforms.py:551
ClassDataArguments
src/evaluation/mmeb_v2/arguments.py:21
ClassEvalArguments
src/evaluation/mmeb_v2/arguments.py:41
ClassKineticsRandomCropResizeVideo
Slide along the long edge, with the short edge as crop size. And resie to the desired size.
src/evaluation/mmeb_v2/utils/vision_utils/video_transforms.py:526
ClassMMEBEmbeddingModel
Simplified MMEBModel for Qwen3VL embeddings.
src/evaluation/mmeb_v2/models.py:10
ClassModelArguments
src/evaluation/mmeb_v2/arguments.py:7
ClassNormalizeVideo
Normalize the video clip by mean subtraction and division by standard deviation Args: mean (3-tuple): pixel RGB mean std (3-t
src/evaluation/mmeb_v2/utils/vision_utils/video_transforms.py:581
ClassQwen3VLForEmbedding
src/models/qwen3_vl_embedding.py:42
ClassRandomCropVideo
src/evaluation/mmeb_v2/utils/vision_utils/video_transforms.py:415
ClassRerankArguments
src/evaluation/mmeb_v2/arguments.py:45
ClassResizeCrop
src/evaluation/mmeb_v2/utils/vision_utils/video_transforms.py:400