try using yolox

main/inference.py

@@ -48,6 +48,11 @@ class Inferer:
         model = init_detector(config_file, checkpoint_file, device=self.device)  # or device='cuda:0'
         self.model = model
 
+        # checkpoint_file = osp.join(CUR_DIR, '../pretrained_models/mmdet/yolox_x_8x8_300e_coco_20211126_140254-1ef88d67.pth')
+        # config_file= osp.join(CUR_DIR, '../pretrained_models/mmdet/yolox_x_8x8-300e_coco.py')
+        # model = init_detector(config_file, checkpoint = checkpoint_file, device=self.device)  # or device='cuda:0'
+        # self.model = model
+
     def infer(self, original_img, iou_thr, multi_person=False, mesh_as_vertices=False):
         from utils.preprocessing import process_bbox, generate_patch_image
         from utils.vis import render_mesh

pretrained_models/mmdet/yolox_s_8x8-300e_coco.py

@@ -0,0 +1,102 @@
+img_scale = (640, 640)  # height, width
+
+# model settings
+model = dict(
+    type='YOLOX',
+    input_size=img_scale,
+    random_size_range=(15, 25),
+    random_size_interval=10,
+    backbone=dict(type='CSPDarknet', deepen_factor=0.33, widen_factor=0.5),
+    neck=dict(
+        type='YOLOXPAFPN',
+        in_channels=[128, 256, 512],
+        out_channels=128,
+        num_csp_blocks=1),
+    bbox_head=dict(
+        type='YOLOXHead', num_classes=80, in_channels=128, feat_channels=128),
+    train_cfg=dict(assigner=dict(type='SimOTAAssigner', center_radius=2.5)),
+    # In order to align the source code, the threshold of the val phase is
+    # 0.01, and the threshold of the test phase is 0.001.
+    test_cfg=dict(score_thr=0.01, nms=dict(type='nms', iou_threshold=0.65)))
+
+# dataset settings
+data_root = 'data/coco/'
+dataset_type = 'CocoDataset'
+
+train_pipeline = [
+    dict(type='Mosaic', img_scale=img_scale, pad_val=114.0),
+    dict(
+        type='RandomAffine',
+        scaling_ratio_range=(0.1, 2),
+        border=(-img_scale[0] // 2, -img_scale[1] // 2)),
+    dict(
+        type='MixUp',
+        img_scale=img_scale,
+        ratio_range=(0.8, 1.6),
+        pad_val=114.0),
+    dict(type='YOLOXHSVRandomAug'),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    # According to the official implementation, multi-scale
+    # training is not considered here but in the
+    # 'mmdet/models/detectors/yolox.py'.
+    dict(type='Resize', img_scale=img_scale, keep_ratio=True),
+    dict(
+        type='Pad',
+        pad_to_square=True,
+        # If the image is three-channel, the pad value needs
+        # to be set separately for each channel.
+        pad_val=dict(img=(114.0, 114.0, 114.0))),
+    dict(type='FilterAnnotations', min_gt_bbox_wh=(1, 1), keep_empty=False),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
+]
+
+train_dataset = dict(
+    type='MultiImageMixDataset',
+    dataset=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_train2017.json',
+        img_prefix=data_root + 'train2017/',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(type='LoadAnnotations', with_bbox=True)
+        ],
+        filter_empty_gt=False,
+    ),
+    pipeline=train_pipeline)
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=img_scale,
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(
+                type='Pad',
+                pad_to_square=True,
+                pad_val=dict(img=(114.0, 114.0, 114.0))),
+            dict(type='DefaultFormatBundle'),
+            dict(type='Collect', keys=['img'])
+        ])
+]
+
+data = dict(
+    samples_per_gpu=8,
+    workers_per_gpu=4,
+    persistent_workers=True,
+    train=train_dataset,
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        pipeline=test_pipeline))
+
+evaluation = dict(interval=1, metric='bbox')

pretrained_models/mmdet/yolox_x_8x8-300e_coco.py

@@ -0,0 +1,8 @@
+_base_ = './yolox_s_8x8-300e_coco.py'
+
+# model settings
+model = dict(
+    backbone=dict(deepen_factor=1.33, widen_factor=1.25),
+    neck=dict(
+        in_channels=[320, 640, 1280], out_channels=320, num_csp_blocks=4),
+    bbox_head=dict(in_channels=320, feat_channels=320))

pretrained_models/mmdet/yolox_x_8x8_300e_coco_20211126_140254-1ef88d67.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ef88d67f9c912a7c3a6df4f4d9bdf391cf70df867e6c9d7f249c7a3990e3dec
+size 396898755