| { | |
| "model_type": "unet", | |
| "model_config": { | |
| "encoder": { | |
| "type": "resnet18", | |
| "pretrained": true | |
| }, | |
| "decoder": { | |
| "type": "unet", | |
| "num_classes": 104 | |
| } | |
| } | |
| } | |
| "norm_cfg": { | |
| "type": "SyncBN", | |
| "requires_grad": true | |
| }, | |
| "model": { | |
| "type": "EncoderDecoder", | |
| "pretrained": "pretrained/swin_small_patch4_window7_224.pth", | |
| "backbone": { | |
| "type": "SwinTransformer", | |
| "embed_dim": 96, | |
| "depths": [2, 2, 18, 2], | |
| "num_heads": [3, 6, 12, 24], | |
| "window_size": 7, | |
| "mlp_ratio": 4.0, | |
| "qkv_bias": true, | |
| "qk_scale": null, | |
| "drop_rate": 0.0, | |
| "attn_drop_rate": 0.0, | |
| "drop_path_rate": 0.3, | |
| "ape": false, | |
| "patch_norm": true, | |
| "out_indices": [0, 1, 2, 3], | |
| "use_checkpoint": false | |
| }, | |
| "decode_head": { | |
| "type": "UPerHead", | |
| "in_channels": [96, 192, 384, 768], | |
| "in_index": [0, 1, 2, 3], | |
| "pool_scales": [1, 2, 3, 6], | |
| "channels": 512, | |
| "dropout_ratio": 0.1, | |
| "num_classes": 104, | |
| "norm_cfg": { | |
| "type": "SyncBN", | |
| "requires_grad": true | |
| }, | |
| "align_corners": false, | |
| "loss_decode": { | |
| "type": "CrossEntropyLoss", | |
| "use_sigmoid": false, | |
| "loss_weight": 1.0 | |
| } | |
| }, | |
| "auxiliary_head": { | |
| "type": "FCNHead", | |
| "in_channels": 384, | |
| "in_index": 2, | |
| "channels": 256, | |
| "num_convs": 1, | |
| "concat_input": false, | |
| "dropout_ratio": 0.1, | |
| "num_classes": 104, | |
| "norm_cfg": { | |
| "type": "SyncBN", | |
| "requires_grad": true | |
| }, | |
| "align_corners": false, | |
| "loss_decode": { | |
| "type": "CrossEntropyLoss", | |
| "use_sigmoid": false, | |
| "loss_weight": 0.4 | |
| } | |
| }, | |
| "train_cfg": {}, | |
| "test_cfg": { | |
| "mode": "whole" | |
| } | |
| }, | |
| "dataset_type": "CustomDataset", | |
| "data_root": "./data/FoodSeg103/Images/", | |
| "img_norm_cfg": { | |
| "mean": [123.675, 116.28, 103.53], | |
| "std": [58.395, 57.12, 57.375], | |
| "to_rgb": true | |
| }, | |
| "crop_size": [512, 1024], | |
| "train_pipeline": [ | |
| { | |
| "type": "LoadImageFromFile" | |
| }, | |
| { | |
| "type": "LoadAnnotations" | |
| }, | |
| { | |
| "type": "Resize", | |
| "img_scale": [2048, 1024], | |
| "ratio_range": [0.5, 2.0] | |
| }, | |
| { | |
| "type": "RandomCrop", | |
| "crop_size": [512, 1024], | |
| "cat_max_ratio": 0.75 | |
| }, | |
| { | |
| "type": "RandomFlip", | |
| "prob": 0.5 | |
| }, | |
| { | |
| "type": "PhotoMetricDistortion" | |
| }, | |
| { | |
| "type": "Normalize", | |
| "mean": [123.675, 116.28, 103.53], | |
| "std": [58.395, 57.12, 57.375], | |
| "to_rgb": true | |
| }, | |
| { | |
| "type": "Pad", | |
| "size": [512, 1024], | |
| "pad_val": 0, | |
| "seg_pad_val": 255 | |
| }, | |
| { | |
| "type": "DefaultFormatBundle" | |
| }, | |
| { | |
| "type": "Collect", | |
| "keys": ["img", "gt_semantic_seg"] | |
| } | |
| ], | |
| "test_pipeline": [ | |
| { | |
| "type": "LoadImageFromFile" | |
| }, | |
| { | |
| "type": "MultiScaleFlipAug", | |
| "img_scale": [2048, 1024], | |
| "flip": false, | |
| "transforms": [ | |
| { | |
| "type": "Resize", | |
| "keep_ratio": true | |
| }, | |
| { | |
| "type": "RandomFlip" | |
| }, | |
| { | |
| "type": "Normalize", | |
| "mean": [123.675, 116.28, 103.53], | |
| "std": [58.395, 57.12, 57.375], | |
| "to_rgb": true | |
| }, | |
| { | |
| "type": "ImageToTensor", | |
| "keys": ["img"] | |
| }, | |
| { | |
| "type": "Collect", | |
| "keys": ["img"] | |
| } | |
| ] | |
| } | |
| ], | |
| "data": { | |
| "samples_per_gpu": 2, | |
| "workers_per_gpu": 2, | |
| "train": { | |
| "type": "CustomDataset", | |
| "data_root": "./data/FoodSeg103/Images/", | |
| "img_dir": "img_dir/train", | |
| "ann_dir": "ann_dir/train", | |
| "pipeline": [ | |
| { | |
| "type": "LoadImageFromFile" | |
| }, | |
| { | |
| "type": "LoadAnnotations" | |
| }, | |
| { | |
| "type": "Resize", | |
| "img_scale": [2048, 1024], | |
| "ratio_range": [0.5, 2.0] | |
| }, | |
| { | |
| "type": "RandomCrop", | |
| "crop_size": [512, 1024], | |
| "cat_max_ratio": 0.75 | |
| }, | |
| { | |
| "type": "RandomFlip", | |
| "prob": 0.5 | |
| }, | |
| { | |
| "type": "PhotoMetricDistortion" | |
| }, | |
| { | |
| "type": "Normalize", | |
| "mean": [123.675, 116.28, 103.53], | |
| "std": [58.395, 57.12, 57.375], | |
| "to_rgb": true | |
| }, | |
| { | |
| "type": "Pad", | |
| "size": [512, 1024], | |
| "pad_val": 0, | |
| "seg_pad_val": 255 | |
| }, | |
| { | |
| "type": "DefaultFormatBundle" | |
| }, | |
| { | |
| "type": "Collect", | |
| "keys": ["img", "gt_semantic_seg"] | |
| } | |
| ] | |
| }, | |
| "val": { | |
| "type": "CustomDataset", | |
| "data_root": "./data/FoodSeg103/Images/", | |
| "img_dir": "img_dir/test", | |
| "ann_dir": "ann_dir/test", | |
| "pipeline": [ | |
| { | |
| "type": "LoadImageFromFile" | |
| }, | |
| { | |
| "type": "MultiScaleFlipAug", | |
| "img_scale": [2048, 1024], |