adding better trained model

20230608_onnx_416_mbnv2_dl3/deploy.json

@@ -0,0 +1,16 @@
+{
+    "version": "1.1.0",
+    "task": "Segmentor",
+    "models": [
+        {
+            "name": "depthwiseseparableaspp",
+            "net": "end2end.onnx",
+            "weights": "",
+            "backend": "onnxruntime",
+            "precision": "FP32",
+            "batch_size": 1,
+            "dynamic_shape": false
+        }
+    ],
+    "customs": []
+}

20230608_onnx_416_mbnv2_dl3/detail.json

@@ -0,0 +1,37 @@
+{
+    "version": "1.1.0",
+    "codebase": {
+        "task": "Segmentation",
+        "codebase": "mmseg",
+        "version": "1.0.0",
+        "pth": "../mmsegmentation/work_dirs/mobilenet_deeplab_drone/iter_96000.pth",
+        "config": "../mmsegmentation/work_dirs/mobilenet_deeplab_drone/mobilenet_deeplab_drone.py"
+    },
+    "codebase_config": {
+        "type": "mmseg",
+        "task": "Segmentation",
+        "with_argmax": true
+    },
+    "onnx_config": {
+        "type": "onnx",
+        "export_params": true,
+        "keep_initializers_as_inputs": false,
+        "opset_version": 11,
+        "save_file": "end2end.onnx",
+        "input_names": [
+            "input"
+        ],
+        "output_names": [
+            "output"
+        ],
+        "input_shape": [
+            416,
+            416
+        ],
+        "optimize": true
+    },
+    "backend_config": {
+        "type": "onnxruntime"
+    },
+    "calib_config": {}
+}

20230608_onnx_416_mbnv2_dl3/end2end.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c28c542c8c484c0c17e5d94afb9e9f4e85aa0c9b8a9cd28ae8ca0e7ff3e72e9
+size 11185635

20230608_onnx_416_mbnv2_dl3/iter_96000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d551e8499ddd3fc34142a7947b34fb3d48decdec4033251b39e92394247207f3
+size 37443597

