查看python版本及内核
import sys
print(sys.version)
print(sys.executable)
3.8.5 (default, Sep 3 2020, 21:29:08) [MSC v.1916 64 bit (AMD64)]
D:\anaconda3\python.exe
查看tf 版本
print(tf.test.is_gpu_available())
print(torch.cuda.is_available())
tf image_dataset_from_directory
tf.keras.preprocessing.image_dataset_from_directory(
directory, labels='inferred', label_mode='int',
class_names=None, color_mode='rgb', batch_size=32, image_size=(256,
256), shuffle=True, seed=None, validation_split=None, subset=None,
interpolation='bilinear', follow_links=False
)
tf.keras.preprocessing.text_dataset_from_directory(
directory, labels='inferred', label_mode='int',
class_names=None, batch_size=32, max_length=None, shuffle=True, seed=None,
validation_split=None, subset=None, follow_links=False
)
tf.keras.preprocessing.timeseries_dataset_from_array(
data, targets, sequence_length, sequence_stride=1, sampling_rate=1,
batch_size=128, shuffle=False, seed=None, start_index=None, end_index=None
)
img = keras.preprocessing.image.load_img(
sunflower_path, target_size=(img_height, img_width)
)
img_array = keras.preprocessing.image.img_to_array(img)
img_array = tf.expand_dims(img_array, 0) # Create a batch
predictions = model.predict(img_array)
score = tf.nn.softmax(predictions[0])
print(
"This image most likely belongs to {} with a {:.2f} percent confidence."
.format(class_names[np.argmax(score)], 100 * np.max(score))
)
RGB 通道顺序
Tensorflow的tensor通道顺序:默认是NHWC, 也支持NCHW,使用cuDNN会更快;
Pytorch中tensor的通道顺序:NCHW
Fine tuning¶
Note: This should only be attempted after you have trained the top-level classifier with the pre-trained model set to non-trainable. If you add a randomly initialized classifier on top of a pre-trained model and attempt to train all layers jointly, the magnitude of the gradient updates will be too large (due to the random weights from the classifier) and your pre-trained model will forget what it has learned.
keras打印模型参数shape
keras.utils.plot_model(model, show_shapes=True)
进度条verbose
verbose: 0 or 1. Verbosity mode. 0 = silent, 1 = progress bar.2=output results without progress
pandas 拆分训练数据集和测试数据集
train_dataset = dataset.sample(frac=0.8,random_state=0)
test_dataset = dataset.drop(train_dataset.index)
归一化数据:
def norm(x):
return (x - train_stats['mean']) / train_stats['std']#pandas
normed_train_data = norm(train_dataset)
normed_test_data = norm(test_dataset)
callbacks用法
# 通过为每个完成的时期打印一个点来显示训练进度
class PrintDot(keras.callbacks.Callback):
def on_epoch_end(self, epoch, logs):
if epoch % 100 == 0: print('')
print('.', end='')
EPOCHS = 1000
history = model.fit(
normed_train_data, train_labels,
epochs=EPOCHS, validation_split = 0.2, verbose=0,
callbacks=[PrintDot()])
keras训练结果绘图
def plot_history(history):
hist = pd.DataFrame(history.history)
hist['epoch'] = history.epoch
plt.figure()
plt.xlabel('Epoch')
plt.ylabel('Mean Abs Error [MPG]')
plt.plot(hist['epoch'], hist['mae'],
label='Train Error')
plt.plot(hist['epoch'], hist['val_mae'],
label = 'Val Error')
plt.ylim([0,5])
plt.legend()
plt.figure()
plt.xlabel('Epoch')
plt.ylabel('Mean Square Error [$MPG^2$]')
plt.plot(hist['epoch'], hist['mse'],
label='Train Error')
plt.plot(hist['epoch'], hist['val_mse'],
label = 'Val Error')
plt.ylim([0,20])
plt.legend()
plt.show()
plot_history(history)
误差分布绘图
error = test_predictions - test_labels
plt.hist(error, bins = 25)
plt.xlabel("Prediction Error [MPG]")
_=plt.ylabel("Count")
tf 图像处理
def preprocess_image(image):
image = tf.image.decode_jpeg(image, channels=3)
image = tf.image.resize(image, [192, 192])
image /= 255.0 # normalize to [0,1] range
return image
def load_and_preprocess_image(path):
image = tf.io.read_file(path)
return preprocess_image(image)
import matplotlib.pyplot as plt
all_image_paths = list(data_root.glob('*/*'))
all_image_paths = [str(path) for path in all_image_paths]
random.shuffle(all_image_paths)
image_path = all_image_paths[0]
label = all_image_labels[0]
plt.imshow(load_and_preprocess_image(img_path))
plt.grid(False)
plt.xlabel(caption_image(img_path))
plt.title(label_names[label].title())
print()
steps_per_epoch=tf.math.ceil(len(all_image_paths)/BATCH_SIZE).numpy()
Jupyter快捷键
命令模式 (按键 Esc 开启)快捷键:
Enter : 转入编辑模式
Shift-Enter : 运行本单元,选中下个单元
Ctrl-Enter : 运行本单元
Alt-Enter : 运行本单元,在其下插入新单元
Y : 单元转入代码状态
M :单元转入markdown状态
R : 单元转入raw状态
Up : 选中上方单元
Down : 选中下方单元
Shift-K : 扩大选中上方单元
Shift-J : 扩大选中下方单元
A : 在上方插入新单元
B : 在下方插入新单元
X : 剪切选中的单元
C : 复制选中的单元
Shift-V : 粘贴到上方单元
V : 粘贴到下方单元
Z : 恢复删除的最后一个单元
D,D : 删除选中的单元
Shift-M : 合并选中的单元
Ctrl-S : 文件存盘
S : 文件存盘
L : 转换行号
O : 转换输出
Shift-O : 转换输出滚动
Esc : 关闭页面
Q : 关闭页面
H : 显示快捷键帮助
I,I : 中断Notebook内核
0,0 : 重启Notebook内核
Shift : 忽略
Shift-Space : 向上滚动
Space : 向下滚动
编辑模式 ( Enter 键启动)下快捷键
Tab : 代码补全或缩进
Shift-Tab : 提示
Ctrl-] : 缩进
Ctrl-[ : 解除缩进
Ctrl-A : 全选
Ctrl-Z : 复原
Ctrl-Shift-Z : 再做
Ctrl-Y : 再做
Ctrl-Home : 跳到单元开头
Ctrl-Up : 跳到单元开头
Ctrl-End : 跳到单元末尾
Ctrl-Down : 跳到单元末尾
Ctrl-Left : 跳到左边一个字首
Ctrl-Right : 跳到右边一个字首
Ctrl-Backspace : 删除前面一个字
Ctrl-Delete : 删除后面一个字
Esc : 进入命令模式
Ctrl-M : 进入命令模式
Shift-Enter : 运行本单元,选中下一单元
Ctrl-Enter : 运行本单元
Alt-Enter : 运行本单元,在下面插入一单元
Ctrl-Shift– : 分割单元
Ctrl-Shift-Subtract : 分割单元
Ctrl-S : 文件存盘
Shift : 忽略
Up : 光标上移或转入上一单元
Down :光标下移或转入下一单元