C:\SOLO-master>call activate solov2_2

C:\SOLO-master>conda.bat activate solov2_2

(solov2_2) C:\SOLO-master>pip list
Package            Version             Location
------------------ ------------------- --------------
addict             2.4.0
certifi            2021.5.30
charset-normalizer 2.0.4
cycler             0.10.0
Cython             0.29.24
idna               3.2
kiwisolver         1.3.2
matplotlib         3.4.3
mmcv               0.2.16
mmdet              1.0.0+unknown       c:\solo-master
numpy              1.21.2
olefile            0.46
opencv-python      4.5.3.56
Pillow             6.2.2
pip                21.0.1
pycocotools        2.0
pyparsing          2.4.7
python-dateutil    2.8.2
PyYAML             5.4.1
requests           2.26.0
scipy              1.7.1
setuptools         52.0.0.post20210125
six                1.16.0
terminaltables     3.1.0
torch              1.10.0.dev20210904
torchvision        0.11.0.dev20210904
typing-extensions  3.10.0.0
urllib3            1.26.6
wheel              0.37.0
wincertstore       0.2

(solov2_2) C:\SOLO-master>python tools/train.py configs/solov2/solov2_r50_fpn_8gpu_3x.py
2021-09-04 15:18:39,590 - mmdet - INFO - Distributed training: False
2021-09-04 15:18:39,590 - mmdet - INFO - MMDetection Version: 1.0.0+unknown
2021-09-04 15:18:39,591 - mmdet - INFO - Config:
# model settings
model = dict(
    type='SOLOv2',
    pretrained='torchvision://resnet50',
    backbone=dict(
        type='ResNet',
        depth=50,
        num_stages=4,
        out_indices=(0, 1, 2, 3), # C2, C3, C4, C5
        frozen_stages=1,
        style='pytorch'),
    neck=dict(
        type='FPN',
        in_channels=[256, 512, 1024, 2048],
        out_channels=256,
        start_level=0,
        num_outs=5),
    bbox_head=dict(
        type='SOLOv2Head',
        num_classes=81,
        in_channels=256,
        stacked_convs=4,
        seg_feat_channels=512,
        strides=[8, 8, 16, 32, 32],
        scale_ranges=((1, 96), (48, 192), (96, 384), (192, 768), (384, 2048)),
        sigma=0.2,
        num_grids=[40, 36, 24, 16, 12],
        ins_out_channels=256,
        loss_ins=dict(
            type='DiceLoss',
            use_sigmoid=True,
            loss_weight=3.0),
        loss_cate=dict(
            type='FocalLoss',
            use_sigmoid=True,
            gamma=2.0,
            alpha=0.25,
            loss_weight=1.0)),
    mask_feat_head=dict(
            type='MaskFeatHead',
            in_channels=256,
            out_channels=128,
            start_level=0,
            end_level=3,
            num_classes=256,
            norm_cfg=dict(type='GN', num_groups=32, requires_grad=True)),
    )
# training and testing settings
train_cfg = dict()
test_cfg = dict(
    nms_pre=500,
    score_thr=0.1,
    mask_thr=0.5,
    update_thr=0.05,
    kernel='gaussian',  # gaussian/linear
    sigma=2.0,
    max_per_img=100)
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
    dict(type='Resize',
         img_scale=[(1333, 800), (1333, 768), (1333, 736),
                    (1333, 704), (1333, 672), (1333, 640)],
         multiscale_mode='value',
         keep_ratio=True),
    dict(type='RandomFlip', flip_ratio=0.5),
    dict(type='Normalize', **img_norm_cfg),
    dict(type='Pad', size_divisor=32),
    dict(type='DefaultFormatBundle'),
    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
]
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='MultiScaleFlipAug',
        img_scale=(1333, 800),
        flip=False,
        transforms=[
            dict(type='Resize', keep_ratio=True),
            dict(type='RandomFlip'),
            dict(type='Normalize', **img_norm_cfg),
            dict(type='Pad', size_divisor=32),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img']),
        ])
]
data = dict(
    imgs_per_gpu=2,
    workers_per_gpu=2,
    train=dict(
        type=dataset_type,
        ann_file=data_root + 'annotations/instances_train2017.json',
        img_prefix=data_root + 'train2017/',
        pipeline=train_pipeline),
    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))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
    policy='step',
    warmup='linear',
    warmup_iters=500,
    warmup_ratio=0.01,
    step=[27, 33])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
    interval=50,
    hooks=[
        dict(type='TextLoggerHook'),
        # dict(type='TensorboardLoggerHook')
    ])
# yapf:enable
# runtime settings
total_epochs = 36
device_ids = range(8)
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/solov2_release_r50_fpn_8gpu_3x'
load_from = None
resume_from = None
workflow = [('train', 1)]

