upl base codes

.gitattributes

@@ -1,35 +1,34 @@
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
 *.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
 *.ftz filter=lfs diff=lfs merge=lfs -text
 *.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,3 @@
+__pycache__/*
+*.pth
+flagged/*

README.md

@@ -1,13 +1,25 @@
 ---
-title: SVHN Recognition
-emoji: ⚡
-colorFrom: yellow
-colorTo: purple
-sdk: gradio
-sdk_version: 4.12.0
-app_file: app.py
-pinned: false
-license: mit
----
+# 详细文档见https://modelscope.cn/docs/%E5%88%9B%E7%A9%BA%E9%97%B4%E5%8D%A1%E7%89%87
+domain: #领域：cv/nlp/audio/multi-modal/AutoML
+# - cv
+tags: #自定义标签
+-
+datasets: #关联数据集
+  evaluation:
+  #- damotest/beans
+  test:
+  #- damotest/squad
+  train:
+  #- modelscope/coco_2014_caption
+models: #关联模型
+#- damo/speech_charctc_kws_phone-xiaoyunxiaoyun
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+## 启动文件(若SDK为Gradio/Streamlit，默认为app.py, 若为Static HTML, 默认为index.html)
+# deployspec:
+#   entry_file: app.py
+license: MIT License
+---
+#### Clone with HTTP
+```bash
+ git clone https://www.modelscope.cn/studios/MuGeminorum/SVHN-Recognition.git
+```

app.py

@@ -0,0 +1,99 @@
+import os
+import torch
+import requests
+import gradio as gr
+from tqdm import tqdm
+from PIL import Image
+from model import Model
+from torchvision import transforms
+import warnings
+warnings.filterwarnings("ignore")
+
+
+def download_model(url="https://www.modelscope.cn/api/v1/models/MuGeminorum/SVHN-Recognition/repo?Revision=master&FilePath=model-122000.pth", local_path="model-122000.pth"):
+    # Check if the file exists
+    if not os.path.exists(local_path):
+        print(f"Downloading file from {url}...")
+        # Make a request to the URL
+        response = requests.get(url, stream=True)
+
+        # Get the total file size in bytes
+        total_size = int(response.headers.get('content-length', 0))
+
+        # Initialize the tqdm progress bar
+        progress_bar = tqdm(total=total_size, unit='B', unit_scale=True)
+
+        # Open a local file with write-binary mode
+        with open(local_path, 'wb') as file:
+            for data in response.iter_content(chunk_size=1024):
+                # Update the progress bar
+                progress_bar.update(len(data))
+
+                # Write the data to the local file
+                file.write(data)
+
+        # Close the progress bar
+        progress_bar.close()
+
+        print("Download completed.")
+
+
+def _infer(path_to_checkpoint_file, path_to_input_image):
+    model = Model()
+    model.restore(path_to_checkpoint_file)
+    model.cuda()
+    outstr = ''
+
+    with torch.no_grad():
+        transform = transforms.Compose([
+            transforms.Resize([64, 64]),
+            transforms.CenterCrop([54, 54]),
+            transforms.ToTensor(),
+            transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])
+        ])
+
+        image = Image.open(path_to_input_image)
+        image = image.convert('RGB')
+        image = transform(image)
+        images = image.unsqueeze(dim=0).cuda()
+
+        length_logits, digit1_logits, digit2_logits, digit3_logits, digit4_logits, digit5_logits = model.eval()(images)
+
+        length_prediction = length_logits.max(1)[1]
+        digit1_prediction = digit1_logits.max(1)[1]
+        digit2_prediction = digit2_logits.max(1)[1]
+        digit3_prediction = digit3_logits.max(1)[1]
+        digit4_prediction = digit4_logits.max(1)[1]
+        digit5_prediction = digit5_logits.max(1)[1]
+
+        output = [
+            digit1_prediction.item(),
+            digit2_prediction.item(),
+            digit3_prediction.item(),
+            digit4_prediction.item(),
+            digit5_prediction.item()
+        ]
+
+        for i in range(length_prediction.item()):
+            outstr += str(output[i])
+
+    return outstr
+
+
+def inference(image_path, weight_path="model-122000.pth"):
+    download_model()
+
+    if not image_path:
+        image_path = '457.png'
+
+    return _infer(weight_path, image_path)
+
+
+if __name__ == '__main__':
+    iface = gr.Interface(
+        fn=inference,
+        inputs=gr.Image(type='filepath'),
+        outputs=gr.Textbox()
+    )
+
+    iface.launch()

