网站建设 新闻,网站里面发消息怎么做超链接,深圳做分销网站建设,php网站培训班这些年#xff0c;有很多感悟#xff1a;一个人精力是有限的#xff0c;一个人视野也有有限的#xff0c;你总会不经意间发现优秀人的就在身边。
看我文章的小伙伴应该经常听我说过的一句话#xff1a;技术要学会交流、分享#xff0c;不建议闭门造车。一个人可以走的很…这些年有很多感悟一个人精力是有限的一个人视野也有有限的你总会不经意间发现优秀人的就在身边。
看我文章的小伙伴应该经常听我说过的一句话技术要学会交流、分享不建议闭门造车。一个人可以走的很快、一堆人可以走的更远。 这句话是这些年经验的总结。
本文就是由我们粉丝群的小伙伴讨论、分享的总结最终汇总成了这个《keras 快速使用手册》如果你也喜欢学习、交流可以文末的方式加入我们。
我们开始正题
keras快速使用手册
import keras
import tensorflow as tf
print(keras.__version__)
print(tf.__version__)基本命令
import random
import tensorflow as tf
import numpy as np
import os
def seed_everything(seed):random.seed(seed)os.environ[PYTHONHASHSEED] str(seed)np.random.seed(seed)tf.random.set_seed(seed)seed_everything(2019)定义数据的输入和输出
直接加载到内存中
train_x np.random.radnom((1000,23))
train_y np.random.radnom((1000,1))
from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test train_test_split(train_x, train_y, test_size0.1, random_state0, shuffleTrue)迭代器的形式读取数据
import keras# helper function for data visualization
def denormalize(x):Scale image to range 0..1 for correct plotx_max np.percentile(x, 98)x_min np.percentile(x, 2) x (x - x_min) / (x_max - x_min)x x.clip(0, 1)return x# classes for data loading and preprocessing
class Dataset:CamVid Dataset. Read images, apply augmentation and preprocessing transformations.Args:images_dir (str): path to images foldermasks_dir (str): path to segmentation masks folderclass_values (list): values of classes to extract from segmentation maskaugmentation (albumentations.Compose): data transfromation pipeline (e.g. flip, scale, etc.)preprocessing (albumentations.Compose): data preprocessing (e.g. noralization, shape manipulation, etc.)def __init__(self, images_dir, masks_dir, classesNone, augmentationNone, preprocessingNone,):self.CLASSES [sky, building, pole, road, pavement, tree, signsymbol, fence, car, pedestrian, bicyclist, unlabelled]self.ids os.listdir(images_dir)self.images_fps [os.path.join(images_dir, image_id) for image_id in self.ids]self.masks_fps [os.path.join(masks_dir, image_id) for image_id in self.ids]# convert str names to class values on masksself.class_values [self.CLASSES.index(cls.lower()) for cls in self.CLASSES]self.augmentation augmentationself.preprocessing preprocessingdef __getitem__(self, i):# read dataimage cv2.imread(self.images_fps[i])image cv2.cvtColor(image, cv2.COLOR_BGR2RGB)image cv2.resize(image,(480,480))mask cv2.imread(self.masks_fps[i], 0)mask cv2.resize(mask,(480,480))# extract certain classes from mask (e.g. cars)masks [(mask v) for v in self.class_values]mask np.stack(masks, axis-1).astype(float)# add background if mask is not binaryif mask.shape[-1] ! 1:background 1 - mask.sum(axis-1, keepdimsTrue)mask np.concatenate((mask, background), axis-1)# apply augmentationsif self.augmentation:sample self.augmentation(imageimage, maskmask)image, mask sample[image], sample[mask]# apply preprocessingif self.preprocessing:sample self.preprocessing(imageimage, maskmask)image, mask sample[image], sample[mask]return image, maskdef __len__(self):return len(self.ids)class Dataloder(keras.utils.Sequence):Load data from dataset and form batchesArgs:dataset: instance of Dataset class for image loading and preprocessing.batch_size: Integet number of images in batch.shuffle: Boolean, if True shuffle image indexes each epoch.def __init__(self, dataset, batch_size1, augmentNone, shuffleFalse):self.dataset datasetself.batch_size batch_sizeself.shuffle shuffleself.indexes np.arange(len(dataset))self.augment augmentself.on_epoch_end()def __getitem__(self, i):# collect batch datastart i * self.batch_sizestop (i 1) * self.batch_sizedata []for j in range(start, stop):if self.augment is None:data.append(np.array(X),np.array(y))else: im,mask [],[] for x,y in zip(X,y):augmented self.augment(imagex, masky)im.append(augmented[image])mask.append(augmented[mask])data.append(np.array(im),np.array(mask))# transpose list of listsbatch [np.stack(samples, axis0) for samples in zip(*data)]return batchdef __len__(self):Denotes the number of batches per epochreturn len(self.indexes) // self.batch_sizedef on_epoch_end(self):Callback function to shuffle indexes each epochif self.shuffle:self.indexes np.random.permutation(self.indexes) # Dataset for validation images
train_dataset Dataset(x_train_dir, y_train_dir)
valid_dataset Dataset(x_valid_dir, y_valid_dir)# check shapes for errors
BATCH_SIZE 4
train_dataloader Dataloder(train_dataset, batch_sizeBATCH_SIZE, shuffleTrue)
valid_dataloader Dataloder(valid_dataset, batch_sizeBATCH_SIZE, shuffleFalse)数据增强
from albumentations import (Compose, HorizontalFlip, CLAHE, HueSaturationValue,RandomBrightness, RandomContrast, RandomGamma, OneOf,ToFloat, ShiftScaleRotate, GridDistortion, ElasticTransform, JpegCompression, HueSaturationValue,RGBShift, RandomBrightness, RandomContrast, Blur, MotionBlur, MedianBlur, GaussNoise, CenterCrop,IAAAdditiveGaussianNoise, GaussNoise, OpticalDistortion, RandomSizedCrop
)AUGMENTATIONS_TRAIN Compose([HorizontalFlip(p0.5),OneOf([RandomContrast(),RandomGamma(),RandomBrightness(),], p0.3),OneOf([ElasticTransform(alpha120, sigma120 * 0.05, alpha_affine120 * 0.03),GridDistortion(),OpticalDistortion(distort_limit2, shift_limit0.5),], p0.3),RandomSizedCrop(min_max_height(sz / 2, sz), heighth, widthw, p0.5),ToFloat(max_value1)
], p1)AUGMENTATIONS_TEST Compose([ToFloat(max_value1)
], p1)train_dataloader Dataloder(train_dataset, batch_sizeBATCH_SIZE,augmentAUGMENTATIONS_TRAIN,shuffleTrue)
valid_dataloader Dataloder(valid_dataset, batch_sizeBATCH_SIZE, augmentAUGMENTATIONS_TEST,shuffleFalse)定义网络模型
from keras.layers import *
from keras.models import *
import warnings
warnings.filterwarnings(ignore)def my_model(input_shape, with_dropout True):m_input Input(input_shape)out Conv2D(32, 3,paddingsame, activationrelu)(m_input)out BatchNormalization()(out)out MaxPool2D(2)(out)out Conv2D(64, 3, paddingsame, activationrelu)(out)out Conv2D(64, 3, paddingsame, activationrelu)(out)out Conv2D(64, 3, paddingsame, activationrelu)(out)out BatchNormalization()(out)out MaxPool2D(2)(out)out Conv2D(64, 3, paddingsame, activationrelu)(out)out Conv2D(64, 3, paddingsame, activationrelu)(out)out Conv2D(64, 3, paddingsame, activationrelu)(out)out BatchNormalization()(out)out MaxPool2D(2)(out)out Conv2D(128, 3, paddingsame, activationrelu)(out)out Conv2D(128, 3, paddingsame, activationrelu)(out)out Conv2D(128, 3, paddingsame, activationrelu)(out)out BatchNormalization()(out)out MaxPool2D(2)(out)out Conv2D(128, 3, paddingsame, activationrelu)(out)out Conv2D(128, 3, paddingsame, activationrelu)(out)out Conv2D(128, 3, paddingsame, activationrelu)(out)out Flatten()(out)out Dense(64, activationrelu)(out)if with_dropout:out Dropout(0.4)(out)out Dense(2, activationlinear)(out)model Model(m_input, out)return modelmodel my_model((128,128,1))
model.summary()获得网络所有的层
获得每一层模型的名称是否可训练权重信息
print( model layers:,len(model.layers))
x np.random.random((1,128,128,1))
out model.predict(x)
print(output size:,x.shape)
for layer in model.layers:print(layer.name,layer.trainable)if len(layer.weights)0:print(layer.weights[0].shape)breakimport keras.backend as K
from keras.layers import *
