-
First, thank you for your contribution.
I follow your step, used CASIA data and 'mnist_siamese_solver.prototxt', 'CASIA_train_test.prototxt' in 'caffe_proto' folder training CNN without mean file by …
-
Hi, I have some questions about the training parameters in train_softmax.py script and I hope someone could answer and help me.
For batch size we have default = 90 and number of batches per epoch i…
-
I trained a face tracking model with HRnet18, and the tracking performance was good (it could be tracked back within 1S after being lost）But not fast enough in the 2070S（about 30fps）。could you give me…
-
I had create my own dataset using CASIA iris detection ,
but when i training my data using i get error but training still work :
Can't open label file. (This can be normal only if you use MSCOC
…
-
hello sir,
 Have you ever met this situation?
This status usually occ…
-
I tried to finetune at L-2 layer :
ftune_vlist = [v for v in all_vars if not v.name.startswith('Mixed_8b')] in inception-resnet-v1,
and train on my_classifier.py to get .pkl file,
but I got the e…
-
Hi.
In the paper, you start training the model with the `ViT-B` model, and this is the smaller available model. Did you run experiments with smaller models, like [ViT-S](https://arxiv.org/pdf/2204.…
-
## Reference
- [VLR - Code - Data](https://www.vlrlab.net/code)
- [TextDetection文本检测数据集汇总](https://www.cnblogs.com/Tom-Ren/p/11054728.html)
- [Awesome-Scene-Text-Recognition](https://github.com/c…
-
I retrained the SpherefaceNet-20 from scratch but the performance on LFW cannt reach 99.30%.
Evaluation log is as below:
```
fold ACC
----------------
1 98.83%
2 98.83%
3 98.50%
4 99.17%
5 99…