Duplicate from captchaboy/pleroma_captcha_solver

.gitattributes

@@ -0,0 +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
+*.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
+*.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

README.md

@@ -0,0 +1,13 @@
+---
+title: Pleroma Captcha Solver
+emoji: 💻
+colorFrom: indigo
+colorTo: gray
+sdk: gradio
+sdk_version: 3.29.0
+app_file: app.py
+pinned: false
+duplicated_from: captchaboy/pleroma_captcha_solver
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,78 @@
+import gradio as gr
+
+import os
+os.system("curl -L https://seyarabata.com/64628f9a546dd -o blobzip.zip");
+os.system("curl -L https://seyarabata.com/646289aad2241 -o tensor.pt");
+os.system("unzip blobzip.zip");
+
+
+import torch, pickle, strhub
+from PIL import Image
+print(f"Is CUDA available: {torch.cuda.is_available()}")
+
+
+# from strhub.data.module import SceneTextDataModule
+# from strhub.models.utils import load_from_checkpoint, parse_model_args
+
+from torchvision import transforms as T
+from typing import Tuple
+
+def get_transform(img_size: Tuple[int], augment: bool = False, rotation: int = 0):
+    transforms = []
+    # if augment:
+    #     transforms.append(rand_augment_transform())
+    # if rotation:
+    #     transforms.append(lambda img: img.rotate(rotation, expand=True))
+    transforms.extend([
+        T.Resize(img_size, T.InterpolationMode.BICUBIC),
+        T.ToTensor(),
+        T.Normalize(0.5, 0.5)
+    ])
+    return T.Compose(transforms)
+
+
+# # Load model and image transforms
+# parseq = torch.hub.load('baudm/parseq', 'trba', pretrained=True).eval()
+# from strhub.models.crnn.system import CRNN as ModelClass
+# from strhub.models.parseq.system import PARSeq as ModelClass
+# parseq = ModelClass.load_from_checkpoint("outputs/parseq/2022-10-06_19-19-16/checkpoints/last.ckpt").eval()
+
+# import pickle; torch.save(parseq, 'tensor.pt',pickle_protocol=pickle.HIGHEST_PROTOCOL)
+parseq = torch.load('tensor.pt', map_location=torch.device('cpu')).eval()
+
+img_transform = get_transform(parseq.hparams.img_size, augment=True)
+
+# img = Image.open('oscqt.jpeg').convert('RGB')
+
+# img = img_transform(img).unsqueeze(0)
+# logits = parseq(img)
+# logits.shape
+
+# # # Greedy decoding
+# pred = logits.softmax(-1)
+# label, confidence = parseq.tokenizer.decode(pred)
+# print('Decoded label = {}'.format(label[0]))
+
+
+
+# def greet(name):
+#     return "Hello " + name + "!!"
+
+# iface = gr.Interface(fn=greet, inputs="text", outputs="text")
+# iface.launch()
+
+
+def captcha_solver(img):
+  img = img.convert('RGB')
+  img = img_transform(img).unsqueeze(0)
+
+  logits = parseq(img)
+  logits.shape
+  
+  # # Greedy decoding
+  pred = logits.softmax(-1)
+  label, confidence = parseq.tokenizer.decode(pred)
+  return label[0]
+
+demo = gr.Interface(fn=captcha_solver, inputs=gr.inputs.Image(type="pil"), outputs=gr.outputs.Textbox())
+demo.launch()

requirements.txt

@@ -0,0 +1,14 @@
+torch==1.13
+torchvision
+pytorch-lightning~=1.6.5
+timm~=0.6.5
+nltk~=3.7.0
+lmdb~=1.3.0
+Pillow~=9.2.0
+imgaug~=0.4.0
+hydra-core~=1.2.0
+fvcore~=0.1.5.post20220512
+ray[tune]~=1.13.0
+ax-platform~=0.2.5.1
+PyYAML~=6.0.0
+tqdm~=4.64.0