Spaces:
Sleeping
Sleeping
Commit
·
c1169cd
1
Parent(s):
04e7d25
Update model.py
Browse files
model.py
CHANGED
|
@@ -7,7 +7,7 @@ def classify(img):
|
|
| 7 |
im = img
|
| 8 |
lt = ["other","Bone","Brain","eye","kidney","chest","skin"]
|
| 9 |
im = cv2.resize(im,(52,52))
|
| 10 |
-
model = tf.keras.models.load_model("all-in-one.h5")
|
| 11 |
result = model.predict(np.array([im]))
|
| 12 |
a = np.argmax(result)
|
| 13 |
c=""
|
|
@@ -31,7 +31,7 @@ def classify(img):
|
|
| 31 |
|
| 32 |
def bone_net(img):
|
| 33 |
img = cv2.resize(img,(224,224))
|
| 34 |
-
model = tf.keras.models.load_model("Fracture_detection.h5")
|
| 35 |
result = model.predict(np.array([img]))
|
| 36 |
op=""
|
| 37 |
if result[0]<0.5:
|
|
@@ -43,7 +43,7 @@ def bone_net(img):
|
|
| 43 |
def brain_net(img):
|
| 44 |
lt = ['pituitary', 'notumor', 'meningioma', 'glioma']
|
| 45 |
img = cv2.resize(img,(224,224))
|
| 46 |
-
model = tf.keras.models.load_model("model_brain_tumur.h5")
|
| 47 |
result = model.predict(np.array([img]))
|
| 48 |
ans = np.argmax(result)
|
| 49 |
return lt[ans]
|
|
@@ -51,7 +51,7 @@ def brain_net(img):
|
|
| 51 |
def chest_net(img):
|
| 52 |
lt = ['PNEUMONIA', 'NORMAL']
|
| 53 |
img = cv2.resize(img,(224,224))
|
| 54 |
-
model = tf.keras.models.load_model("chest_cls_model.h5")
|
| 55 |
result = model.predict(np.array([img]))
|
| 56 |
ans = np.argmax(result)
|
| 57 |
return lt[ans]
|
|
@@ -59,7 +59,7 @@ def chest_net(img):
|
|
| 59 |
def Eye_net(img):
|
| 60 |
lt = ['glaucoma', 'normal', 'diabetic_retinopathy', 'cataract']
|
| 61 |
img = cv2.resize(img,(224,224))
|
| 62 |
-
model = tf.keras.models.load_model("Eye_diseases.h5")
|
| 63 |
result = model.predict(np.array([img]))
|
| 64 |
ans = np.argmax(result)
|
| 65 |
return lt[ans]
|
|
@@ -67,7 +67,7 @@ def Eye_net(img):
|
|
| 67 |
def kidney_net(img):
|
| 68 |
lt = ['Cyst', 'Tumor', 'Stone', 'Normal']
|
| 69 |
img = cv2.resize(img,(224,224))
|
| 70 |
-
model = tf.keras.models.load_model("kidney_stone.h5")
|
| 71 |
result = model.predict(np.array([img]))
|
| 72 |
ans = np.argmax(result)
|
| 73 |
return lt[ans]
|
|
@@ -75,7 +75,7 @@ def kidney_net(img):
|
|
| 75 |
def skin_net(img):
|
| 76 |
lt = ['pigmented benign keratosis', 'melanoma', 'vascular lesion', 'actinic keratosis', 'squamous cell carcinoma', 'basal cell carcinoma', 'seborrheic keratosis', 'dermatofibroma', 'nevus']
|
| 77 |
img = cv2.resize(img,(224,224))
|
| 78 |
-
model = tf.keras.models.load_model("skin_cancer.h5")
|
| 79 |
result = model.predict(np.array([img]))
|
| 80 |
ans = np.argmax(result)
|
| 81 |
return lt[ans]
|
|
|
|
| 7 |
im = img
|
| 8 |
lt = ["other","Bone","Brain","eye","kidney","chest","skin"]
|
| 9 |
im = cv2.resize(im,(52,52))
|
| 10 |
+
model = tf.keras.models.load_model("all-in-one.h5",compile=False)
|
| 11 |
result = model.predict(np.array([im]))
|
| 12 |
a = np.argmax(result)
|
| 13 |
c=""
|
|
|
|
| 31 |
|
| 32 |
def bone_net(img):
|
| 33 |
img = cv2.resize(img,(224,224))
|
| 34 |
+
model = tf.keras.models.load_model("Fracture_detection.h5",compile=False)
|
| 35 |
result = model.predict(np.array([img]))
|
| 36 |
op=""
|
| 37 |
if result[0]<0.5:
|
|
|
|
| 43 |
def brain_net(img):
|
| 44 |
lt = ['pituitary', 'notumor', 'meningioma', 'glioma']
|
| 45 |
img = cv2.resize(img,(224,224))
|
| 46 |
+
model = tf.keras.models.load_model("model_brain_tumur.h5",compile=False)
|
| 47 |
result = model.predict(np.array([img]))
|
| 48 |
ans = np.argmax(result)
|
| 49 |
return lt[ans]
|
|
|
|
| 51 |
def chest_net(img):
|
| 52 |
lt = ['PNEUMONIA', 'NORMAL']
|
| 53 |
img = cv2.resize(img,(224,224))
|
| 54 |
+
model = tf.keras.models.load_model("chest_cls_model.h5",compile=False)
|
| 55 |
result = model.predict(np.array([img]))
|
| 56 |
ans = np.argmax(result)
|
| 57 |
return lt[ans]
|
|
|
|
| 59 |
def Eye_net(img):
|
| 60 |
lt = ['glaucoma', 'normal', 'diabetic_retinopathy', 'cataract']
|
| 61 |
img = cv2.resize(img,(224,224))
|
| 62 |
+
model = tf.keras.models.load_model("Eye_diseases.h5",compile=False)
|
| 63 |
result = model.predict(np.array([img]))
|
| 64 |
ans = np.argmax(result)
|
| 65 |
return lt[ans]
|
|
|
|
| 67 |
def kidney_net(img):
|
| 68 |
lt = ['Cyst', 'Tumor', 'Stone', 'Normal']
|
| 69 |
img = cv2.resize(img,(224,224))
|
| 70 |
+
model = tf.keras.models.load_model("kidney_stone.h5",compile=False)
|
| 71 |
result = model.predict(np.array([img]))
|
| 72 |
ans = np.argmax(result)
|
| 73 |
return lt[ans]
|
|
|
|
| 75 |
def skin_net(img):
|
| 76 |
lt = ['pigmented benign keratosis', 'melanoma', 'vascular lesion', 'actinic keratosis', 'squamous cell carcinoma', 'basal cell carcinoma', 'seborrheic keratosis', 'dermatofibroma', 'nevus']
|
| 77 |
img = cv2.resize(img,(224,224))
|
| 78 |
+
model = tf.keras.models.load_model("skin_cancer.h5",compile=False)
|
| 79 |
result = model.predict(np.array([img]))
|
| 80 |
ans = np.argmax(result)
|
| 81 |
return lt[ans]
|