-
I'd like to start a discussion about maintenance of PaddleOCR project.
## Current Status
PaddleOCR is an open-source OCR toolkit, based on PaddlePaddle, and is known for it's high performance, a…
-
rvm在这里用时大概 660ms到750ms
lite.ai.toolkit 大概 115ms到230ms
scrfd这里大概11ms到30ms
lite.ai.toolkit 大概 8ms到20ms
环境是MacBook Pro 2.6 GHz 六核Intel Core i7
-
x2paddle转换问题，无法支持onnx v12以上，tensorflow v2.0.0以上版本的现象
1）无法支持onnx v12以上
Now, onnx2paddle support convert onnx model opset_verison [9],opset_verison of your onnx model is 12, automatically treated as o…
-
# 平台：MacOS
# Github版本: 2.6.3
使用如下的方式将onnx转换为mnn
```
./MNNConvert -f ONNX --modelFile ./rvm_mobilenetv3_fp32.onnx --MNNModel ./test.mnn --bizCode biz
```
转换后提示如下
```
hw.cpufamily: 3660…
-
Can you give me the specific code to change the backbone network to mobilenetv2? I want to try how it works
-
方向分类器的训练txt文件如下图所示：
问题：训练txt文件中加上标签是180度的图片，训练就报错，报错内容如下图所…
-
大佬，MobileNetV3 small CRNN训练batchsize合workers各种设置，固态硬盘，16G单卡跑不满，占用率50~90之间变化，请问是因为模型太小导致的吗？
-
**是检测模型**
中英文超轻量PP-OCRv2模型（13.0M） | ch_PP-OCRv2_xx
下载并用这个训练模型直接训练
载入配置文件以后 先报错
NING: The pretrained params student2_model.backbone.stage2.1.linear_conv.bn._variance not in model
[2022/01/…
-
Can you explain your data annotation format？
0001_c001_00016460_0.jpg 1 1 1
What do the second, third, and fourth columns represent？
-
### 🐛 Describe the bug
TIMM model tf_mobilenetv3_large_075 with torch.compile fails with `TypeError: 'Tensor' object is not callable`
Reproduce:
```python
root@48784a41d2f1:/workspace/timm-model…