20230608_onnx_416_mbnv2_dl3/mobilenet_deeplab_drone.py

@@ -0,0 +1,221 @@
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+data_preprocessor = dict(
+    type='SegDataPreProcessor',
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    bgr_to_rgb=True,
+    pad_val=0,
+    seg_pad_val=255,
+    size=(416, 416))
+model = dict(
+    type='EncoderDecoder',
+    data_preprocessor=dict(
+        type='SegDataPreProcessor',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        bgr_to_rgb=True,
+        pad_val=0,
+        seg_pad_val=255,
+        size=(416, 416)),
+    pretrained='mmcls://mobilenet_v2',
+    backbone=dict(
+        type='MobileNetV2',
+        widen_factor=1.0,
+        strides=(1, 2, 2, 1, 1, 1, 1),
+        dilations=(1, 1, 1, 2, 2, 4, 4),
+        out_indices=(1, 2, 4, 6),
+        norm_cfg=dict(type='SyncBN', requires_grad=True)),
+    decode_head=dict(
+        type='DepthwiseSeparableASPPHead',
+        in_channels=320,
+        in_index=3,
+        channels=128,
+        dilations=(1, 12, 24, 36),
+        c1_in_channels=24,
+        c1_channels=12,
+        dropout_ratio=0.1,
+        num_classes=3,
+        norm_cfg=dict(type='SyncBN', requires_grad=True),
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    auxiliary_head=dict(
+        type='FCNHead',
+        in_channels=96,
+        in_index=2,
+        channels=64,
+        num_convs=1,
+        concat_input=False,
+        dropout_ratio=0.1,
+        num_classes=3,
+        norm_cfg=dict(type='SyncBN', requires_grad=True),
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))
+dataset_type = 'DroneDataset'
+data_root = 'data/drone_custom_dataset'
+crop_size = (416, 416)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(
+        type='RandomResize',
+        scale=(2048, 416),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=(416, 416), cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=(2048, 416), keep_ratio=True),
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs')
+]
+img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
+tta_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=None),
+    dict(
+        type='TestTimeAug',
+        transforms=[[{
+            'type': 'Resize',
+            'scale_factor': 0.5,
+            'keep_ratio': True
+        }, {
+            'type': 'Resize',
+            'scale_factor': 0.75,
+            'keep_ratio': True
+        }, {
+            'type': 'Resize',
+            'scale_factor': 1.0,
+            'keep_ratio': True
+        }, {
+            'type': 'Resize',
+            'scale_factor': 1.25,
+            'keep_ratio': True
+        }, {
+            'type': 'Resize',
+            'scale_factor': 1.5,
+            'keep_ratio': True
+        }, {
+            'type': 'Resize',
+            'scale_factor': 1.75,
+            'keep_ratio': True
+        }],
+                    [{
+                        'type': 'RandomFlip',
+                        'prob': 0.0,
+                        'direction': 'horizontal'
+                    }, {
+                        'type': 'RandomFlip',
+                        'prob': 1.0,
+                        'direction': 'horizontal'
+                    }], [{
+                        'type': 'LoadAnnotations'
+                    }], [{
+                        'type': 'PackSegInputs'
+                    }]])
+]
+train_dataloader = dict(
+    batch_size=24,
+    num_workers=1,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(
+        type='DroneDataset',
+        data_root='data/drone_custom_dataset',
+        data_prefix=dict(img_path='images', seg_map_path='anns'),
+        ann_file='train.txt',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(type='LoadAnnotations'),
+            dict(
+                type='RandomResize',
+                scale=(2048, 416),
+                ratio_range=(0.5, 2.0),
+                keep_ratio=True),
+            dict(type='RandomCrop', crop_size=(416, 416), cat_max_ratio=0.75),
+            dict(type='RandomFlip', prob=0.5),
+            dict(type='PhotoMetricDistortion'),
+            dict(type='PackSegInputs')
+        ]))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type='DroneDataset',
+        data_root='data/drone_custom_dataset',
+        data_prefix=dict(img_path='images', seg_map_path='anns'),
+        ann_file='val.txt',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(type='Resize', scale=(2048, 416), keep_ratio=True),
+            dict(type='LoadAnnotations'),
+            dict(type='PackSegInputs')
+        ]))
+test_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type='DroneDataset',
+        data_root='data/drone_custom_dataset',
+        data_prefix=dict(img_path='images', seg_map_path='anns'),
+        ann_file='val.txt',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(type='Resize', scale=(2048, 416), keep_ratio=True),
+            dict(type='LoadAnnotations'),
+            dict(type='PackSegInputs')
+        ]))
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+test_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+default_scope = 'mmseg'
+env_cfg = dict(
+    cudnn_benchmark=True,
+    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
+    dist_cfg=dict(backend='nccl'))
+vis_backends = [dict(type='LocalVisBackend')]
+visualizer = dict(
+    type='SegLocalVisualizer',
+    vis_backends=[dict(type='LocalVisBackend')],
+    name='visualizer')
+log_processor = dict(by_epoch=False)
+log_level = 'INFO'
+load_from = None
+resume = False
+tta_model = dict(type='SegTTAModel')
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005),
+    clip_grad=None)
+param_scheduler = [
+    dict(
+        type='PolyLR',
+        eta_min=0.0001,
+        power=0.9,
+        begin=0,
+        end=240000,
+        by_epoch=False)
+]
+train_cfg = dict(
+    type='IterBasedTrainLoop', max_iters=240000, val_interval=24000)
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')
+default_hooks = dict(
+    timer=dict(type='IterTimerHook'),
+    logger=dict(type='LoggerHook', interval=50, log_metric_by_epoch=False),
+    param_scheduler=dict(type='ParamSchedulerHook'),
+    checkpoint=dict(type='CheckpointHook', by_epoch=False, interval=24000),
+    sampler_seed=dict(type='DistSamplerSeedHook'),
+    visualization=dict(type='SegVisualizationHook'))
+launcher = 'pytorch'
+work_dir = './work_dirs/mobilenet_deeplab_drone'

