fix check path; fix

pytorch_classification/ConfusionMatrix/main.py

@@ -1,12 +1,15 @@
+import os
+import json
+
 import torch
 from torchvision import transforms, datasets
-import json
-import os
-from model import MobileNetV2
 import numpy as np
+from tqdm import tqdm
 import matplotlib.pyplot as plt
 from prettytable import PrettyTable
 
+from model import MobileNetV2
+
 
 class ConfusionMatrix(object):
     """
@@ -39,9 +42,9 @@ def summary(self):
             FP = np.sum(self.matrix[i, :]) - TP
             FN = np.sum(self.matrix[:, i]) - TP
             TN = np.sum(self.matrix) - TP - FP - FN
-            Precision = round(TP / (TP + FP), 3)
-            Recall = round(TP / (TP + FN), 3)
-            Specificity = round(TN / (TN + FP), 3)
+            Precision = round(TP / (TP + FP), 3) if TP + FP != 0 else 0.
+            Recall = round(TP / (TP + FN), 3) if TP + FN != 0 else 0.
+            Specificity = round(TN / (TN + FP), 3) if TN + FP != 0 else 0.
             table.add_row([self.labels[i], Precision, Recall, Specificity])
         print(table)
 
@@ -111,7 +114,7 @@ def plot(self):
     confusion = ConfusionMatrix(num_classes=5, labels=labels)
     net.eval()
     with torch.no_grad():
-        for val_data in validate_loader:
+        for val_data in tqdm(validate_loader):
             val_images, val_labels = val_data
             outputs = net(val_images.to(device))
             outputs = torch.softmax(outputs, dim=1)

tensorflow_classification/ConfusionMatrix/main.py

@@ -1,13 +1,17 @@
+import os
+import math
+import json
+import glob
+
 from tensorflow.keras.preprocessing.image import ImageDataGenerator
 import matplotlib.pyplot as plt
-from model import MobileNetV2
 import tensorflow as tf
-import json
-import os
-import math
 import numpy as np
+from tqdm import tqdm
 from prettytable import PrettyTable
 
+from model import MobileNetV2
+
 
 class ConfusionMatrix(object):
     """
@@ -40,9 +44,9 @@ def summary(self):
             FP = np.sum(self.matrix[i, :]) - TP
             FN = np.sum(self.matrix[:, i]) - TP
             TN = np.sum(self.matrix) - TP - FP - FN
-            Precision = round(TP / (TP + FP), 3)
-            Recall = round(TP / (TP + FN), 3)
-            Specificity = round(TN / (TN + FP), 3)
+            Precision = round(TP / (TP + FP), 3) if TP + FP != 0 else 0.
+            Recall = round(TP / (TP + FN), 3) if TP + FN != 0 else 0.
+            Specificity = round(TN / (TN + FP), 3) if TN + FP != 0 else 0.
             table.add_row([self.labels[i], Precision, Recall, Specificity])
         print(table)
 
@@ -107,8 +111,8 @@ def pre_function(img):
 
     model = MobileNetV2(num_classes=5)
     # feature.build((None, 224, 224, 3))  # when using subclass model
-    pre_weights_path = './MobileNetV2.ckpt'
-    assert os.path.exists(pre_weights_path), "cannot find {}".format(pre_weights_path)
+    pre_weights_path = './myMobileNet.ckpt'
+    assert len(glob.glob(pre_weights_path+"*")), "cannot find {}".format(pre_weights_path)
     model.load_weights(pre_weights_path)
 
     # read class_indict
@@ -121,7 +125,7 @@ def pre_function(img):
     confusion = ConfusionMatrix(num_classes=5, labels=labels)
 
     # validate
-    for step in range(math.ceil(total_val / batch_size)):
+    for step in tqdm(range(math.ceil(total_val / batch_size))):
         val_images, val_labels = next(val_data_gen)
         results = model.predict_on_batch(val_images)
         results = tf.keras.layers.Softmax()(results).numpy()

tensorflow_classification/Test2_alexnet/fine_train_alexnet.py

@@ -4,6 +4,7 @@
 import tensorflow as tf
 import json
 import os
+import glob
 from tensorflow.keras import layers, models, Model, Sequential
 
