You are reading the article Oppo R11 Specs: All You Need To Know updated in December 2023 on the website Minhminhbmm.com. We hope that the information we have shared is helpful to you. If you find the content interesting and meaningful, please share it with your friends and continue to follow and support us for the latest updates. Suggested January 2024 Oppo R11 Specs: All You Need To Know
Of late, Oppo’s camera-centric phone dubbed as the R11 had been generating quite a lot of buzz. It had already visited a few certification sites including the 3C and TENAA before officially launching today.
Also, several image renders of the smartphone had popped up online revealing the design aspects of the Oppo R11. Now that the device has been officially announced in China, we have got clear idea about the specs of the device.
Hence we have created this all-you-need-to-know post about Oppo R11.
Oppo R11 Specs
If you observe carefully, you can see that most, if not all the Oppo smartphones look alike. Needless to say, Oppo has been taking design cues from Apple iPhone’s so far.
And the upcoming Oppo R11 doesn’t seem to be an exception to this trend. The handset, in the image renders and in the real life pictures, looks like a clear rip-off of the iPhone 7 Plus from the rear. In fact, the position, as well as the look of dual camera setup on the R11’s back, is quite identical to that of the Plus variant of current generation iPhone.
Again, when it comes to the front, the R11 looks like just any other Oppo handset. The home button which also doubles as the fingerprint scanner sits below the display and the usual array of sensors along with the front-facing camera sits above the screen.
The Oppo R11 features 5.5-inch AMOLED display. As far as the resolution is concerned, it gets a Full HD resolution. Don’t expect a bezel-less display here since the Oppo R11 is aimed to cater to the needs of mid-rage smartphone buyers.
There is another plus variant of Oppo R11. A Plus variant, as most of you, may already know, associates itself with a bigger display which will also be the case with the Oppo R11 Plus, which features 6inch Full HD AMOLED display.
There were myriad of leaks claiming that the Oppo R11 will come with Snapdragon 660 chipset. And only recently, the Chinese smartphone vendor, in a Weibo post, confirmed that the smartphone will indeed be powered by the recently unveiled Qualcomm Snapdragon 660 chipset. Now that the device is out in the open, obviously it is powered by Snapdragon 660 chipset. The chipset coupled with Adreno 512 GPU has Quad cores clocked at 2.2GHz and other Quad cores clocked at 1.8GHz.
For the unaware, the Snapdragon 660 chipset has also been built on the same 14nm process like the Snapdragon 625 chip. So, expect it to deliver higher power efficiency.
RAM and Storage
4GB of RAM is a norm of sorts these days on the mid-range smartphones which will also be the case with the Oppo R11.
So far, several rumors repeatedly suggested that the smartphone will get 4GB of RAM to work in tandem with the Snapdragon 660 chipset. And that is exactly what happened. Oppo R11 features 4GB RAM.
There will also be 64GB of onboard storage space available which should be decent enough to hoard a good number of multimedia files be it audio or video.
The Oppo R11 will ship with Android 7.1.1 Nougat-based ColorOS 3.1.
Design is not the only area where Oppo draws inspiration from Apple. The software aspects of the company’s smartphones are heavily inspired by Apple’s iOS. In fact, a few app icons such as the Settings, Music, Calculator look so similar that the resemblance is uncanny.
Okay, we know you have been eagerly waiting to get here since the camera is the major highlight of the Oppo R11. So, let’s get into details without wasting any time. Shall we?
The Oppo R11 features a 20MP+16MP dual camera setup on the back with dual-tone LED Flash. While 16MP camera will feature f/1.7 aperture, PDAF, 6P lens, Sony IMX398 sensor, secondary 20MP camera will feature f/2.6 aperture, 5P lens, Sony IMX350 sensor.
Also, Oppo has detailed in its Weibo post that the camera will get up to 10x (2x confirmed) optical zoom capabilities alongside other goodies like background blurring effect.
For selfie enthusiasts, there is a 20MP sensor at the front.
The Oppo R11 runs on 2,900mAh battery. Needless to say, the smartphone will offer support to the company’s VOOC Flash Charge technology which is claimed to offer two hours of talk time just on five minutes of charging.
Oppo R11 Plus
Like mentioned earlier, the Oppo R11 was unveiled in two variants. One is the standard Oppo R11 while the other is the Plus variant.
Now, as soon as we say a Plus variant, the first thing that pops into your head is a bigger display or a bigger battery or both. Well, you guessed it right. Those are the two areas in addition to RAM where the Plus variant differs from the regular variant.
Speaking of which, the Oppo R11 Plus features 6inch display with the same resolution, i.e. Full HD which can be considered as a slight letdown since you won’t get the same kind of crispness on the Plus variant as you would get on the standard 5.5-inch R11.
Another change, as mentioned above, is in terms of the battery capacity. The R11 Plus gets a significantly bigger 4,000mAh battery. Talking about RAM, the Plus variant gets 6GB RAM with same 64GB internal memory.
Apart from these changes, all the features are same as the standard variant.