20230608_onnx_416_mbnv2_dl3/pipeline.json

@@ -0,0 +1,125 @@
+{
+    "pipeline": {
+        "input": [
+            "img"
+        ],
+        "output": [
+            "post_output"
+        ],
+        "tasks": [
+            {
+                "type": "Task",
+                "module": "Transform",
+                "name": "Preprocess",
+                "input": [
+                    "img"
+                ],
+                "output": [
+                    "prep_output"
+                ],
+                "transforms": [
+                    {
+                        "type": "LoadImageFromFile"
+                    },
+                    {
+                        "type": "Resize",
+                        "keep_ratio": false,
+                        "size": [
+                            416,
+                            416
+                        ]
+                    },
+                    {
+                        "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"
+                        ],
+                        "meta_keys": [
+                            "img_shape",
+                            "pad_shape",
+                            "ori_shape",
+                            "img_norm_cfg",
+                            "scale_factor"
+                        ]
+                    }
+                ]
+            },
+            {
+                "name": "depthwiseseparableaspp",
+                "type": "Task",
+                "module": "Net",
+                "is_batched": false,
+                "input": [
+                    "prep_output"
+                ],
+                "output": [
+                    "infer_output"
+                ],
+                "input_map": {
+                    "img": "input"
+                },
+                "output_map": {}
+            },
+            {
+                "type": "Task",
+                "module": "mmseg",
+                "name": "postprocess",
+                "component": "ResizeMask",
+                "params": {
+                    "type": "DepthwiseSeparableASPPHead",
+                    "in_channels": 320,
+                    "in_index": 3,
+                    "channels": 128,
+                    "dilations": [
+                        1,
+                        12,
+                        24,
+                        36
+                    ],
+                    "c1_in_channels": 24,
+                    "c1_channels": 12,
+                    "dropout_ratio": 0.1,
+                    "num_classes": 3,
+                    "norm_cfg": {
+                        "type": "SyncBN",
+                        "requires_grad": true
+                    },
+                    "align_corners": false,
+                    "loss_decode": {
+                        "type": "CrossEntropyLoss",
+                        "use_sigmoid": false,
+                        "loss_weight": 1.0
+                    },
+                    "with_argmax": true
+                },
+                "output": [
+                    "post_output"
+                ],
+                "input": [
+                    "prep_output",
+                    "infer_output"
+                ]
+            }
+        ]
+    }
+}