import numpy as npmodelNonemodel.load_weights(finall_weights.h5)def get_layers_output(model,x_input,index):middle_layer K.function([model.input], [model.layers[index].output])middle_outmiddle_layer([np.expand_dims(x_input,axis0)])[0]return middle_out############################################################################
##获得某一层的权重
layer_dict dict([(layer.name, layer) for layer in model.layers])
print(layer_dict)
print(model.layers[-1].output)
last_weightsmodel.layers[-1].get_weights()[0]
last_baismodel.layers[-1].get_weights()[1]
print(last layer weights:,last_weights.shape)
print(last layer bias:,last_bais,last_bais.shape) ##[0.4908378 0.48844907]############################################################################
##获得某一层的输出
x_trainnp.random.random((1,100,100,))
first_layer_outget_layers_output(model,x_train[0],1)
print(first_layer_out[:,1,1,:3]) ## results:[[0.07100815 0.38357598 0. ]]
########################################################################################################################################################
##设置模型网络层是否可训练
def make_trainable(net, val):net.trainable valfor l in net.layers:l.trainable val
# make_trainable(model,False)
############################################################################获得网络的权重参数
tmodel.get_layer(conv2d_14)
print(t)
for index in t.get_weights():print(index.shape)冻结网络的某一层
for layer in model.layers:if not isinstance(layer, BatchNormalization):layer.trainable False保存和加载权重参数信息
model.save_weights(weights.h5) ## v1
model.load_weights(weights.h5,by_nameTrue)## v2def IoU(y_true, y_pred, eps1e-6):if K.max(y_true) 0.0:return IoU(1-y_true, 1-y_pred) ## empty image; calc IoU of zerosintersection K.sum(y_true * y_pred, axis[1,2,3])union K.sum(y_true, axis[1,2,3]) K.sum(y_pred, axis[1,2,3]) - intersectionreturn K.mean( (intersection eps) / (union eps), axis0)加载模型
from keras.models import load_model
model load_model(model.h5, custom_objects{IoU: IoU}) ## v3model.save(path_to_my_model)检查权重是否加载成功
model get_model()
# Train the model.
test_input np.random.random((128, 32))
test_target np.random.random((128, 1))
model.fit(test_input, test_target)# Calling save(my_model) creates a SavedModel folder my_model.
model.save(my_model)# It can be used to reconstruct the model identically.
reconstructed_model keras.models.load_model(my_model)
# # Option 1: Load with the custom_object argument.
# reconstructed_model keras.models.load_model(
# my_model, custom_objects{CustomModel: CustomModel}
# )# Lets check:
np.testing.assert_allclose(model.predict(test_input), reconstructed_model.predict(test_input)
)自定义网络层
import keras.backend as K
from keras.layers import *
from keras.models import *
import numpy as npdef sub_mean(x):x-x/2return xclass MyLayer(Layer):def __init__(self, output_dim, **kw):self.output_dim output_dimsuper(MyLayer, self).__init__(**kw)def build(self, input_shape):input_dim input_shape[1]inital_SCALER np.ones((input_dim,self.output_dim))self.SCALER K.variable(inital_SCALER)self.trainable_weights [self.SCALER]super(MyLayer, self).build(input_shape)def call(self, x, maskNone):x K.dot(x,self.SCALER)return xdef compute_output_shape(self, input_shape):return (input_shape[0],self.output_dim)def get_submean_model():model Sequential()model.add(Dense(5, input_dim7))model.add(MyLayer(1))model.add(Lambda(sub_mean,output_shapelambda input_shape:input_shape))model.compile(optimizerrmsprop, lossmse)return model
model get_submean_model()
model.summary()import tensorflow as tf
from keras.layers import *
