Upload Pipeline

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 +1,311 @@
+{
+  "inputs": [
+    "images"
+  ],
+  "modules": {
+    "avg_pool": {
+      "config": {
+        "args": {
+          "output_size": [
+            null,
+            1
+          ]
+        }
+      },
+      "type": "torch.nn.AdaptiveAvgPool2d"
+    },
+    "feature_extraction": {
+      "config": {
+        "args": {
+          "input_channel": 1,
+          "output_channel": 512,
+          "variant": "DTRB"
+        }
+      },
+      "type": "DeepTextRecognition.ResNetModel"
+    },
+    "max": {
+      "config": {
+        "args": {
+          "dim": 2
+        }
+      },
+      "type": "torch.max"
+    },
+    "permute": {
+      "config": {
+        "args": {
+          "dims": [
+            0,
+            3,
+            1,
+            2
+          ]
+        }
+      },
+      "type": "torch.permute"
+    },
+    "prediction": {
+      "config": {
+        "args": {
+          "hidden_size": 256,
+          "input_size": 256,
+          "num_classes": 96
+        }
+      },
+      "type": "DeepTextRecognition.AttentionModel"
+    },
+    "processing": {
+      "config": {
+        "args": {
+          "channels_size": 1,
+          "image_size": [
+            32,
+            100
+          ],
+          "padding": "left"
+        }
+      },
+      "type": "DeepTextRecognition.ImageProcessor"
+    },
+    "sequence_modeling": {
+      "config": {
+        "args": {
+          "hidden_sizes": [
+            256,
+            256
+          ],
+          "input_size": 512,
+          "output_size": 256
+        }
+      },
+      "type": "DeepTextRecognition.BiLSTMModel"
+    },
+    "squeeze": {
+      "config": {
+        "args": {
+          "dim": 3
+        }
+      },
+      "type": "torch.squeeze"
+    },
+    "tokenizer": {
+      "config": {
+        "args": {
+          "characters": [
+            "0",
+            "1",
+            "2",
+            "3",
+            "4",
+            "5",
+            "6",
+            "7",
+            "8",
+            "9",
+            "a",
+            "b",
+            "c",
+            "d",
+            "e",
+            "f",
+            "g",
+            "h",
+            "i",
+            "j",
+            "k",
+            "l",
+            "m",
+            "n",
+            "o",
+            "p",
+            "q",
+            "r",
+            "s",
+            "t",
+            "u",
+            "v",
+            "w",
+            "x",
+            "y",
+            "z",
+            "A",
+            "B",
+            "C",
+            "D",
+            "E",
+            "F",
+            "G",
+            "H",
+            "I",
+            "J",
+            "K",
+            "L",
+            "M",
+            "N",
+            "O",
+            "P",
+            "Q",
+            "R",
+            "S",
+            "T",
+            "U",
+            "V",
+            "W",
+            "X",
+            "Y",
+            "Z",
+            "!",
+            "\"",
+            "#",
+            "$",
+            "%",
+            "&",
+            "'",
+            "(",
+            ")",
+            "*",
+            "+",
+            ",",
+            "-",
+            ".",
+            "/",
+            ":",
+            ";",
+            "<",
+            "=",
+            ">",
+            "?",
+            "@",
+            "[",
+            "]",
+            "^",
+            "_",
+            "`",
+            "{",
+            "|",
+            "}",
+            "~"
+          ],
+          "max_length": 25
+        }
+      },
+      "type": "DeepTextRecognition.AttentionTokenizer"
+    },
+    "transformation": {
+      "config": {
+        "args": {
+          "F": 20,
+          "I_channel_num": 1,
+          "I_r_size": [
+            32,
+            100
+          ],
+          "I_size": [
+            32,
+            100
+          ]
+        }
+      },
+      "type": "DeepTextRecognition.TPSModel"
+    }
+  },
+  "order": [
+    "processing",
+    "transformation",
+    "feature_extraction",
+    "permute",
+    "avg_pool",
+    "squeeze",
+    "sequence_modeling",
+    "prediction",
+    "max",
+    "tokenizer"
+  ],
+  "outputs": [
+    "tokenizer:labels"
+  ],
+  "routing": {
+    "avg_pool": {
+      "inputs": [
+        "permute:permuted_features"
+      ],
+      "outputs": [
+        "avg_pool:pooled_features"
+      ]
+    },
+    "feature_extraction": {
+      "inputs": [
+        "transformation:transformed_images"
+      ],
+      "outputs": [
+        "feature_extraction:extracted_features"
+      ]
+    },
+    "max": {
+      "inputs": [
+        "prediction:predictions"
+      ],
+      "outputs": [
+        "max:none",
+        "max:predictions"
+      ]
+    },
+    "permute": {
+      "inputs": [
+        "feature_extraction:extracted_features"
+      ],
+      "outputs": [
+        "permute:permuted_features"
+      ]
+    },
+    "prediction": {
+      "inputs": [
+        "sequence_modeling:modeled_features"
+      ],
+      "outputs": [
+        "prediction:predictions"
+      ]
+    },
+    "processing": {
+      "inputs": [
+        "images"
+      ],
+      "outputs": [
+        "processing:processed_images"
+      ]
+    },
+    "sequence_modeling": {
+      "inputs": [
+        "squeeze:squeezed_features"
+      ],
+      "outputs": [
+        "sequence_modeling:modeled_features"
+      ]
+    },
+    "squeeze": {
+      "inputs": [
+        "avg_pool:pooled_features"
+      ],
+      "outputs": [
+        "squeeze:squeezed_features"
+      ]
+    },
+    "tokenizer": {
+      "inputs": [
+        "max:predictions"
+      ],
+      "outputs": [
+        "tokenizer:labels"
+      ]
+    },
+    "transformation": {
+      "inputs": [
+        "processing:processed_images"
+      ],
+      "outputs": [
+        "transformation:transformed_images"
+      ]
+    }
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7bfcb7f7eb88c610bb7e0b3734d4c22a4f258c075ad2f39cea3adc1472ae9d6
+size 198952948