| { |
| "dataset_param": { |
| "dataset_type": "dt2v", |
| "fps_max": 24, |
| "text_add_fps": true, |
| "basic_parameters": { |
| "data_path": "/your_data_folder/train_data.csv", |
| "data_folder": "/your_data_folder/", |
| "return_type": "dict" |
| }, |
| "preprocess_parameters": { |
| "video_processor_type": "OpensoraVideoProcessor", |
| "video_reader_type": "AvVideo", |
| "image_reader_type": "torchvision", |
| "train_pipeline": { |
| "video": [ |
| {"trans_type": "ToTensorVideo"}, |
| {"trans_type": "ResizeCrop", "param": {"size": "auto"}}, |
| {"trans_type": "norm_fun", "param": {"mean": [0.5, 0.5, 0.5], "std": [0.5, 0.5, 0.5], "inplace": true}} |
| ], |
| "image": [ |
| {"trans_type": "RandomHorizontalFlip"}, |
| {"trans_type": "ToTensor"}, |
| {"trans_type": "norm_fun", "param": {"mean": [0.5, 0.5, 0.5], "std": [0.5, 0.5, 0.5], "inplace": true}} |
| ] |
| } |
| }, |
| "use_text_processer": true, |
| "enable_text_preprocessing": false, |
| "tokenizer_config": [ |
| { |
| "autotokenizer_name": "T5Tokenizer", |
| "hub_backend": "hf", |
| "from_pretrained": "Open-Sora-v2/google/t5-v1_1-xxl", |
| "model_max_length": 512 |
| }, |
| { |
| "autotokenizer_name": "CLIPTokenizer", |
| "hub_backend": "hf", |
| "from_pretrained": "Open-Sora-v2/openai/clip-vit-large-patch14", |
| "model_max_length": 77 |
| } |
| ], |
| "use_feature_data": false, |
| "vid_img_fusion_by_splicing": false, |
| "use_img_num": 4, |
| "use_img_from_vid": true, |
| "video_mask_ratios": { |
| "random": 0.05, |
| "intepolate": 0.005, |
| "quarter_random": 0.005, |
| "quarter_head": 0.005, |
| "quarter_tail": 0.005, |
| "quarter_head_tail": 0.005, |
| "image_random": 0.025, |
| "image_head": 0.05, |
| "image_tail": 0.025, |
| "image_head_tail": 0.025 |
| } |
| }, |
| "dataloader_param": { |
| "dataloader_mode": "variable", |
| "auto_gen_bucket": true, |
| "shuffle": true, |
| "drop_last": true, |
| "pin_memory": true, |
| "bucket_config": { |
| "256px": {"1": [1.0, 1], "5": [1.0, 1], "9": [1.0, 1], "13": [1.0, 1], "17": [1.0, 1], "21": [1.0, 1], "25": [1.0, 1], "29": [1.0, 1], "33": [1.0, 1], "37": [1.0, 1], "41": [1.0, 1], "45": [1.0, 1], "49": [1.0, 1], "53": [1.0, 1], "57": [1.0, 1], "61": [1.0, 1], "65": [1.0, 1], "69": [1.0, 1], "73": [1.0, 1], "77": [1.0, 1], "81": [1.0, 1], "85": [1.0, 1], "89": [1.0, 1], "93": [1.0, 1], "97": [1.0, 1], "101": [1.0, 1], "105": [1.0, 1], "109": [1.0, 1], "113": [1.0, 1], "117": [1.0, 1], "121": [1.0, 1], "125": [1.0, 1], "129": [1.0, 1]}, |
| "768px": {"1": [0.5, 1]}, |
| "1024px": {"1": [0.5, 1]} |
| } |
| } |
| } |