Upload 19 files

README.md

@@ -1,12 +1,13 @@
 ---
-title: Piel Cancer Prueba
-emoji: 💻
-colorFrom: green
-colorTo: green
+title: Skin Cancer Diagnose
+emoji: 🐠
+colorFrom: yellow
+colorTo: indigo
 sdk: gradio
-sdk_version: 3.34.0
+sdk_version: 3.0.22
 app_file: app.py
 pinned: false
+license: gpl-3.0
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

ada_learn_malben.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:441760abd9a3a6b143917c68cf1709a1d96323fa334b4952009f50a34ddb57c2
+size 87548073

ada_learn_skin_norm2000.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:820252747a54e3e7494fdc86c998d1d67996cb31bde244ddd4260307e80dd819
+size 87739881

app.py

@@ -0,0 +1,173 @@
+
+import fastai
+import fastai.vision
+import PIL
+import gradio
+import matplotlib
+import numpy
+import pandas
+from fastai.vision.all import *
+#
+# create class
+class ADA_SKIN(object):
+  #
+  # initialize the object
+  def __init__(self, name="Wallaby",verbose=True,*args, **kwargs):
+    super(ADA_SKIN, self).__init__(*args, **kwargs)
+    self.author = "Duc Haba"
+    self.name = name
+    if (verbose):
+      self._ph()
+      self._pp("Hello from class", str(self.__class__) + " Class: " + str(self.__class__.__name__))
+      self._pp("Code name", self.name)
+      self._pp("Author is", self.author)
+      self._ph()
+    #
+    self.article = '<div><h3>Warning:</h3>Do NOT use this for any medical diagnosis.<br>' 
+    self.article += 'I am not a dermatologist, and NO dermatologist has endorsed it. '
+    self.article += 'This DL model is for my independent research. <br>Please refer to the GPL 3.0 for usage and license.'
+    self.article += '<h3>Citation:</h3><ul><li>'
+    self.article += 'Author/Dev: Duc Haba, 2022.</li>'
+    self.article += '<li><a target="_blank" href="https://linkedin.com/in/duchaba">https://linkedin.com/in/duchaba</a></li>'
+    self.article += '<li>The training dataset are from the International Skin Imaging Collaboration (ISIC)</li>'
+    self.article += '<li>The Skin Cancer Identification are from 3 seperate datasets.</li>'
+    self.article += '<ol>'
+    self.article += '<li>https://www.kaggle.com/datasets/surajghuwalewala/ham1000-segmentation-and-classification</li>'
+    self.article += '<li>https://www.kaggle.com/datasets/andrewmvd/isic-2019</li>'
+    self.article += '<li>https://www.kaggle.com/datasets/jnegrini/skin-lesions-act-keratosis-and-melanoma</li>'        
+    self.article += '<ul><li>'
+    self.article += 'The Malignant versus Benign dataset</li>'
+    self.article += '<ol><li>https://www.kaggle.com/datasets/fanconic/skin-cancer-malignant-vs-benign</li>'
+    self.article += '</ol></ul>'
+    self.article += '<h3>Articles:</h3><ul>'
+    self.article += '<li><a target="_blank" href="https://www.linkedin.com/pulse/skin-cancer-diagnose-using-deep-learning-duc-haba/">'
+    self.article += '"Skin Cancer Diagnose"</a> on LinkedIn, on <a target="_blank" href='
+    self.article += '"https://www.linkedin.com/pulse/skin-cancer-diagnose-using-deep-learning-duc-haba/">Medium.</a></li>'
+    self.article += '</ul>'  
+    self.article += '<h3>Example Images: (left to right)</h3><ol>'
+    self.article += '<li>Bowen Disease (AKIEC)</li>'
+    self.article += '<li>Basal Cell Carcinoma</li>'
+    self.article += '<li>Benign Keratosis-like Lesions</li>'
+    self.article += '<li>Dermatofibroma</li>'
+    self.article += '<li>Melanoma</li>'
+    self.article += '<li>Melanocytic Nevi</li>'
+    self.article += '<li>Squamous Cell Carcinoma</li>'   
+    self.article += '<li>Vascular Lesions</li>' 
+    self.article += '<li>Benign</li>' 
+    self.article += '<li>Benign 2</li></ol>'         
+    self.article += '<h3>Train Result:</h3><ul>'
+    self.article += '<li>Skin Cancer Classificaiton: F1-Score, Precision, and Recall Graph</li>'
+    self.article += '<li><img src="file/ada_f1_skin.png" alt="F1-Score, Precision, and Recall Graph" width="640"</li>'
+    self.article += '<li>Skin Cancer Malignant or Benign: F1-Score, Precision, and Recall Graph</li>'
+    self.article += '<li><img src="file/ada_f1_skin_be.png" alt="F1-Score, Precision, and Recall Graph" width="640"</li>'    
+    self.article += '</ul>'
+    self.article += '<h3>Dev Stack:</h3><ul>'
+    self.article += '<li>Jupyter Notebook, Python, Pandas, Matplotlib, Sklearn</li>'
+    self.article += '<li>Fast.ai, PyTorch</li>'