You're reading Oppo R11 Specs: All You Need To Know
Motorola held a press event at its Chicago HQ on August 2 and out came the Moto Z3, the company’s 2023 flagship phone but with 2023-era specs. And no, this time there’s no Force variant, just like there was no standard variant in 2023.
As you may have guessed, the Motorola Moto Z3 is superior to the Moto Z3 Play that came out earlier and just like the Moto Z handsets before it, you can only get the Z3 in the U.S. via Verizon Wireless, the exclusive carrier.
Moto Z3 specs
6.01-inch 18:9 FHD+ AMOLED display
Qualcomm Snapdragon 835 processor
64GB expandable storage
Dual 12 + 12MP main camera
8MP front camera
Android 8.1 Oreo
Extras: Bluetooth 5.0, USB-C, NFC, Face unlock, side-mounted scanner, fast charging, water-repellant coating, Moto Display, Voice, Actions, etc.
A closer look at the Moto Z3 reveals quite some resemblance with the Moto Z3 Play. The design language is largely the same because, Moto Mods. Speaking of which, the Z3 was accompanied by a Moto Mod that adds 5G support to the device, which is pretty cool to have.
The two also share some specs such as the display screen, side-mounted fingerprint scanner, face unlock, missing 3.5mm audio jack in favor of a USB-C port, and dual-lens cameras on the back, although the Moto Z3’s setup is obviously superior. However, under the hood, this is easily a 2023 smartphone.
Related: Motorola Moto Z3 and Moto Z3 Play software update news2023 specs in a 2023 body
The Motorola Moto Z3 is an imitation of what LG has been doing in the recent past. The phone packs 2023 specs in a 2023 body and even though not necessarily a good thing, it has been reflected in the modest asking price for the device.
What this means is that you are not getting a Snapdragon 845, instead, the Moto Z3 has a Snapdragon 835 chipset. Unlike most 2023 flagship phones that have 6GB/8GB RAM modules and 128GB or more storage, the Z3 only gets 4GB of RAM and 64GB of storage, but it can be expanded up to 2TB. Note that the Moto Z2 Force got a 6GB RAM variant with 128GB of internal storage, things you won’t find on the Moto Z3. As noted earlier, you get the same display screen properties as the Moto Z3 Play, but the battery is a little bigger than the mediocre 2730mAh unit found in the Moto Z2 Force.
Like most phones in 2023, the Moto Z3 has a dual-lens camera on the back. Of course, the setup is better than the Play variant, especially the secondary lens that offers black and white shots and is expected to improve performance in low-light conditions. If anything, the dual 12MP setup on the Z3 is identical to the one used on the Moto Z2 Force and for the selfies, you get an 8MP unit.
In 2023, display screens on flagship phones are protected by the latest from Corning – Gorilla Glass 5, but on the Moto Z3 you’ll come across Gorilla Glass 3. Like the Moto Z3 Play and pre-2023 Sony Xperia flagship phones, the fingerprint scanner is side-mounted. The phone also supports facial recognition technology.
Moto Z3 price and availability
The Moto Z3 was unveiled on the second day of August 2023 and starts shipping on August 16th. As pointed out earlier, the phone will be sold through one U.S. carrier – Verizon Wireless. Given the fact that the Z3 has 2023 specs in a 2023 body, the price tag much reflects the former than the latter.
Related: The best Verizon phones to buy today
Verizon says you only need $20 per month for 24 months to grab the Moto Z3 off their shelves. If paying it outright, you only need $480. This is even cheaper than the Moto Z3 Play, which has a price tag of $500, making the Z3 one of the best deals you can get right now.
Motorola’s 5G Mod makes the Z3 future-proof, with the accessory expected to start shipping in early 2023. At the moment, there are no price details, but Motorola says it will be ready at the same time Verizon’s 5G network fully goes mainstream.
We’ve heard reports that HTC is planning to exit the Indian market – a market that is known for its power in budget and midrange smartphones. This implied that HTC could be doing away with the budget/midrange smartphone category and concentrate more on the high-end market, something we are not strangers to. However, the Taiwanese company still believes it has something to offer the midrange segment and it’s called the HTC U12 Life.
A quick look at the U12 Life reveals what looks like a blend between the Google Pixel and iPhone X, but it ditches the latter’s most controversial feature, the notch. Even more interesting is that unlike other HTC phones from the recent past, the U12 Life has gone back to the much-loved 3.5mm audio jack and the trending 18:9 aspect ratio is also on display.
Let’s check out the specs.
Related: The best HTC phones to buy right now
HTC U12 Life specs
6-inch 18:9 FHD+ LCD display
Qualcomm Snapdragon 636 processor
64GB expandable storage
Dual 16MP + 5MP main camera
13MP front camera
Android 8.1 Oreo
Extras: Bluetooth 5.0, NFC, USB-C, Dual-SIM, 3.5mm audio jack, rear-mounted scanner, etc.
