File size: 2,419 Bytes
2ad102c 80af1e9 cffb46b 80af1e9 cffb46b 80af1e9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 |
---
license: mit
---
# FIDNetV3 from LayoutDM
[FIDNetV3](https://github.com/CyberAgentAILab/layout-dm/blob/main/src/trainer/trainer/fid/model.py#L123-L180) from [LayoutDM](https://github.com/CyberAgentAILab/layout-dm)
```python
from transformers import AutoModel
model = AutoModel.from_pretrained("shunk031/layoutdm-fidnet-v3-publaynet", trust_remote_code=True)
print(model)
# LayoutDmFIDNetV3(
# (emb_label): Embedding(5, 256)
# (fc_bbox): Linear(in_features=4, out_features=256, bias=True)
# (enc_fc_in): Linear(in_features=512, out_features=256, bias=True)
# (enc_transformer): TransformerWithToken(
# (core): TransformerEncoder(
# (layers): ModuleList(
# (0-3): 4 x TransformerEncoderLayer(
# (self_attn): MultiheadAttention(
# (out_proj): NonDynamicallyQuantizableLinear(in_features=256, out_features=256, bias=True)
# )
# (linear1): Linear(in_features=256, out_features=128, bias=True)
# (dropout): Dropout(p=0.1, inplace=False)
# (linear2): Linear(in_features=128, out_features=256, bias=True)
# (norm1): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
# (norm2): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
# (dropout1): Dropout(p=0.1, inplace=False)
# (dropout2): Dropout(p=0.1, inplace=False)
# )
# )
# )
# )
# (fc_out_disc): Linear(in_features=256, out_features=1, bias=True)
# (dec_fc_in): Linear(in_features=512, out_features=256, bias=True)
# (dec_transformer): TransformerEncoder(
# (layers): ModuleList(
# (0-3): 4 x TransformerEncoderLayer(
# (self_attn): MultiheadAttention(
# (out_proj): NonDynamicallyQuantizableLinear(in_features=256, out_features=256, bias=True)
# )
# (linear1): Linear(in_features=256, out_features=128, bias=True)
# (dropout): Dropout(p=0.1, inplace=False)
# (linear2): Linear(in_features=128, out_features=256, bias=True)
# (norm1): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
# (norm2): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
# (dropout1): Dropout(p=0.1, inplace=False)
# (dropout2): Dropout(p=0.1, inplace=False)
# )
# )
# )
# (fc_out_cls): Linear(in_features=256, out_features=5, bias=True)
# (fc_out_bbox): Linear(in_features=256, out_features=4, bias=True)
# )
```
|