Update README.md
Browse files
README.md
CHANGED
@@ -54,9 +54,10 @@ Train the Model: Use the provided code to train the model on your dataset.
|
|
54 |
Evaluate: Test the model on a separate set of images to assess performance.
|
55 |
|
56 |
|
57 |
-
|
58 |
## Training Details
|
59 |
|
|
|
|
|
60 |
### Training Data
|
61 |
|
62 |
-Dataset: DataScienceProject/Art_Images_Ai_And_Real_
|
@@ -65,20 +66,32 @@ Evaluate: Test the model on a separate set of images to assess performance.
|
|
65 |
|
66 |
### Training Procedure
|
67 |
|
68 |
-
|
69 |
-
|
70 |
|
71 |
|
72 |
#### Training Hyperparameters
|
73 |
|
74 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
75 |
|
76 |
## Evaluation
|
77 |
|
78 |
|
79 |
|
|
|
80 |
### Testing Data, Factors & Metrics
|
81 |
|
|
|
|
|
|
|
|
|
|
|
82 |
|
83 |
#### Testing Data
|
84 |
|
@@ -92,6 +105,7 @@ Images are resized to a uniform dimension and normalized. ELA is applied to emph
|
|
92 |
|
93 |
|
94 |
|
|
|
95 |
### Results
|
96 |
|
97 |
|
|
|
54 |
Evaluate: Test the model on a separate set of images to assess performance.
|
55 |
|
56 |
|
|
|
57 |
## Training Details
|
58 |
|
59 |
+
|
60 |
+
|
61 |
### Training Data
|
62 |
|
63 |
-Dataset: DataScienceProject/Art_Images_Ai_And_Real_
|
|
|
66 |
|
67 |
### Training Procedure
|
68 |
|
69 |
+
Train the CNN with the Preprocessed images , use valitadion set.
|
|
|
70 |
|
71 |
|
72 |
#### Training Hyperparameters
|
73 |
|
74 |
|
75 |
+
optimizer = RMSprop(lr=0.0005, rho=0.9, epsilon=1e-08, decay=0.0)
|
76 |
+
epochs = 22
|
77 |
+
batch_size = 100
|
78 |
+
loss = "categorical_crossentropy"
|
79 |
+
metrics=["accuracy"]
|
80 |
+
early_stopping = EarlyStopping(monitor='val_acc',min_delta=0,patience=2,verbose=0, mode='auto')
|
81 |
+
|
82 |
|
83 |
## Evaluation
|
84 |
|
85 |
|
86 |
|
87 |
+
|
88 |
### Testing Data, Factors & Metrics
|
89 |
|
90 |
+
precision
|
91 |
+
recall
|
92 |
+
f1
|
93 |
+
confusion_matrix
|
94 |
+
accuracy
|
95 |
|
96 |
#### Testing Data
|
97 |
|
|
|
105 |
|
106 |
|
107 |
|
108 |
+
|
109 |
### Results
|
110 |
|
111 |
|