Duplicate from keras-io/ocr-for-captcha

Co-authored-by: Anurag Singh <[email protected]>

.gitattributes

@@ -0,0 +1,27 @@
+*.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
+*.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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,46 @@
+---
+title: OCR For Captcha
+emoji: 🤖
+colorFrom: yellow
+colorTo: red
+sdk: gradio
+app_file: app.py
+pinned: false
+duplicated_from: keras-io/ocr-for-captcha
+---
+
+# Configuration
+
+`title`: _string_
+Display title for the Space
+
+`emoji`: _string_
+Space emoji (emoji-only character allowed)
+
+`colorFrom`: _string_
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`colorTo`: _string_
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`sdk`: _string_
+Can be either `gradio`, `streamlit`, or `static`
+
+`sdk_version` : _string_
+Only applicable for `streamlit` SDK.  
+See [doc](https://hf.co/docs/hub/spaces) for more info on supported versions.
+
+`app_file`: _string_
+Path to your main application file (which contains either `gradio` or `streamlit` Python code, or `static` html code).
+Path is relative to the root of the repository.
+
+`models`: _List[string]_
+HF model IDs (like "gpt2" or "deepset/roberta-base-squad2") used in the Space.
+Will be parsed automatically from your code if not specified here.
+
+`datasets`: _List[string]_
+HF dataset IDs (like "common_voice" or "oscar-corpus/OSCAR-2109") used in the Space.
+Will be parsed automatically from your code if not specified here.
+
+`pinned`: _boolean_
+Whether the Space stays on top of your list.

app.py

@@ -0,0 +1,70 @@
+import tensorflow as tf
+from tensorflow import keras
+from tensorflow.keras import layers
+
+from huggingface_hub import from_pretrained_keras
+
+import numpy as np
+import gradio as gr
+
+max_length = 5
+img_width = 200
+img_height = 50
+
+model = from_pretrained_keras("keras-io/ocr-for-captcha", compile=False)
+
+prediction_model = keras.models.Model(
+    model.get_layer(name="image").input, model.get_layer(name="dense2").output
+)
+
+with open("vocab.txt", "r") as f:
+    vocab = f.read().splitlines()
+
+# Mapping integers back to original characters
+num_to_char = layers.StringLookup(
+    vocabulary=vocab, mask_token=None, invert=True
+)
+
+def decode_batch_predictions(pred):
+    input_len = np.ones(pred.shape[0]) * pred.shape[1]
+    # Use greedy search. For complex tasks, you can use beam search
+    results = keras.backend.ctc_decode(pred, input_length=input_len, greedy=True)[0][0][
+        :, :max_length
+    ]
+    # Iterate over the results and get back the text
+    output_text = []
+    for res in results:
+        res = tf.strings.reduce_join(num_to_char(res)).numpy().decode("utf-8")
+        output_text.append(res)
+    return output_text
+
+def classify_image(img_path):
+    # 1. Read image
+    img = tf.io.read_file(img_path)
+    # 2. Decode and convert to grayscale
+    img = tf.io.decode_png(img, channels=1)
+    # 3. Convert to float32 in [0, 1] range
+    img = tf.image.convert_image_dtype(img, tf.float32)
+    # 4. Resize to the desired size
+    img = tf.image.resize(img, [img_height, img_width])
+    # 5. Transpose the image because we want the time
+    # dimension to correspond to the width of the image.
+    img = tf.transpose(img, perm=[1, 0, 2])
+    img = tf.expand_dims(img, axis=0)
+    preds = prediction_model.predict(img)
+    pred_text = decode_batch_predictions(preds)
+    return pred_text[0]
+  
+image = gr.inputs.Image(type='filepath')
+text = gr.outputs.Textbox()
+
+iface = gr.Interface(classify_image,image,text,
+  title="OCR for CAPTCHA",
+	description = "Keras Implementation of OCR model for reading captcha 🤖🦹🏻",
+        article = "Author: <a href=\"https://huggingface.co/anuragshas\">Anurag Singh</a>. Based on the keras example from <a href=\"https://keras.io/examples/vision/captcha_ocr/\">A_K_Nain</a>",
+        examples = ["dd764.png","3p4nn.png"]
+)
+
+
+iface.launch()
+

requirements.txt

@@ -0,0 +1 @@
+tensorflow>2.6

vocab.txt

@@ -0,0 +1,20 @@
+[UNK]
+8
+6
+m
+x
+d
+y
+w
+2
+7
+n
+g
+5
+c
+f
+p
+e
+3
+4
+b