-
Hello, the network structure of MobileNetV3 seems to be different from that of the original author. The SE module of V3 is not a module that uses SENet. The author changed nn.Line to nn.Conv
-
When running the unittest suite with `--iree-mhlo-demote-i64-to-i32=false`, a few Wide Integer Emulation patterns appear missing: `arith.maxsi`, `arith.minsi`, `arith.index_cast`.
Full log:
```
…
-
请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem
- 系统环境/System Environment：win10
- 版本号/Version：Paddle： PaddleOCR： 问题相关组件/Related components：模型：ch_PP-OCRv2_…
-
## Checklist:
1. 查找[历史相关issue](https://github.com/PaddlePaddle/PaddleX/issues)寻求解答
2. 翻阅[FAQ常见问题汇总和答疑](https://github.com/PaddlePaddle/PaddleX/blob/develop/docs/FAQ/FAQ.md)
3. 确认bug是否在新版本里还未修复
4…
-
配置权重配置的https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x1_0_pretrained.tar 这个是对的吗？还想问这串地址自己写的时候该怎么填，paddle默认的模型库能出来这个url地址吗？训练损失在训练了近5000iter损失还有几百，这是正常现象吗？还是我哪里配置错了
zmdcs updated
2 years ago
-
您好,我下载了ICDAR2015,并且按照步骤使用gen_label.py产生标签文件;下载了MobileNetV3_large_x0_5_pretrained预训练模型,训练时报如下错误,这种情况是因为什么呢?看了好issue,好像和大家的问题不太一样.
python3 tools/train.py -c configs/det/det_mv3_db_v1.1.yml -o Global.pr…
-
Is it possible to use this model over torch2trt? https://github.com/NVIDIA-AI-IOT/torch2trt
How would one go about accomplishing that? It seems that the matting network exists externally from the NN.
-
有人知道这是什么问题吗？
[2022/09/25 01:31:33] ppocr INFO: epoch: [123/292], global_step: 3900, lr: 0.000355, dila_dbloss_Student_Teacher: 1.147592, dila_dbloss_Student2_Teacher: 1.116941, loss: 5.599220, dml_th…
-
pspnet
修改如下：
model:
type: PSPNet
backbone:
type: MobileNetV3_large_x1_0
pretrained: https://paddleseg.bj.bcebos.com/dygraph/backbone/mobilenetv3_large_x1_0_ssld.tar.gz
backbone…
-
How do you convert the algorithm to onnx for model deployment?(e.g. Padim)