xinyu1205/recognize-anything
Open-source and strong foundation image recognition models.
Jupyter NotebookApache-2.0
Issues
- 0
NameError: name '_C' is not defined
#180 opened by abinzzz - 1
RuntimeError: checkpoint url or path is invalid
#167 opened by wkrrya - 0
A question on embedding
#179 opened by Researcher-DL - 2
Relax transformers dependency version
#175 opened by theearthwanderer - 2
- 1
generative tagging
#171 opened by EricIrving-chs - 0
Why is the tag and Caption text predicted by Tag2Text different? Why didn't Tag2Text use specific tags given by user?
#176 opened by aabbc-cell - 2
Open-set Tagging
#125 opened by EduardoPach - 7
Finetuning question
#173 opened by adbmdp - 1
- 3
available images for trained data
#147 opened by jurijsnazarovsambientai - 7
- 2
Error while running inference_ram_plus.py
#169 opened by Pranavk02 - 6
一个tag对应tag_chinese多个标签,如"table"==“桌子/表格”,如何过滤标签
#168 opened by Agnets - 2
Can i inference RAM to output text?
#166 opened by DYDevelop - 1
4M version checkpoint
#165 opened by fmy7834 - 5
Concat label embed RAM++
#154 opened by pribadihcr - 0
- 8
How to fine-tune Tag2Text with custom tags?
#143 opened by SeeknnDestroy - 0
pre_caption function
#163 opened by pribadihcr - 1
The pre-trained checkpoint
#162 opened by pribadihcr - 1
Effect commit b85a8770a8c75bd7a508e97a328ebea7444917b7
#160 opened by pribadihcr - 1
Utilize SoViT-400m/14 image encoder
#161 opened by pribadihcr - 2
- 2
- 1
Docker image / FastAPI wrapper
#158 opened by mnahkies - 3
sbu和cc3m的数据集照片怎么下载呀?
#157 opened by Juhywcy - 1
Tags categories
#150 opened by Fa-ti-ma - 1
请问如何使用预训练模型进行微调,增加了一个类别
#153 opened by chentiao - 2
- 0
Visualization Map RAM
#152 opened by pribadihcr - 2
- 2
Weights for SWIN_B/SWIN_T
#144 opened by jurijsnazarovsambientai - 2
- 1
中文tag文本中很多尾缀有个空格,是有什么代表含义么?
#142 opened by YoungerGao - 1
Question when finetuning Tag2Text Configuration
#141 opened by DH-RYU - 6
- 2
Question about class thresholds
#137 opened by vishaal27 - 1
loss_tag is too large
#136 opened by SANJINGSHOU14 - 1
Question about RAM
#135 opened by Davidyao99 - 2
Demo: batch_inference.py: error: the following arguments are required: --checkpoint, --dataset
#132 opened by ooza - 1
Woo, it's so amazing for your rapid implementation!您好,请问现在caption的接口有开放的计划吗?
#134 opened by starrism-yu - 2
parse_tag
#133 opened by mengpingzeng - 2
High resolution images
#131 opened by codonna9 - 3
Error when run finetune.py
#130 opened by shuxjweb - 5
parse_label_id
#128 opened by mengpingzeng - 2
Cannot run plus RAM model
#129 opened by 5875johnsmith - 1
Confusion about spatial embeddings in ram_plus!
#127 opened by stoensin - 2
训练数据集链接失效了
#126 opened by wbh604 - 7
pre-train 和 finetune 阶段,swin-transformer、CLIP text encoder和 tag embedding 都反传梯度吗,学习率也都是相同的吗?
#124 opened by tigerzjh