 
@@ -94,7 +95,7 @@ def pre_function(img: np.ndarray):
     model = AlexNet_pytorch(im_height=im_height, im_width=im_width, class_num=5)
 
     pre_weights_path = './pretrain_weights.ckpt'
-    assert os.path.exists(pre_weights_path), "cannot find {}".format(pre_weights_path)
+    assert len(glob.glob(pre_weights_path+"*")), "cannot find {}".format(pre_weights_path)
     model.load_weights(pre_weights_path)
     for layer_t in model.layers:
         if 'conv2d' in layer_t.name:

tensorflow_classification/Test3_vgg/fine_train_vgg16.py

@@ -4,6 +4,7 @@
 import tensorflow as tf
 import json
 import os
+import glob
 
 
 def main():
@@ -68,7 +69,7 @@ def pre_function(img):
     model = vgg("vgg16", 224, 224, 5)
 
     pre_weights_path = './pretrain_weights.ckpt'
-    assert os.path.exists(pre_weights_path), "cannot find {}".format(pre_weights_path)
+    assert len(glob.glob(pre_weights_path+"*")), "cannot find {}".format(pre_weights_path)
     model.load_weights(pre_weights_path)
     for layer_t in model.layers:
         if layer_t.name == 'feature':

tensorflow_classification/Test4_goolenet/train_add_bn.py

@@ -4,6 +4,7 @@
 import tensorflow as tf
 import json
 import os
+import glob
 import numpy as np
 
 
@@ -68,7 +69,7 @@ def pre_function(img: np.ndarray):
     # model.build((batch_size, 224, 224, 3))  # when using subclass model
 
     pre_weights_path = './pretrain_weights.ckpt'
-    assert os.path.exists(pre_weights_path), "cannot find {}".format(pre_weights_path)
+    assert len(glob.glob(pre_weights_path+"*")), "cannot find {}".format(pre_weights_path)
     model.load_weights(pre_weights_path)
     model.summary()
 

tensorflow_classification/Test5_resnet/train.py

@@ -4,6 +4,7 @@
 import tensorflow as tf
 import json
 import os
+import glob
 import PIL.Image as im
 import numpy as np
 
@@ -69,7 +70,7 @@ def pre_function(img):
     # feature.build((None, 224, 224, 3))  # when using subclass model
 
     pre_weights_path = './pretrain_weights.ckpt'
-    assert os.path.exists(pre_weights_path), "cannot find {}".format(pre_weights_path)
+    assert len(glob.glob(pre_weights_path+"*")), "cannot find {}".format(pre_weights_path)
     feature.load_weights(pre_weights_path)
     feature.trainable = False
     feature.summary()

tensorflow_classification/Test5_resnet/trainGPU.py

@@ -65,7 +65,6 @@ def main():
     print("using {} images for training, {} images for validation.".format(train_num,
                                                                            val_num))
 
-
     def process_train_img(img_path, label):
         label = tf.one_hot(label, depth=class_num)
         image = tf.io.read_file(img_path)

tensorflow_classification/Test6_mobilenet/train.py

@@ -4,6 +4,7 @@
 import tensorflow as tf
 import json
 import os
+import glob
 import PIL.Image as im
 import numpy as np
 
@@ -65,7 +66,7 @@ def pre_function(img):
     # feature.build((None, 224, 224, 3))  # when using subclass model
 
     pre_weights_path = './pretrain_weights.ckpt'
-    assert os.path.exists(pre_weights_path), "cannot find {}".format(pre_weights_path)
+    assert len(glob.glob(pre_weights_path+"*")), "cannot find {}".format(pre_weights_path)
     model.load_weights(pre_weights_path)
     for layer_t in model.layers[:-1]:
         layer_t.trainable = False