Upload folder using huggingface_hub

mmdets/bbox/mmdet_anime-face_yolov3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38208bb6b8a4633193feba532e96ed9a7942129af8fe948b27bfcf8e9a30a12e
+size 246462357

mmdets/bbox/mmdet_anime-face_yolov3.py

@@ -0,0 +1,177 @@
+# _base_ = ["../_base_/schedules/schedule_1x.py", "../_base_/default_runtime.py"]
+# model settings
+data_preprocessor = dict(
+    type="DetDataPreprocessor",
+    mean=[0, 0, 0],
+    std=[255.0, 255.0, 255.0],
+    bgr_to_rgb=True,
+    pad_size_divisor=32,
+)
+model = dict(
+    type="YOLOV3",
+    data_preprocessor=data_preprocessor,
+    backbone=dict(
+        type="Darknet",
+        depth=53,
+        out_indices=(3, 4, 5),
+        init_cfg=dict(type="Pretrained", checkpoint="open-mmlab://darknet53"),
+    ),
+    neck=dict(
+        type="YOLOV3Neck",
+        num_scales=3,
+        in_channels=[1024, 512, 256],
+        out_channels=[512, 256, 128],
+    ),
+    bbox_head=dict(
+        type="YOLOV3Head",
+        num_classes=1,
+        in_channels=[512, 256, 128],
+        out_channels=[1024, 512, 256],
+        anchor_generator=dict(
+            type="YOLOAnchorGenerator",
+            base_sizes=[
+                [(116, 90), (156, 198), (373, 326)],
+                [(30, 61), (62, 45), (59, 119)],
+                [(10, 13), (16, 30), (33, 23)],
+            ],
+            strides=[32, 16, 8],
+        ),
+        bbox_coder=dict(type="YOLOBBoxCoder"),
+        featmap_strides=[32, 16, 8],
+        loss_cls=dict(
+            type="CrossEntropyLoss", use_sigmoid=True, loss_weight=1.0, reduction="sum"
+        ),
+        loss_conf=dict(
+            type="CrossEntropyLoss", use_sigmoid=True, loss_weight=1.0, reduction="sum"
+        ),
+        loss_xy=dict(
+            type="CrossEntropyLoss", use_sigmoid=True, loss_weight=2.0, reduction="sum"
+        ),
+        loss_wh=dict(type="MSELoss", loss_weight=2.0, reduction="sum"),
+    ),
+    # training and testing settings
+    train_cfg=dict(
+        assigner=dict(
+            type="GridAssigner", pos_iou_thr=0.5, neg_iou_thr=0.5, min_pos_iou=0
+        )
+    ),
+    test_cfg=dict(
+        nms_pre=1000,
+        min_bbox_size=0,
+        score_thr=0.05,
+        conf_thr=0.005,
+        nms=dict(type="nms", iou_threshold=0.45),
+        max_per_img=100,
+    ),
+)
+# dataset settings
+dataset_type = "CocoDataset"
+data_root = "data/coco/"
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/detection/coco/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+backend_args = None
+
+train_pipeline = [
+    dict(type="LoadImageFromFile", backend_args=backend_args),
+    dict(type="LoadAnnotations", with_bbox=True),
+    dict(
+        type="Expand",
+        mean=data_preprocessor["mean"],
+        to_rgb=data_preprocessor["bgr_to_rgb"],
+        ratio_range=(1, 2),
+    ),
+    dict(
+        type="MinIoURandomCrop",
+        min_ious=(0.4, 0.5, 0.6, 0.7, 0.8, 0.9),
+        min_crop_size=0.3,
+    ),
+    dict(type="RandomResize", scale=[(320, 320), (608, 608)], keep_ratio=True),
+    dict(type="RandomFlip", prob=0.5),
+    dict(type="PhotoMetricDistortion"),
+    dict(type="PackDetInputs"),
+]
+test_pipeline = [
+    dict(type="LoadImageFromFile", backend_args=backend_args),
+    dict(type="Resize", scale=(608, 608), keep_ratio=True),
+    dict(type="LoadAnnotations", with_bbox=True),
+    dict(
+        type="PackDetInputs",
+        meta_keys=("img_id", "img_path", "ori_shape", "img_shape", "scale_factor"),
+    ),
+]
+
+train_dataloader = dict(
+    batch_size=8,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type="DefaultSampler", shuffle=True),
+    batch_sampler=dict(type="AspectRatioBatchSampler"),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file="annotations/instances_train2017.json",
+        data_prefix=dict(img="train2017/"),
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        pipeline=train_pipeline,
+        backend_args=backend_args,
+    ),
+)
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type="DefaultSampler", shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file="annotations/instances_val2017.json",
+        data_prefix=dict(img="val2017/"),
+        test_mode=True,
+        pipeline=test_pipeline,
+        backend_args=backend_args,
+    ),
+)
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type="CocoMetric",
+    ann_file=data_root + "annotations/instances_val2017.json",
+    metric="bbox",
+    backend_args=backend_args,
+)
+test_evaluator = val_evaluator
+
+train_cfg = dict(max_epochs=273, val_interval=7)
+
+# optimizer
+optim_wrapper = dict(
+    type="OptimWrapper",
+    optimizer=dict(type="SGD", lr=0.001, momentum=0.9, weight_decay=0.0005),
+    clip_grad=dict(max_norm=35, norm_type=2),
+)
+
+# learning policy
+param_scheduler = [
+    dict(type="LinearLR", start_factor=0.1, by_epoch=False, begin=0, end=2000),
+    dict(type="MultiStepLR", by_epoch=True, milestones=[218, 246], gamma=0.1),
+]
+
+default_hooks = dict(checkpoint=dict(type="CheckpointHook", interval=7))
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR,
+# USER SHOULD NOT CHANGE ITS VALUES.
+# base_batch_size = (8 GPUs) x (8 samples per GPU)
+auto_scale_lr = dict(base_batch_size=64)