20230608_onnx_416_mbnv2_dl3/vis_data/config.py

@@ -0,0 +1,221 @@
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+data_preprocessor = dict(
+    type='SegDataPreProcessor',
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    bgr_to_rgb=True,
+    pad_val=0,
+    seg_pad_val=255,
+    size=(416, 416))
+model = dict(
+    type='EncoderDecoder',
+    data_preprocessor=dict(
+        type='SegDataPreProcessor',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        bgr_to_rgb=True,
+        pad_val=0,
+        seg_pad_val=255,
+        size=(416, 416)),
+    pretrained='mmcls://mobilenet_v2',
+    backbone=dict(
+        type='MobileNetV2',
+        widen_factor=1.0,
+        strides=(1, 2, 2, 1, 1, 1, 1),
+        dilations=(1, 1, 1, 2, 2, 4, 4),
+        out_indices=(1, 2, 4, 6),
+        norm_cfg=dict(type='SyncBN', requires_grad=True)),
+    decode_head=dict(
+        type='DepthwiseSeparableASPPHead',
+        in_channels=320,
+        in_index=3,
+        channels=128,
+        dilations=(1, 12, 24, 36),
+        c1_in_channels=24,
+        c1_channels=12,
+        dropout_ratio=0.1,
+        num_classes=3,
+        norm_cfg=dict(type='SyncBN', requires_grad=True),
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    auxiliary_head=dict(
+        type='FCNHead',
+        in_channels=96,
+        in_index=2,
+        channels=64,
+        num_convs=1,
+        concat_input=False,
+        dropout_ratio=0.1,
+        num_classes=3,
+        norm_cfg=dict(type='SyncBN', requires_grad=True),
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
+    train_cfg=dict(),
+    test_cfg=dict(mode='whole'))
+dataset_type = 'DroneDataset'
+data_root = 'data/drone_custom_dataset'
+crop_size = (416, 416)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(
+        type='RandomResize',
+        scale=(2048, 416),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=(416, 416), cat_max_ratio=0.75),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='PackSegInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=(2048, 416), keep_ratio=True),
+    dict(type='LoadAnnotations'),
+    dict(type='PackSegInputs')
+]
+img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
+tta_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=None),
+    dict(
+        type='TestTimeAug',
+        transforms=[[{
+            'type': 'Resize',
+            'scale_factor': 0.5,
+            'keep_ratio': True
+        }, {
+            'type': 'Resize',
+            'scale_factor': 0.75,
+            'keep_ratio': True
+        }, {
+            'type': 'Resize',
+            'scale_factor': 1.0,
+            'keep_ratio': True
+        }, {
+            'type': 'Resize',
+            'scale_factor': 1.25,
+            'keep_ratio': True
+        }, {
+            'type': 'Resize',
+            'scale_factor': 1.5,
+            'keep_ratio': True
+        }, {
+            'type': 'Resize',
+            'scale_factor': 1.75,
+            'keep_ratio': True
+        }],
+                    [{
+                        'type': 'RandomFlip',
+                        'prob': 0.0,
+                        'direction': 'horizontal'
+                    }, {
+                        'type': 'RandomFlip',
+                        'prob': 1.0,
+                        'direction': 'horizontal'
+                    }], [{
+                        'type': 'LoadAnnotations'
+                    }], [{
+                        'type': 'PackSegInputs'
+                    }]])
+]
+train_dataloader = dict(
+    batch_size=24,
+    num_workers=1,
+    persistent_workers=True,
+    sampler=dict(type='InfiniteSampler', shuffle=True),
+    dataset=dict(
+        type='DroneDataset',
+        data_root='data/drone_custom_dataset',
+        data_prefix=dict(img_path='images', seg_map_path='anns'),
+        ann_file='train.txt',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(type='LoadAnnotations'),
+            dict(
+                type='RandomResize',
+                scale=(2048, 416),
+                ratio_range=(0.5, 2.0),
+                keep_ratio=True),
+            dict(type='RandomCrop', crop_size=(416, 416), cat_max_ratio=0.75),
+            dict(type='RandomFlip', prob=0.5),
+            dict(type='PhotoMetricDistortion'),
+            dict(type='PackSegInputs')
+        ]))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type='DroneDataset',
+        data_root='data/drone_custom_dataset',
+        data_prefix=dict(img_path='images', seg_map_path='anns'),
+        ann_file='val.txt',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(type='Resize', scale=(2048, 416), keep_ratio=True),
+            dict(type='LoadAnnotations'),
+            dict(type='PackSegInputs')
+        ]))
+test_dataloader = dict(
+    batch_size=1,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type='DroneDataset',
+        data_root='data/drone_custom_dataset',
+        data_prefix=dict(img_path='images', seg_map_path='anns'),
+        ann_file='val.txt',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(type='Resize', scale=(2048, 416), keep_ratio=True),
+            dict(type='LoadAnnotations'),
+            dict(type='PackSegInputs')
+        ]))
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+test_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
+default_scope = 'mmseg'
+env_cfg = dict(
+    cudnn_benchmark=True,
+    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
+    dist_cfg=dict(backend='nccl'))
+vis_backends = [dict(type='LocalVisBackend')]
+visualizer = dict(
+    type='SegLocalVisualizer',
+    vis_backends=[dict(type='LocalVisBackend')],
+    name='visualizer')
+log_processor = dict(by_epoch=False)
+log_level = 'INFO'
+load_from = None
+resume = False
+tta_model = dict(type='SegTTAModel')
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005),
+    clip_grad=None)
+param_scheduler = [
+    dict(
+        type='PolyLR',
+        eta_min=0.0001,
+        power=0.9,
+        begin=0,
+        end=240000,
+        by_epoch=False)
+]
+train_cfg = dict(
+    type='IterBasedTrainLoop', max_iters=240000, val_interval=24000)
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')
+default_hooks = dict(
+    timer=dict(type='IterTimerHook'),
+    logger=dict(type='LoggerHook', interval=50, log_metric_by_epoch=False),
+    param_scheduler=dict(type='ParamSchedulerHook'),
+    checkpoint=dict(type='CheckpointHook', by_epoch=False, interval=24000),
+    sampler_seed=dict(type='DistSamplerSeedHook'),
+    visualization=dict(type='SegVisualizationHook'))
+launcher = 'pytorch'
+work_dir = './work_dirs/mobilenet_deeplab_drone'