Upload folder using huggingface_hub

EasyOCR_model/apex_stats_detector.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e2efc7f6b123863756ab0b62f90550772f9facaae9caa78727dd9105376fc68
+size 15257702

EasyOCR_model/craft_mlt_25k.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a5efbfb48b4081100544e75e1e2b57f8de3d84f213004b14b85fd4b3748db17
+size 83152330

EasyOCR_user_network/apex_stats_detector.py

@@ -0,0 +1,101 @@
+import torch.nn as nn
+
+
+class BidirectionalLSTM(nn.Module):
+
+    def __init__(self, input_size, hidden_size, output_size):
+        super(BidirectionalLSTM, self).__init__()
+        self.rnn = nn.LSTM(
+            input_size, hidden_size, bidirectional=True, batch_first=True
+        )
+        self.linear = nn.Linear(hidden_size * 2, output_size)
+
+    def forward(self, input):
+        """
+        input : visual feature [batch_size x T x input_size]
+        output : contextual feature [batch_size x T x output_size]
+        """
+        try:  # multi gpu needs this
+            self.rnn.flatten_parameters()
+        except:  # quantization doesn't work with this
+            pass
+        recurrent, _ = self.rnn(
+            input
+        )  # batch_size x T x input_size -> batch_size x T x (2*hidden_size)
+        output = self.linear(recurrent)  # batch_size x T x output_size
+        return output
+
+
+class VGG_FeatureExtractor(nn.Module):
+
+    def __init__(self, input_channel, output_channel=256):
+        super(VGG_FeatureExtractor, self).__init__()
+        self.output_channel = [
+            int(output_channel / 8),
+            int(output_channel / 4),
+            int(output_channel / 2),
+            output_channel,
+        ]
+        self.ConvNet = nn.Sequential(
+            nn.Conv2d(input_channel, self.output_channel[0], 3, 1, 1),
+            nn.ReLU(True),
+            nn.MaxPool2d(2, 2),
+            nn.Conv2d(self.output_channel[0], self.output_channel[1], 3, 1, 1),
+            nn.ReLU(True),
+            nn.MaxPool2d(2, 2),
+            nn.Conv2d(self.output_channel[1], self.output_channel[2], 3, 1, 1),
+            nn.ReLU(True),
+            nn.Conv2d(self.output_channel[2], self.output_channel[2], 3, 1, 1),
+            nn.ReLU(True),
+            nn.MaxPool2d((2, 1), (2, 1)),
+            nn.Conv2d(
+                self.output_channel[2], self.output_channel[3], 3, 1, 1, bias=False
+            ),
+            nn.BatchNorm2d(self.output_channel[3]),
+            nn.ReLU(True),
+            nn.Conv2d(
+                self.output_channel[3], self.output_channel[3], 3, 1, 1, bias=False
+            ),
+            nn.BatchNorm2d(self.output_channel[3]),
+            nn.ReLU(True),
+            nn.MaxPool2d((2, 1), (2, 1)),
+            nn.Conv2d(self.output_channel[3], self.output_channel[3], 2, 1, 0),
+            nn.ReLU(True),
+        )
+
+    def forward(self, input):
+        return self.ConvNet(input)
+
+
+class Model(nn.Module):
+
+    def __init__(self, input_channel, output_channel, hidden_size, num_class):
+        super(Model, self).__init__()
+        """ FeatureExtraction """
+        self.FeatureExtraction = VGG_FeatureExtractor(input_channel, output_channel)
+        self.FeatureExtraction_output = output_channel
+        self.AdaptiveAvgPool = nn.AdaptiveAvgPool2d((None, 1))
+
+        """ Sequence modeling"""
+        self.SequenceModeling = nn.Sequential(
+            BidirectionalLSTM(self.FeatureExtraction_output, hidden_size, hidden_size),
+            BidirectionalLSTM(hidden_size, hidden_size, hidden_size),
+        )
+        self.SequenceModeling_output = hidden_size
+
+        """ Prediction """
+        self.Prediction = nn.Linear(self.SequenceModeling_output, num_class)
+
+    def forward(self, input, text):
+        """Feature extraction stage"""
+        visual_feature = self.FeatureExtraction(input)
+        visual_feature = self.AdaptiveAvgPool(visual_feature.permute(0, 3, 1, 2))
+        visual_feature = visual_feature.squeeze(3)
+
+        """ Sequence modeling stage """
+        contextual_feature = self.SequenceModeling(visual_feature)
+
+        """ Prediction stage """
+        prediction = self.Prediction(contextual_feature.contiguous())
+
+        return prediction

EasyOCR_user_network/apex_stats_detector.yaml

@@ -0,0 +1,7 @@
+network_params:
+  input_channel: 1
+  output_channel: 256
+  hidden_size: 256
+imgH: 64
+lang_list: ['en', 'ru']
+character_list: 0123456789!"#$%&'()*+,-./:;<=>?@[\]№_`{|}~ €₽ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyzАБВГДЕЁЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯабвгдеёжзийклмнопрстуфхцчшщъыьэюяЂђЃѓЄєІіЇїЈјЉљЊњЋћЌќЎўЏџҐґҒғҚқҮүҲҳҶҷӀӏӢӣӨөӮӯ

lgbm_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b78387f45c5b007b5e64a08606ba7a99c5669f381961eccede412295ff57da74
+size 13555124