尝试使用 Tensorflow 版本 2.7.0 保存具有数据增强层的模型时出现错误。
这是数据增强的代码：
input_shape_rgb = (img_height, img_width, 3)
data_augmentation_rgb = tf.keras.Sequential(
[
layers.RandomFlip("horizontal"),
layers.RandomFlip("vertical"),
layers.RandomRotation(0.5),
layers.RandomZoom(0.5),
layers.RandomContrast(0.5),
RandomColorDistortion(name='random_contrast_brightness/none'),
]
)
现在我像这样构建我的模型：
# Build the model
input_shape = (img_height, img_width, 3)
model = Sequential([
layers.Input(input_shape),
data_augmentation_rgb,
layers.Rescaling((1./255)),
layers.Conv2D(16, kernel_size, padding=padding, activation='relu', strides=1,
data_format='channels_last'),
layers.MaxPooling2D(),
layers.BatchNormalization(),
layers.Conv2D(32, kernel_size, padding=padding, activation='relu'), # best 4
layers.MaxPooling2D(),
layers.BatchNormalization(),
layers.Conv2D(64, kernel_size, padding=padding, activation='relu'), # best 3
layers.MaxPooling2D(),
layers.BatchNormalization(),
layers.Conv2D(128, kernel_size, padding=padding, activation='relu'), # best 3
layers.MaxPooling2D(),
layers.BatchNormalization(),
layers.Flatten(),
layers.Dense(128, activation='relu'), # best 1 …将我的代码从 TF1 调整为 TF2.6 我遇到了麻烦。我正在尝试向 inception resnet 添加一些自定义层，保存模型，然后加载并运行它。
from tensorflow.keras.layers import Dense
from tensorflow.keras.models import Model
from tensorflow.keras.applications.inception_resnet_v2 import InceptionResNetV2
from tensorflow.keras.layers import Dense, GlobalAveragePooling2D
import tensorflow as tf
import numpy as np
from PIL import Image
export_path = "./save_test"
# Get model without top and add two layers
base_model = InceptionResNetV2(weights='imagenet', input_tensor=None, include_top=False)
out = base_model.output
out = GlobalAveragePooling2D()(out)
predictions = Dense(7, activation='softmax', name="output")(out)
# Make new model using inputs from base model and custom outputs
model = Model(inputs=base_model.input, …我是 Tensorflow 新手，正在尝试训练特定的深度学习神经网络。我正在使用 Tensorflow (2.11.0) 来获取深度神经网络模型，如下所述。我使用的数据也给出如下：
数据：
这是一些示例数据。为了方便起见，我们可以考虑数据中的 10 个样本。在这里，每个样本都有形状：(128,128)。
可以将以下代码视为示例训练数据。
x_train = np.random.rand(10, 128, 128, 1)
归一化层：
normalizer = tf.keras.layers.Normalization(axis=-1)
normalizer.adapt(x_train)
构建模型：
def build_and_compile_model(norm):
model = tf.keras.Sequential([
norm,
layers.Conv2D(128, 128, activation='relu'),
layers.Conv2D(3, 3, activation='relu'),
layers.Flatten(),
layers.Dense(units=32, activation='relu'),
layers.Dense(units=1)
])
model.compile(loss='mean_absolute_error', optimizer=tf.keras.optimizers.Adam(0.001))
return model
当我做
dnn_model = build_and_compile_model(normalizer)
dnn_model.summary()
我收到以下错误：
ValueError: The channel dimension of the inputs should be defined. The input_shape received is (None, None, None, None), where axis -1 (0-based) is the channel dimension, which found …我必须为我的一个项目使用 NestJs 中的 SOAP 服务。我正在尝试从网络使用虚拟 SOAP 服务。以下是详细信息——
网址 -
http://webservices.oorsprong.org/websamples.countryinfo/CountryInfoService.wso?WSDL
方法-POST
标头 -
Content-Type: text/xml
请求正文 -
<Envelope xmlns="http://schemas.xmlsoap.org/soap/envelope/">
<Body>
<CapitalCity xmlns="http://www.oorsprong.org/websamples.countryinfo">
<sCountryISOCode>IN</sCountryISOCode>
</CapitalCity>
</Body>
</Envelope>
响应正文 -
<?xml version="1.0" encoding="utf-8"?>
<soap:Envelope xmlns:soap="http://schemas.xmlsoap.org/soap/envelope/">
<soap:Body>
<m:CapitalCityResponse xmlns:m="http://www.oorsprong.org/websamples.countryinfo">
<m:CapitalCityResult>New Delhi</m:CapitalCityResult>
</m:CapitalCityResponse>
</soap:Body>
</soap:Envelope>
现在我无法弄清楚如何在我的 NestJs 虚拟应用程序中使用此服务。经过一段时间的探索，我发现了一个 Nestjs-soap 库，我安装并配置了它，如下所述 -
npm install nestjs-soap --save
我的 app.module.ts -
import { Module } from '@nestjs/common';
import { ConfigModule } from '@nestjs/config';
import { AppController } from './app.controller';
import { AppService } from './app.service';
import { …我有多个时间序列数据，如下所示：
df = pd.DataFrame({'Time': np.tile(np.arange(5), 2),
'Object': np.concatenate([[i] * 5 for i in [1, 2]]),
'Feature1': np.random.randint(10, size=10),
'Feature2': np.random.randint(10, size=10)})
Time Object Feature1 Feature2
0 0 1 3 3
1 1 1 9 2
2 2 1 6 6
3 3 1 4 0
4 4 1 7 7
5 0 2 4 8
6 1 2 3 7
7 2 2 1 1
8 3 2 7 5
9 4 2 1 7
其中每个对象（1 和 2）都有自己的数据（实际数据中大约有 2000 个对象）。我想将这些数据分块输入 …
python time-series deep-learning tensorflow tensorflow-datasets
我的输入是一个包含 64 个整数的数组。