from keras.models import *class CustomDense(Layer):def __init__(self, units32):super(CustomDense, self).__init__()self.units unitsdef build(self, input_shape):self.w self.add_weight(shape(input_shape[-1], self.units),initializerrandom_normal,trainableTrue,)self.b self.add_weight(shape(self.units,), initializerrandom_normal, trainableTrue)def call(self, inputs):return tf.matmul(inputs, self.w) self.bdef get_config(self):return {units: self.units}inputs Input((4,))
outputs CustomDense(10)(inputs)model Model(inputs, outputs)
model.summary()config model.get_config()
new_model Model.from_config(config, custom_objects{CustomDense: CustomDense})
new_model.summary()out new_model(tf.zeros((2,4)))
out.shape获得某一层参数
layer layers.Dense(3)
print(layer.weights) # Emptyxtf.zeros((2,3))
outlayer(x)
out.shape,layer.weightsmodel keras.Sequential()
model.add(layers.Dense(2, activationrelu, input_shape(4,)))model.summary()常用的优化器
from keras.optimizers import RMSprop,Adam,SGD,Adadelta
m_sgd SGD(lr0.01,momentum0.9,decay1e-3,nesterovFalse)from keras.losses import *
from keras.optimizers import *
model.compile(optimizerRMSprop(1e-3),loss{priority: BinaryCrossentropy(from_logitsTrue),department: CategoricalCrossentropy(from_logitsTrue),},metrics[acc],loss_weights{priority: 1.0, department: 0.2},
)常用的损失函数
from keras.losses import mean_squared_error,sparse_categorical_crossentropy,binary_crossentropyfrom keras.optimizers import Adam,SGDdef dice_coef_loss(y_true, y_pred):def dice_coef(y_true, y_pred, smooth1):intersection K.sum(y_true * y_pred, axis[1, 2, 3])union K.sum(y_true, axis[1, 2, 3]) K.sum(y_pred, axis[1, 2, 3])return K.mean((2. * intersection smooth) / (union smooth), axis0)return 1 - dice_coef(y_true, y_pred, smooth1)# 自定义损失函数
def IoU(y_true, y_pred, eps1e-6):if K.max(y_true) 0.0:return IoU(1-y_true, 1-y_pred) ## empty image; calc IoU of zerosintersection K.sum(y_true * y_pred, axis[1,2,3])union K.sum(y_true, axis[1,2,3]) K.sum(y_pred, axis[1,2,3]) - intersectionreturn K.mean( (intersection eps) / (union eps), axis0)model.compile(optimizerAdam(lr0.001),lossdice_coef_loss, metrics[IoU])常用的指标验证函数 categorical_accuracy
accuracy
binary_accuracy
mse
mape
top_k_categorical_accuracy
model.compile(lossmse, optimizerRMSprop(lr0.001),metrics[mape])
# 自定义验证指标函数
def define_rmse(y_true, y_pred):return K.sqrt(K.mean(K.square(y_true - y_pred), axis-1))model.compile(optimizerrmsprop,metrics[define_rmse],loss define_rmse)训练过程
# train model
from keras.callbacks import *callbacks [ModelCheckpoint(./best_model.h5, save_weights_onlyTrue, save_best_onlyTrue, modemin,verbose1),ReduceLROnPlateau(monitorval_loss,factor0.6,patience6,modemin,verbose1),EarlyStopping(monitorval_loss, patience30, verbose1),
]history model.fit_generator(train_dataloader, steps_per_epochlen(train_dataloader), epochsEPOCHS, callbackscallbacks, validation_datavalid_dataloader, validation_stepslen(valid_dataloader),verbose1)## train modelhistory model.fit(x_train, y_train, batch_size16 * 4, epochs120, verbose1, validation_data(x_test, y_test),callbacks[checkpoint, early_stopping,r_lr],verbose1)预测阶段
scores model.evaluate_generator(val_dataloader)
scores model.predict_generator(test_dataloader)scores model.evaluate(x val_train, y val_label,batch_size None, verbose 1)
pred model.predict(np.expand_dims(image, axis0))import numpy as np
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
units 32
timesteps 10
input_dim 5# Define a Functional model
inputs keras.Input((None, units))
x layers.GlobalAveragePooling1D()(inputs)
outputs layers.Dense(1)(x)