2021-09-04 15:18:39,821 - mmdet - INFO - load model from: torchvision://resnet50
2021-09-04 15:18:39,872 - mmdet - WARNING - The model and loaded state dict do not match exactly

unexpected key in source state_dict: fc.weight, fc.bias

loading annotations into memory...
Done (t=0.03s)
creating index...
index created!
2021-09-04 15:18:40,145 - mmdet - INFO - Start running, host: MASTER@DESKTOP-9AP1OFR, work_dir: C:\SOLO-master\work_dirs\solov2_release_r50_fpn_8gpu_3x
2021-09-04 15:18:40,146 - mmdet - INFO - workflow: [('train', 1)], max: 36 epochs
C:\Users\MASTER\.conda\envs\solov2_2\lib\site-packages\torch\nn\functional.py:3635: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.
  "See the documentation of nn.Upsample for details.".format(mode)
C:\Users\MASTER\.conda\envs\solov2_2\lib\site-packages\torch\nn\functional.py:3680: UserWarning: The default behavior for interpolate/upsample with float scale_factor changed in 1.6.0 to align with other frameworks/libraries, and now uses scale_factor directly, instead of relying on the computed output size. If you wish to restore the old behavior, please set recompute_scale_factor=True. See the documentation of nn.Upsample for details.
  "The default behavior for interpolate/upsample with float scale_factor changed "
c:\solo-master\mmdet\models\anchor_heads\solov2_head.py:322: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
  coord_w = int((center_w / upsampled_size[1]) // (1. / num_grid))
c:\solo-master\mmdet\models\anchor_heads\solov2_head.py:323: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
  coord_h = int((center_h / upsampled_size[0]) // (1. / num_grid))
c:\solo-master\mmdet\models\anchor_heads\solov2_head.py:326: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
  top_box = max(0, int(((center_h - half_h) / upsampled_size[0]) // (1. / num_grid)))
c:\solo-master\mmdet\models\anchor_heads\solov2_head.py:327: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
  down_box = min(num_grid - 1, int(((center_h + half_h) / upsampled_size[0]) // (1. / num_grid)))
c:\solo-master\mmdet\models\anchor_heads\solov2_head.py:328: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
  left_box = max(0, int(((center_w - half_w) / upsampled_size[1]) // (1. / num_grid)))
c:\solo-master\mmdet\models\anchor_heads\solov2_head.py:329: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
  right_box = min(num_grid - 1, int(((center_w + half_w) / upsampled_size[1]) // (1. / num_grid)))
Traceback (most recent call last):
  File "tools/train.py", line 125, in <module>
    main()
  File "tools/train.py", line 121, in main
    timestamp=timestamp)
  File "c:\solo-master\mmdet\apis\train.py", line 111, in train_detector
    timestamp=timestamp)
  File "c:\solo-master\mmdet\apis\train.py", line 297, in _non_dist_train
    runner.run(data_loaders, cfg.workflow, cfg.total_epochs)
  File "C:\Users\MASTER\.conda\envs\solov2_2\lib\site-packages\mmcv\runner\runner.py", line 364, in run
    epoch_runner(data_loaders[i], **kwargs)
  File "C:\Users\MASTER\.conda\envs\solov2_2\lib\site-packages\mmcv\runner\runner.py", line 275, in train
    self.call_hook('after_train_iter')
  File "C:\Users\MASTER\.conda\envs\solov2_2\lib\site-packages\mmcv\runner\runner.py", line 231, in call_hook
    getattr(hook, fn_name)(self)
  File "C:\Users\MASTER\.conda\envs\solov2_2\lib\site-packages\mmcv\runner\hooks\optimizer.py", line 18, in after_train_iter
    runner.outputs['loss'].backward()
  File "C:\Users\MASTER\.conda\envs\solov2_2\lib\site-packages\torch\_tensor.py", line 306, in backward
    torch.autograd.backward(self, gradient, retain_graph, create_graph, inputs=inputs)
  File "C:\Users\MASTER\.conda\envs\solov2_2\lib\site-packages\torch\autograd\__init__.py", line 156, in backward
    allow_unreachable=True, accumulate_grad=True)  # allow_unreachable flag
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [2, 128, 232, 160]], which is output 0 of ReluBackward, is at version 3; expected version 0 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).

(solov2_2) C:\SOLO-master>pause
Appuyez sur une touche pour continuer...