model = Sequential()
model.add( Input(shape=(68,), name="input"))
model.add(Conv1D(64, 2, activation="relu", padding="same", name="convLayer"))
我的训练集中有 10,000 个这样的数组。我应该指定这个以便 conv1D 工作吗？
我遇到了可怕的事情
ValueError: Input 0 of layer convLayer is incompatible with the layer: : expected min_ndim=3, found ndim=2. Full shape received: [None, 68]
错误，我真的不明白我需要做什么。
这是我之前创建的用于适应模型的批量数据集：
train_ds = tf.keras.preprocessing.image_dataset_from_directory(
train_path,
label_mode = 'categorical', #it is used for multiclass classification. It is one hot encoded labels for each class
validation_split = 0.2, #percentage of dataset to be considered for validation
subset = "training", #this subset is used for training
seed = 1337, # seed is set so that same results are reproduced
image_size = img_size, # shape of input images
batch_size = batch_size, # This should match with model batch size
)
valid_ds = tf.keras.preprocessing.image_dataset_from_directory(
train_path, …我正在尝试保存下面经过训练的模型。
resnet = ResNet50V2(input_shape=(im_size,im_size,3), weights='imagenet', include_top=False)
headModel = AvgPool2D(pool_size=(3,3))(resnet.output)
headModel = Flatten(name="flatten")(headModel)
headModel = Dense(256, activation="relu")(headModel)
headModel = Dropout(0.5)(headModel)
headModel = Dense(1, activation="sigmoid")(headModel)
resnet50v2 = Model(inputs=resnet.input, outputs=headModel)
resnet50v2.compile(loss='binary_crossentropy', optimizer=opt, metrics=METRICS)
history = resnet50v2.fit(
datagen.flow(X_train, y_train, batch_size=32, subset='training'),
batch_size=batch_size,
epochs=150,
steps_per_epoch=steps_per_epoch,
validation_data=datagen.flow(X_train, y_train, batch_size=8, subset='validation'))
但是，每当我尝试使用以下命令保存它时：
resnet50v2.save('Saved_Models/resnet50.h5', save_format='h5')
我收到错误
ValueError Traceback (most recent call last)
/tmp/ipykernel_3252071/2034094124.py in <module>
----> 1 resnet50v2.save('Saved_Models/resnet50.h5', save_format='h5')
~/.local/lib/python3.8/site-packages/keras/utils/traceback_utils.py in error_handler(*args, **kwargs)
65 except Exception as e: # pylint: disable=broad-except
66 filtered_tb = _process_traceback_frames(e.__traceback__)
---> 67 raise …我正在学习一门有关使用 Tensorflow 进行时间序列预测的在线课程。用于将 Numpy 数组（TS）转换为 Tensorflow 数据集的函数是基于 LSTM 的模型，已经给出（带有我的注释行）：
def windowed_dataset(series, window_size, batch_size, shuffle_buffer):
# creating a tensor from an array
dataset = tf.data.Dataset.from_tensor_slices(series)
# cutting the tensor into fixed-size windows
dataset = dataset.window(window_size + 1, shift=1, drop_remainder=True)
# joining windows into a batch?
dataset = dataset.flat_map(lambda window: window.batch(window_size + 1))
# separating row into features/label
dataset = dataset.shuffle(shuffle_buffer).map(lambda window: (window[:-1], window[-1]))
dataset = dataset.batch(batch_size).prefetch(1)
return dataset
这段代码工作正常，但我想更好地理解它，以便根据我的需要修改/调整它。
如果我删除dataset.flat_map(lambda window: window.batch(window_size + 1))操作，我会收到TypeError: '_VariantDataset' object is not …
我一直在尝试微调 HuggingFace 的对话模型：Blendebot。我已经尝试过官方拥抱脸网站上给出的传统方法，该方法要求我们使用 trainer.train() 方法来完成此操作。我使用 .compile() 方法尝试了它。我尝试过使用 PyTorch 以及 TensorFlow 对我的数据集进行微调。这两种方法似乎都失败了，并给我们一个错误，指出没有适用于 Blenderbot 模型的编译或训练方法。我什至在网上到处查看 Blenderbot 如何对我的自定义数据进行微调，但没有任何地方正确提及运行时不会抛出错误。我浏览了 Youtube 教程、博客和 StackOverflow 帖子，但没有一个回答这个问题。希望有人能在这里回复并帮助我。我也愿意使用其他 HuggingFace 对话模型进行微调。
这是我用来微调 Blenderbot 模型的链接。
微调方法：https://huggingface.co/docs/transformers/training
Blenderbot：https://huggingface.co/docs/transformers/model_doc/blenderbot
from transformers import BlenderbotTokenizer, BlenderbotForConditionalGeneration
mname = "facebook/blenderbot-400M-distill"
model = BlenderbotForConditionalGeneration.from_pretrained(mname)
tokenizer = BlenderbotTokenizer.from_pretrained(mname)
#FOR TRAINING:
trainer = Trainer(
model=model,
args=training_args,
train_dataset=small_train_dataset,
eval_dataset=small_eval_dataset,
compute_metrics=compute_metrics,
)
trainer.train()
#OR
model.compile(
optimizer=tf.keras.optimizers.Adam(learning_rate=5e-5),
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=tf.metrics.SparseCategoricalAccuracy(),
)
model.fit(tf_train_dataset, validation_data=tf_validation_dataset, epochs=3)
这些都不起作用。
python ×9
tensorflow ×9
keras ×6
conv1d ×1
nestjs ×1
nlp ×1
pytorch ×1
resnet ×1
save ×1
soap ×1
time-series ×1
web-services ×1
xml ×1