model keras.Model(inputs, outputs)class CustomRNN(layers.Layer):def __init__(self):super(CustomRNN, self).__init__()self.units unitsself.projection_1 layers.Dense(unitsunits, activationtanh)self.projection_2 layers.Dense(unitsunits, activationtanh)# Our previously-defined Functional modelself.classifier modeldef call(self, inputs):outputs []state tf.zeros(shape(inputs.shape[0], self.units))for t in range(inputs.shape[1]):x inputs[:, t, :]h self.projection_1(x)y h self.projection_2(state)state youtputs.append(y)features tf.stack(outputs, axis1)return self.classifier(features)rnn_model CustomRNN()
out rnn_model(tf.zeros((1, timesteps, input_dim)))
print(out.shape)(1, 1)keras 模型与pytorch模型
二维卷积层(keras vs pytorch)
import numpy as np
import torch
import torch.nn as nn
import tensorflow as tf
import tensorflow.keras as keras
import tensorflow.keras.layers as layers#initialize the layers respectively
torch_layer nn.Conv2d( in_channels3,out_channels32,kernel_size(3, 3),stride(1, 1)
)
torch_model nn.Sequential(# nn.ZeroPad2d((2,3,2,3)),torch_layer)tf_layer layers.Conv2D(filters32,kernel_size(3, 3),strides(1, 1),# paddingsame,# use_biasFalse
)tf_model keras.Sequential([# layers.ZeroPadding2D((3, 3)),tf_layer])#setting weights in torch layer and tf layer respectively
torch_weights np.random.rand(32, 3, 3, 3)
torch_bias np.random.rand(32)
tf_weights np.transpose(torch_weights, (2, 3, 1, 0))
tf_bias torch_bias## 赋值固定的权重
torch_layer.weight torch.nn.Parameter(torch.Tensor(torch_weights))
torch_layer.bias torch.nn.Parameter(torch.Tensor(torch_bias))tf_model(np.zeros((1,256,256,3)))
# tf_layer.kernel.assign(tf_weights)
tf_layer.weights[0].assign(tf_weights)
tf_layer.weights[1].assign(tf_bias)tf_inputs np.random.rand(1, 256, 256, 3)
torch_inputs torch.Tensor(np.transpose(tf_inputs, (0, 3 ,1,2)))with torch.no_grad():torch_output torch_model(torch_inputs)
tf_output tf_model(tf_inputs)
print(tf_output.numpy().shape, torch_output.shape)
np.allclose(tf_output.numpy() ,np.transpose(torch_output.numpy(),(0, 2, 3, 1))) #True(1, 254, 254, 32) torch.Size([1, 32, 254, 254])TrueBatchNormal层(keras vs pytorch) tf_inputs np.random.rand(1, 12, 12, 32)
layer layers.BatchNormalization()
layer(tf_inputs)
weights layer.get_weights() # gamma,beta,mean,var
for layer in weights:print(layer.shape)(32,)
(32,)
(32,)
(32,)torch_layer nn.BatchNorm2d(32)
torch_layer.weight,torch_layer.bias
(Parameter containing:tensor([1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.],requires_gradTrue),Parameter containing:tensor([0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,0., 0., 0., 0., 0., 0., 0., 0.], requires_gradTrue))import numpy as np
import torch
import torch.nn as nn
import tensorflow as tf
import tensorflow.keras as keras
import tensorflow.keras.layers as layers#initialize the layers respectively
torch_layer nn.BatchNorm2d(32,eps1e-05, momentum0.1) #weight(gamma)和bias(beta)将被使用
torch_model nn.Sequential(# nn.ZeroPad2d((2,3,2,3)),torch_layer)tf_layer layers.BatchNormalization( momentum0.1,epsilon1e-05,)tf_model keras.Sequential([# layers.ZeroPadding2D((3, 3)),tf_layer])#setting weights in torch layer and tf layer respectively
weights np.random.rand(32)
bias np.random.rand(32)
## 赋值固定的权重
torch_layer.weight torch.nn.Parameter(torch.Tensor(weights))
torch_layer.bias torch.nn.Parameter(torch.Tensor(bias))tf_model(np.zeros((1,12,12,32)))
# tf_layer.kernel.assign(tf_weights)
tf_layer.weights[0].assign(weights)
tf_layer.weights[1].assign(bias)tf_inputs np.random.rand(1, 12, 12, 32)
torch_inputs torch.Tensor(np.transpose(tf_inputs, (0, 3 ,1,2)))
tf_layer.weights[2].assign(tf_inputs.mean(axis(0,1,2)))
tf_layer.weights[3].assign(tf_inputs.std(axis(0,1,2)))with torch.no_grad():torch_output torch_model(torch_inputs)
tf_output tf_model(tf_inputs)
print(tf_output.numpy().shape, torch_output.shape)
