-
maskrcnn训练自己的数据小目标非常非常差，检测不出来
auto_scale_lr = dict(base_batch_size=32, enable=False)
backend_args = None
data_root = 'D:\\Program Files\\mmdetection\\mmdet\\data\\keii\\'
dataset_type = 'KeIIDatas…
-
The readthedocs description of the pipeline products needs a bit of work. This is somewhat related to (retired) issues #38 and #39
1) Divide the table into engineering and science data products. F…
-
Now that smaug is up we need to deploy the recurring data collection pipelines there so that we start to collect data.
Acceptance Criteria:
- [ ] Data collection and processing pipelines run da…
-
One idea is to replace clone/deep copy of payload data with immutable objects with structural sharing, eg immutable.js
-
-
在train.py中为什么加载数据这里val_pipeline = copy.deepcopy(train_pipeline) 测试集的处理需要复制训练集的处理，这样训练集每次都会随机裁剪尺寸，在evaluation.py里也是这样，
train_dataset = Mydataset(train_datas, train_pipeline)
val_pipeline = c…
-
### Component(s)
exporter/prometheusremotewrite
### What happened?
## Description
I'm reporting what I _think_ is a memory leak in the `prometheusremotewriteexporter` that is triggered whe…
-
-
完全按照readme文档进行的安装, 运行出现报错
具体报错信息
```
# ComfyUI Error Report
## Error Details
- **Node Type:** Joy_caption_two
- **Exception Type:** TypeError
- **Exception Message:** LoraConfig.__init__() go…
-
I have already modified the line "checkpoint_files = sorted(load_data_list(osp.join(cur_dir, '../../models/checkpoints'), '.pt;.pth;.ckpt;.safetensors'))" to point to the local model directory as desc…