VamosC / CLIP4STR

An implementation of "CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model".

VamosC/CLIP4STR Issues

是否支持长文本的识别及空格识别
Updated 17 days ago1
inference error
Closed a month ago3
Inference only
Closed a month ago1
Training other language
Closed a month ago3
Error Running Code: Missing clip4str_base16x16_d70bde1f2d.ckpt Checkpoint File
Closed a month ago1
how to Finetuning in korean (or other language)
Closed 2 months ago2
Error While Inferencing
Closed 3 months ago2
Recognize French accents
Closed 3 months ago2
Could training Parseq directly on image data containing text content sampled from the 400 million images used to train CLIP potentially yield better results?
Closed 3 months ago
Issue with inference !
Closed 3 months ago9
Using the LaTeX dataset to train CLIP4STR
Closed 4 months ago1
bad filename format for base checkpoint pre-trained on DC-1B
Closed 5 months ago9
Issue with inference
Closed 6 months ago13
Convert to ONNX
Closed 6 months ago2
Inference time on CPU/GPU
Closed 6 months ago2
Is there a way to detect spaces?
Closed 7 months ago1
clip4str attention graph
Closed 7 months ago2
Bug in run bash script
Closed 9 months ago12
请问训练时图片的尺寸大小是会resize成224*224还是128*32呢？
Closed 9 months ago9
training with japanese language
Closed 9 months ago2
The provided lr scheduler `OneCycleLR` doesn't follow PyTorch's LRScheduler API
Closed a year ago2
Error locating target for VL4STR
Closed a year ago1