|
16 | 16 | data = [] |
17 | 17 | labels = [] |
18 | 18 |
|
19 | | -Parasitized = os.listdir("../input/cell-images-for-detecting-malaria/cell_images/Parasitized/") |
| 19 | +Parasitized = os.listdir("../input/malaria/cell_images/Parasitized/") |
20 | 20 |
|
21 | 21 | for a in Parasitized: |
22 | 22 | try: |
23 | | - imageP = cv2.imread("../input/cell-images-for-detecting-malaria/cell_images/Parasitized/" + a) |
| 23 | + imageP = cv2.imread("../input/malaria/cell_images/Parasitized/" + a) |
24 | 24 | image_from_arrayP = Image.fromarray(imageP, 'RGB') |
25 | 25 | size_imageP = image_from_arrayP.resize((36, 36)) |
26 | 26 | data.append(np.array(size_imageP)) |
27 | 27 | labels.append(0) |
28 | 28 | except AttributeError: |
29 | 29 | print("") |
30 | 30 |
|
31 | | -Uninfected = os.listdir("../input/cell-images-for-detecting-malaria/cell_images/Uninfected/") |
| 31 | +Uninfected = os.listdir("../input/malaria/cell_images/Uninfected/") |
32 | 32 |
|
33 | 33 | for b in Uninfected: |
34 | 34 | try: |
35 | | - imageU = cv2.imread("../input/cell-images-for-detecting-malaria/cell_images/Uninfected/" + b) |
| 35 | + imageU = cv2.imread("../input/malaria/cell_images/Uninfected/" + b) |
36 | 36 | image_from_arrayU = Image.fromarray(imageU, 'RGB') |
37 | 37 | size_imageU = image_from_arrayU.resize((36, 36)) |
38 | 38 | data.append(np.array(size_imageU)) |
|
54 | 54 | # Splitting the dataset into the Training set and Test set |
55 | 55 | X_train, X_valid, y_train, y_valid = train_test_split(data2, labels2, test_size=0.2, random_state=0) |
56 | 56 | X_trainF = X_train.astype('float32') |
57 | | -X_validF = X_valid.astype('float32') |
58 | | -# One Hot Encoding |
| 57 | +X_validF = X_valid.astype('float32') |
59 | 58 | y_trainF = to_categorical(y_train) |
60 | 59 | y_validF = to_categorical(y_valid) |
61 | 60 |
|
|
78 | 77 | history = classifier.fit(X_trainF, y_trainF, batch_size=120, epochs=15, verbose=1, validation_data=(X_validF, y_validF)) |
79 | 78 | classifier.summary() |
80 | 79 |
|
81 | | - |
82 | 80 | y_pred = classifier.predict(X_validF) |
83 | | -# Convert back to categorical values |
84 | 81 | y_predF = np.argmax(y_pred, axis=1) |
85 | 82 | y_valid_one = np.argmax(y_validF, axis=1) |
86 | 83 | classifier.save("./Malaria/Models/malaria.h5") |
0 commit comments