model.py

@@ -0,0 +1,178 @@
+import os
+import glob
+import torch
+import torch.jit
+import torch.nn as nn
+
+
+class Model(torch.jit.ScriptModule):
+    CHECKPOINT_FILENAME_PATTERN = 'model-{}.pth'
+
+    __constants__ = [
+        '_hidden1', '_hidden2', '_hidden3', '_hidden4', '_hidden5', '_hidden6',
+        '_hidden7', '_hidden8', '_hidden9', '_hidden10', '_features', '_classifier',
+        '_digit_length', '_digit1', '_digit2', '_digit3', '_digit4', '_digit5'
+    ]
+
+    def __init__(self):
+        super(Model, self).__init__()
+
+        self._hidden1 = nn.Sequential(
+            nn.Conv2d(
+                in_channels=3,
+                out_channels=48,
+                kernel_size=5,
+                padding=2
+            ),
+            nn.BatchNorm2d(num_features=48),
+            nn.ReLU(),
+            nn.MaxPool2d(kernel_size=2, stride=2, padding=1),
+            nn.Dropout(0.2)
+        )
+        self._hidden2 = nn.Sequential(
+            nn.Conv2d(
+                in_channels=48,
+                out_channels=64,
+                kernel_size=5,
+                padding=2
+            ),
+            nn.BatchNorm2d(num_features=64),
+            nn.ReLU(),
+            nn.MaxPool2d(kernel_size=2, stride=1, padding=1),
+            nn.Dropout(0.2)
+        )
+        self._hidden3 = nn.Sequential(
+            nn.Conv2d(
+                in_channels=64,
+                out_channels=128,
+                kernel_size=5,
+                padding=2
+            ),
+            nn.BatchNorm2d(num_features=128),
+            nn.ReLU(),
+            nn.MaxPool2d(kernel_size=2, stride=2, padding=1),
+            nn.Dropout(0.2)
+        )
+        self._hidden4 = nn.Sequential(
+            nn.Conv2d(
+                in_channels=128,
+                out_channels=160,
+                kernel_size=5,
+                padding=2
+            ),
+            nn.BatchNorm2d(num_features=160),
+            nn.ReLU(),
+            nn.MaxPool2d(kernel_size=2, stride=1, padding=1),
+            nn.Dropout(0.2)
+        )
+        self._hidden5 = nn.Sequential(
+            nn.Conv2d(
+                in_channels=160,
+                out_channels=192,
+                kernel_size=5,
+                padding=2
+            ),
+            nn.BatchNorm2d(num_features=192),
+            nn.ReLU(),
+            nn.MaxPool2d(kernel_size=2, stride=2, padding=1),
+            nn.Dropout(0.2)
+        )
+        self._hidden6 = nn.Sequential(
+            nn.Conv2d(
+                in_channels=192,
+                out_channels=192,
+                kernel_size=5,
+                padding=2
+            ),
+            nn.BatchNorm2d(num_features=192),
+            nn.ReLU(),
+            nn.MaxPool2d(kernel_size=2, stride=1, padding=1),
+            nn.Dropout(0.2)
+        )
+        self._hidden7 = nn.Sequential(
+            nn.Conv2d(
+                in_channels=192,
+                out_channels=192,
+                kernel_size=5,
+                padding=2
+            ),
+            nn.BatchNorm2d(num_features=192),
+            nn.ReLU(),
+            nn.MaxPool2d(kernel_size=2, stride=2, padding=1),
+            nn.Dropout(0.2)
+        )
+        self._hidden8 = nn.Sequential(
+            nn.Conv2d(
+                in_channels=192,
+                out_channels=192,
+                kernel_size=5,
+                padding=2
+            ),
+            nn.BatchNorm2d(num_features=192),
+            nn.ReLU(),
+            nn.MaxPool2d(kernel_size=2, stride=1, padding=1),
+            nn.Dropout(0.2)
+        )
+        self._hidden9 = nn.Sequential(
+            nn.Linear(192 * 7 * 7, 3072),
+            nn.ReLU()
+        )
+        self._hidden10 = nn.Sequential(
+            nn.Linear(3072, 3072),
+            nn.ReLU()
+        )
+
+        self._digit_length = nn.Sequential(nn.Linear(3072, 7))
+        self._digit1 = nn.Sequential(nn.Linear(3072, 11))
+        self._digit2 = nn.Sequential(nn.Linear(3072, 11))
+        self._digit3 = nn.Sequential(nn.Linear(3072, 11))
+        self._digit4 = nn.Sequential(nn.Linear(3072, 11))
+        self._digit5 = nn.Sequential(nn.Linear(3072, 11))
+
+    @torch.jit.script_method
+    def forward(self, x):
+        x = self._hidden1(x)
+        x = self._hidden2(x)
+        x = self._hidden3(x)
+        x = self._hidden4(x)
+        x = self._hidden5(x)
+        x = self._hidden6(x)
+        x = self._hidden7(x)
+        x = self._hidden8(x)
+        x = x.view(x.size(0), 192 * 7 * 7)
+        x = self._hidden9(x)
+        x = self._hidden10(x)
+
+        length_logits = self._digit_length(x)
+        digit1_logits = self._digit1(x)
+        digit2_logits = self._digit2(x)
+        digit3_logits = self._digit3(x)
+        digit4_logits = self._digit4(x)
+        digit5_logits = self._digit5(x)
+
+        return length_logits, digit1_logits, digit2_logits, digit3_logits, digit4_logits, digit5_logits
+
+    def store(self, path_to_dir, step, maximum=5):
+        path_to_models = glob.glob(os.path.join(
+            path_to_dir, Model.CHECKPOINT_FILENAME_PATTERN.format('*')))
+        if len(path_to_models) == maximum:
+            min_step = min(
+                [int(path_to_model.split('\\')[-1][6:-4])
+                 for path_to_model in path_to_models]
+            )
+            path_to_min_step_model = os.path.join(
+                path_to_dir,
+                Model.CHECKPOINT_FILENAME_PATTERN.format(min_step)
+            )
+            os.remove(path_to_min_step_model)
+
+        path_to_checkpoint_file = os.path.join(
+            path_to_dir, Model.CHECKPOINT_FILENAME_PATTERN.format(step)
+        )
+        torch.save(self.state_dict(), path_to_checkpoint_file)
+        return path_to_checkpoint_file
+
+    def restore(self, path_to_checkpoint_file):
+        self.load_state_dict(torch.load(path_to_checkpoint_file))
+        step = int(path_to_checkpoint_file.split('\\')[-1][6:-4])
+        return step

requirements.txt

@@ -0,0 +1,4 @@
+gradio
+pillow
+torch
+torchvision