+    self.article += '</ul>'
+    self.article += '<h3>Licenses:</h3><ul>'
+    self.article += '<li><a target="_blank" href="https://www.gnu.org/licenses/gpl-3.0.txt">GNU GPL 3.0</a></li>'        
+    self.article += '</ul></div>'
+    self.examples = ['akiec1.jpg','bcc1.jpg','bkl1.jpg','df1.jpg','mel1.jpg',
+      'nevi1.jpg','scc1.jpg','vl1.jpg','benign1.jpg','benign3.jpg']
+    self.title = "Skin Cancer Diagnose"
+    return
+  # 
+  # pretty print output name-value line
+  def _pp(self, a, b):
+    print("%34s : %s" % (str(a), str(b)))
+    return
+  #
+  # pretty print the header or footer lines
+  def _ph(self):
+    print("-" * 34, ":", "-" * 34)
+    return
+  # 
+  def _predict_image(self,img,cat):
+    pred,idx,probs = learn.predict(img)
+    return dict(zip(cat, map(float,probs)))
+  #
+  def _predict_image2(self,img,cat):
+    pred,idx,probs = learn2.predict(img)
+    return dict(zip(cat, map(float,probs)))
+  #  
+  def _draw_pred(self,df_pred, df2):
+    canvas, pic = matplotlib.pyplot.subplots(1,2, figsize=(12,6))
+    ti = df_pred["vocab"].head(3).values
+    ti2 = df2["vocab"].head(2).values
+    # special case
+    #if (matplotlib.__version__) >= "3.5.2":
+    try:
+      df_pred["pred"].head(3).plot(ax=pic[0],kind="pie",
+        cmap="Set2",labels=ti, explode=(0.02,0,0),
+        wedgeprops=dict(width=.4),
+        normalize=False)
+      df2["pred"].head(2).plot(ax=pic[1],kind="pie",
+        colors=["cornflowerblue","darkorange"],labels=ti2, explode=(0.02,0),
+        wedgeprops=dict(width=.4),
+        normalize=False)      
+    except:
+      df_pred["pred"].head(3).plot(ax=pic[0],kind="pie",
+        cmap="Set2",labels=ti, explode=(0.02,0,0),
+        wedgeprops=dict(width=.4))
+      df2["pred"].head(2).plot(ax=pic[1],kind="pie",
+        colors=["cornflowerblue","darkorange"],labels=ti2, explode=(0.02,0),
+        wedgeprops=dict(width=.4))
+    t = str(ti[0]) + ": " + str(numpy.round(df_pred.head(1).pred.values[0]*100, 2)) + "% Certainty"
+    pic[0].set_title(t,fontsize=14.0, fontweight="bold")
+    pic[0].axis('off')
+    pic[0].legend(ti, loc="lower right",title="Skin Cancers: Top 3")
+    #
+    k0 = numpy.round(df2.head(1).pred.values[0]*100, 2)
+    k1 = numpy.round(df2.tail(1).pred.values[0]*100, 2)
+    if (k0 > k1):
+      t2 = str(ti2[0]) + ": " + str(k0) + "% Certainty"
+    else:
+      t2 = str(ti2[1]) + ": " + str(k1) + "% Certainty"
+    pic[1].set_title(t2,fontsize=14.0, fontweight="bold")
+    pic[1].axis('off')
+    pic[1].legend(ti2, loc="lower right",title="Skin Cancers:")
+    #
+    # # draw circle
+    # centre_circle = matplotlib.pyplot.Circle((0, 0), 0.6, fc='white')
+    # p = matplotlib.pyplot.gcf()
+    # # Adding Circle in Pie chart
+    # p.gca().add_artist(centre_circle)
+    #
+    #p=plt.gcf()
+    #p.gca().add_artist(my_circle)
+    #
+    canvas.tight_layout()
+    return canvas
+  #
+  def predict_donut(self,img):
+    d = self._predict_image(img,self.categories)
+    df = pandas.DataFrame(d, index=[0])
+    df = df.transpose().reset_index()
+    df.columns = ["vocab", "pred"]
+    df.sort_values("pred", inplace=True,ascending=False, ignore_index=True)
+    #
+    d2 = self._predict_image2(img,self.categories2)
+    df2 = pandas.DataFrame(d2, index=[0])
+    df2 = df2.transpose().reset_index()
+    df2.columns = ["vocab", "pred"]
+    #
+    canvas = self._draw_pred(df,df2)
+    return canvas
+#
+maxi = ADA_SKIN(verbose=False)
+#
+learn = fastai.learner.load_learner('ada_learn_skin_norm2000.pkl')
+learn2 = fastai.learner.load_learner('ada_learn_malben.pkl')
+maxi.categories = learn.dls.vocab
+maxi.categories2 = learn2.dls.vocab
+hf_image = gradio.inputs.Image(shape=(192, 192))
+hf_label = gradio.outputs.Label()
+intf = gradio.Interface(fn=maxi.predict_donut, 
+  inputs=hf_image, 
+  outputs=["plot"], 
+  examples=maxi.examples,
+  title=maxi.title,
+  live=True,
+  article=maxi.article)
+intf.launch(inline=False,share=True)

gitattributes.txt

@@ -0,0 +1,29 @@
+*.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
+*.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
+*.wasm 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
+ada_learn_malben.pkl filter=lfs diff=lfs merge=lfs -text
+ada_learn_skin_norm2000.pkl filter=lfs diff=lfs merge=lfs -text

requirements.txt

@@ -0,0 +1,2 @@
+fastai>=2.6.3
+pandas>=1.4.1