Upload LayoutFIDNetV3

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "LayoutFIDNetV3"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_layout_fidnet_v3.LayoutFIDNetV3Config",
+    "AutoModel": "modeling_layout_fidnet_v3.LayoutFIDNetV3"
+  },
+  "d_model": 256,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "max_bbox": 10,
+  "model_type": "layoutdm_fidnet_v3",
+  "nhead": 4,
+  "num_layers": 4,
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.3"
+}

configuration_layout_fidnet_v3.py

@@ -0,0 +1,23 @@
+from transformers.configuration_utils import PretrainedConfig
+
+
+class LayoutFIDNetV3Config(PretrainedConfig):
+    model_type = "layoutdm_fidnet_v3"
+
+    def __init__(
+        self,
+        num_labels: int = 1,
+        d_model: int = 256,
+        nhead: int = 4,
+        num_layers: int = 4,
+        max_bbox: int = 50,
+        **kwargs,
+    ) -> None:
+        super().__init__(
+            num_labels=num_labels,
+            **kwargs,
+        )
+        self.d_model = d_model
+        self.nhead = nhead
+        self.num_layers = num_layers
+        self.max_bbox = max_bbox

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4525657c114d0ec259692cbb809d0907b3091aa211479fb05d25214c4beb5446
+size 11655965

modeling_layout_fidnet_v3.py

@@ -0,0 +1,145 @@
+import logging
+from dataclasses import dataclass
+from typing import Optional
+
+import torch
+import torch.nn as nn
+from transformers.modeling_utils import PreTrainedModel
+from transformers.utils import ModelOutput
+
+from .configuration_layout_fidnet_v3 import LayoutFIDNetV3Config
+
+logger = logging.getLogger(__name__)
+
+
+@dataclass
+class LayoutFIDNetV3Output(ModelOutput):
+    logit_disc: torch.Tensor
+    logit_cls: torch.Tensor
+    bbox_pred: torch.Tensor
+
+
+class TransformerWithToken(nn.Module):
+    def __init__(
+        self,
+        d_model: int,
+        nhead: int,
+        dim_feedforward: int,
+        num_layers: int,
+    ) -> None:
+        super().__init__()
+
+        self.token = nn.Parameter(torch.randn(1, 1, d_model))
+        token_mask = torch.zeros(1, 1, dtype=torch.bool)
+        self.register_buffer("token_mask", token_mask)
+
+        self.core = nn.TransformerEncoder(
+            nn.TransformerEncoderLayer(
+                d_model=d_model,
+                nhead=nhead,
+                dim_feedforward=dim_feedforward,
+            ),
+            num_layers=num_layers,
+        )
+
+    def forward(self, x, src_key_padding_mask):
+        # x: [N, B, E]
+        # padding_mask: [B, N]
+        #   `False` for valid values
+        #   `True` for padded values
+
+        B = x.size(1)
+
+        token = self.token.expand(-1, B, -1)
+        x = torch.cat([token, x], dim=0)
+
+        token_mask = self.token_mask.expand(B, -1)
+        padding_mask = torch.cat([token_mask, src_key_padding_mask], dim=1)
+
+        x = self.core(x, src_key_padding_mask=padding_mask)
+
+        return x
+
+
+class LayoutFIDNetV3(PreTrainedModel):
+    config_class = LayoutFIDNetV3Config
+
+    def __init__(self, config: LayoutFIDNetV3Config) -> None:
+        super().__init__(config)
+
+        # encoder
+        self.emb_label = nn.Embedding(config.num_labels, config.d_model)
+        self.fc_bbox = nn.Linear(4, config.d_model)
+        self.enc_fc_in = nn.Linear(config.d_model * 2, config.d_model)
+
+        self.enc_transformer = TransformerWithToken(
+            d_model=config.d_model,
+            dim_feedforward=config.d_model // 2,
+            nhead=config.nhead,
+            num_layers=config.num_layers,
+        )
+
+        self.fc_out_disc = nn.Linear(config.d_model, 1)
+
+        # decoder
+        self.pos_token = nn.Parameter(torch.rand(config.max_bbox, 1, config.d_model))
+        self.dec_fc_in = nn.Linear(config.d_model * 2, config.d_model)
+
+        te = nn.TransformerEncoderLayer(
+            d_model=config.d_model,
+            nhead=config.nhead,
+            dim_feedforward=config.d_model // 2,
+        )
+        self.dec_transformer = nn.TransformerEncoder(te, num_layers=config.num_layers)
+
+        self.fc_out_cls = nn.Linear(config.d_model, config.num_labels)
+        self.fc_out_bbox = nn.Linear(config.d_model, 4)
+
+    def extract_features(self, bbox, label, padding_mask):
+        b = self.fc_bbox(bbox)
+        l = self.emb_label(label)
+        x = self.enc_fc_in(torch.cat([b, l], dim=-1))
+        x = torch.relu(x).permute(1, 0, 2)
+        x = self.enc_transformer(x, padding_mask)
+        return x[0]
+
+    def forward(self, bbox, label, padding_mask):
+        B, N, _ = bbox.size()
+        x = self.extract_features(bbox, label, padding_mask)
+
+        logit_disc = self.fc_out_disc(x).squeeze(-1)
+
+        x = x.unsqueeze(0).expand(N, -1, -1)
+        t = self.pos_token[:N].expand(-1, B, -1)
+        x = torch.cat([x, t], dim=-1)
+        x = torch.relu(self.dec_fc_in(x))
+
+        x = self.dec_transformer(x, src_key_padding_mask=padding_mask)
+        # x = x.permute(1, 0, 2)[~padding_mask]
+        x = x.permute(1, 0, 2)
+
+        # logit_cls: [B, N, L]    bbox_pred: [B, N, 4]
+        logit_cls = self.fc_out_cls(x)
+        bbox_pred = torch.sigmoid(self.fc_out_bbox(x))
+
+        return LayoutFIDNetV3Output(
+            logit_disc=logit_disc, logit_cls=logit_cls, bbox_pred=bbox_pred
+        )
+
+
+def convert_from_checkpoint(
+    repo_id: str, filename: str, config: Optional[LayoutFIDNetV3Config] = None
+) -> LayoutFIDNetV3:
+    from huggingface_hub import hf_hub_download
+
+    checkpoint_path = hf_hub_download(repo_id=repo_id, filename=filename)
+    config = config or LayoutFIDNetV3Config()
+    model = LayoutFIDNetV3(config)
+
+    logger.info(f"Loading model from {checkpoint_path}")
+    state_dict = torch.load(checkpoint_path, map_location="cpu")["state_dict"]
+
+    model.load_state_dict(state_dict, strict=True)
+    model.eval()
+
+    return model