-
Hi, thank you for your work. This is a very meaningful job. Regarding algorithm design, I have a question.
You convert an input image into patches firstly, if some characters are cut off or some pat…
-
你好，我最近在尝试ABINet算法，但是运行时进行eval时出现以下错误：
```
[2023-09-08 13:50:59,079 main.py:229 INFO pretrain-vision-model] Construct learner.
[2023-09-08 13:51:01,400 main.py:233 INFO pretrain-vision-model] Start …
-
I am reproducing the vit-tiny model but have a problem when testing on III5k.It prompts unmatched number of channels.Then i find the input images are RGB mode but the input channels of vitstr is just …
-
CUDA_VISIBLE_DEVICES=0 python train.py --train_data mydata/mytrain --valid_data mydata/mytrain --select_data / --batch_ratio 1 --Transformation None --FeatureExtraction None --SequenceModeling None --…
-
Hello @roatienza!
Thanks for this great repo!
I am trying to train using rand_aug but I am facing some issues. I get an error on blur.py when trying to convert from BGR to Grayscale. It seems th…
-
I trained my model for japanese language. The validation accuracy goes upto 99.9% but when testing on test image it fails very badly. Can you share demo.py file so that I can check if I am doing every…
-
### 🚀 The feature
`torch.compile` is a Pytorch feature that compiles the model into static kernels using a JIT. More information on: https://pytorch.org/tutorials/intermediate/torch_compile_tutoria…
-
hi, i try run test.py with this:
CUDA_VISION_DEVICES=0 python test.py --eval_data ../../data/data_lmdb_release/evaluation/ --benchmark_all_eval --Transformation None --FeatureExtraction None --Seque…
-
I am training the VITSTR-tiny model on my custom text dataset and it is giving the same training loss for every iteration which is 0..0000. I have not changed any parameters in the model. What might b…
-
Thanks for sharing the source codes!
I found that you exploited **'Pretrained weight file of DeiT'** instead of training from scratch.
However, i see you emphasize 'Efficiency' of your model.
I wo…