print(np.allclose(tf_output.numpy() ,np.transpose(torch_output.numpy(),(0, 2, 3, 1)))) #True
tf_output[0,0,0,:10],np.transpose(torch_output.numpy(),(0, 2, 3, 1))[0,0,0,:10](1, 12, 12, 32) torch.Size([1, 32, 12, 12])
False(tf.Tensor: shape(10,), dtypefloat32, numpyarray([ 0.45506844, -0.12573612, 0.81879985, 0.08219968, 0.08907801,0.88896 , 0.6723665 , 0.9736586 , -0.1965737 , 0.38121822],dtypefloat32),array([ 0.53097904, -0.34610078, 0.8367056 , -0.046165 , -0.2674462 ,0.953462 , 0.69444454, 1.0367548 , -0.36438996, 0.60396177],dtypefloat32))最大池化层(keras vs pytorch)
import numpy as np
import torch
import torch.nn as nn
import tensorflow as tf
import tensorflow.keras as keras
import tensorflow.keras.layers as layers#prepare inputs and do inference
# torch_inputs torch.Tensor(np.random.rand(1, 3, 256, 256))
# tf_inputs np.transpose(torch_inputs.numpy(), (0, 2, 3, 1))
tf_inputs np.random.rand(1, 256, 256, 3)
torch_inputs torch.Tensor(np.transpose(tf_inputs, (0, 3 ,1,2)))torch_layer nn.MaxPool2d(2)
torch_model nn.Sequential(torch_layer)
tf_layer layers.MaxPooling2D(pool_size(2, 2))
tf_model keras.Sequential([tf_layer])with torch.no_grad():torch_output torch_model(torch_inputs)
tf_output tf_model.predict(tf_inputs)
print(tf_output.shape, torch_output.shape)
np.allclose(tf_output ,np.transpose(torch_output.numpy(),(0, 2, 3, 1))) #True(1, 128, 128, 3) torch.Size([1, 3, 128, 128])
True全连接层输出(keras vs pytorch)
import numpy as np
import torch
import torch.nn as nn
import tensorflow as tf
import tensorflow.keras as keras
import tensorflow.keras.layers as layers#initialize the layers respectively
torch_layer nn.Linear(256,10)
torch_model nn.Sequential( torch_layer)tf_layer layers.Dense(10,activationNone)
tf_model keras.Sequential([ tf_layer])#setting weights in torch layer and tf layer respectively
torch_weights np.random.rand(10,256)
torch_bias np.random.rand(10)tf_weights np.transpose(torch_weights, (1, 0))
tf_bias torch_bias## 赋值固定的权重
torch_layer.weight torch.nn.Parameter(torch.Tensor(torch_weights))
torch_layer.bias torch.nn.Parameter(torch.Tensor(torch_bias))
tf_model(np.zeros((4,256)))
tf_layer.weights[0].assign(tf_weights)
tf_layer.weights[1].assign(tf_bias)inputs torch.Tensor(np.random.rand(4, 256))
with torch.no_grad():torch_output torch_model(inputs)
tf_output tf_model(inputs.numpy())
print(tf_output.numpy().shape, torch_output.shape)
np.allclose(tf_output.numpy() ,torch_output.numpy()) #True(4, 10) torch.Size([4, 10])TrueFlatten vs view() (keras vs pytorch)
import numpy as np
import torch
import torch.nn as nn
import tensorflow as tf
import tensorflow.keras as keras
import tensorflow.keras.layers as layers
np.set_printoptions(precision4)
torch.set_printoptions(precision4)#initialize the layers respectivelytf_layer layers.Flatten()
tf_model keras.Sequential([ tf_layer])tf_inputs np.random.rand(2,2,2,3)
torch_inputs torch.Tensor(tf_inputs) #np.transpose(tf_inputs, (0, 3, 1, 2)))
print(tf_inputs.shape, torch_inputs.shape)
with torch.no_grad():torch_output torch.flatten(torch_inputs,start_dim1)
tf_output tf_model(tf_inputs)
print(tf_output.numpy().shape, torch_output.shape)
np.allclose(tf_output.numpy() ,torch_output.numpy()) #True(2, 2, 2, 3) torch.Size([2, 2, 2, 3])
(2, 12) torch.Size([2, 12])
True技术交流与资料获取
技术要学会交流、分享不建议闭门造车。一个人可以走的很快、一堆人可以走的更远。
资料干货、数据、技术交流提升均可加交流群获取群友已超过2000人添加时最好的备注方式为来源兴趣方向方便找到志同道合的朋友。
技术交流、代码、数据获取方式如下 方式①、微信搜索公众号Python学习与数据挖掘后台回复交流 方式②、添加微信号dkl88194备注交流 我们打造了《100个超强算法模型》特点从0到1轻松学习原理、代码、案例应有尽有所有的算法模型都是按照这样的节奏进行表述所以是一套完完整整的案例库。
很多初学者是有这么一个痛点就是案例案例的完整性直接影响同学的兴致。因此我整理了 100个最常见的算法模型在你的学习路上助推一把