As you may have guessed, we are looking at the successor to the HTC U11 Life and indeed it’s a real upgrade. The 2023 edition had a 5.2-inch display screen and a smaller 2600mAh battery while the Snapdragon 630 processor took care of matters under the hood. As for the HTC U12 Life, there’s a bigger 6-inch 18:9 panel with a full HD+ resolution, an even bigger 3600mAh battery unit and a more powerful Snapdragon 636 processor running the show.
HTC did great to include a USB-C port on the U11 Life but then shot itself in the foot by ditching the 3.5mm audio jack. The company has made amends for this move and on the U12 Life, both connectors are present, something that should make it a unique device in the company’s latest smartphone portfolio.
The HTC U12 Life has a dual-lens camera on the back and like many similar setups, the second sensor will be used to provide bokeh effects in photos. This is an effect where the background in a photo appears blurry in order to make the object outstanding, but unlike the premium U12+, there’s no second lens on the front panel, only a 13MP unit.
In terms of software, the HTC U12 Life runs Android 8.1 Oreo out of the box. Of course, it should be upgraded to Android Pie later on, but what remains unclear is whether we can look forward to an Android One version that has Pie out of the box, just like it happened last year, where the U.S. variant had Nougat out of the box while the rest of the globe got an Android One variant with Oreo preinstalled.
Related: These HTC phones will receive Android Pie
HTC U12 Life price and availability
At launch, the HTC U11 Life was valued at $349 and HTC isn’t changing a thing about this. Although it won’t be coming to the U.S., the HTC U12 Life will be sold at €349 in Europe and £299 in the UK. Availability begins in September and the device can be picked up in Moonlight Blue or Twilight Purple.
It will be interesting to see how the HTC U12 Life performs against other Snapdragon 636-powered smartphones that are essentially cheaper. Even more interesting is how the phone will go against superior midrangers with similar or much cheaper price tags, among them Xiaomi Mi A2, Nokia 7 Plus, and Xiaomi Poco F1, among others.
Reinforcement learning (RL) is the area of machine learning that is concerned with how software is able to take the right decision. The computer employs a trial and error method in order to find the best possible behavior or path that should be taken in a specific situation. Reinforcement learning is more or less a game-like situation. In order to enable the machine to do what is desired by the programmer, the artificial intelligence gets either rewards or penalties for the actions it performs. Ultimately, the goal is to maximize the rewards. Needless to say, this aspect of machine learning is the most effective way to hint at a machine’s creativity as of now. Consider an example wherein an autonomous vehicle is to be designed with a focus on parameters like minimizing the ride time, reducing pollution, obeying the traffic rules, etc. While coming up with this model, rather than relying on lengthy ‘if-then’ statements, reinforcement learning serves to be a savior. Here, the programmer would focus on preparing the reinforcement learning agent capable enough of learning from the system of rewards and penalties.How to get into this field?
This is one of the most exciting fields that has garnered attention from so many. For the ones looking to make a career in this, there’s no better time than now to get started.AWS Deepracer
Signing up for Deepracer will give you an access to a simulator. This further allows the user to select a track, code a reward function, and also adjust tuning parameters. With a default reward function with tuning parameters, one can start training the racer followed by evaluating its performance. AWS Deepracer is undoubtedly a great tool to get started and get acquainted with RL.Real-world examples
The best way to learn anything is to see how it applies to the real-world. With tons of real-world examples of business, academics, and government organizations experimenting as well as succeeding with this innovative aspect of machine learning, a lot can be learned and understood. Some real-life examples that can help in this aspect are – a grocery store that employs a personalized and recommendation engine that uses reinforcement learning, army deploying vehicles in different parts of the battle area, a robot playing sports, to name a few.Books
Needless to say, books are certainly one of the best ways to gain knowledge and expertise no matter what the field is. Some of the best books and papers to get going are –
The Basics of Deep Q Learning: With this book, one can surely gain command on Math and processes of Reinforcement Learning.
The Hierarchical Learning paper: This is handy especially for those who want to understand Hierarchical Learning in detail.
Deep RL: As evident as the name, this delves deeper into the subject.Applications of RL
Some of the applications of RL are in the areas of –
Bidding & Advertising
Supply Chain & Logistics
Load BalancingChallenges in RL
Scaling and tweaking the neural network that controls the agent
The agent performs the task as it is and not in the optimal or required way.
Preparing the simulation environment is yet another challenge faced.
Reinforcement learning (RL) is the area of machine learning that is concerned with how software is able to take the right decision. The computer employs a trial and error method in order to find the best possible behavior or path that should be taken in a specific situation. Reinforcement learning is more or less a game-like situation. In order to enable the machine to do what is desired by the programmer, the artificial intelligence gets either rewards or penalties for the actions it performs. Ultimately, the goal is to maximize the rewards. Needless to say, this aspect of machine learning is the most effective way to hint at a machine’s creativity as of now. Consider an example wherein an autonomous vehicle is to be designed with a focus on parameters like minimizing the ride time, reducing pollution, obeying the traffic rules, etc. While coming up with this model, rather than relying on lengthy ‘if-then’ statements, reinforcement learning serves to be a savior. Here, the programmer would focus on preparing the reinforcement learning agent capable enough of learning from the system of rewards and chúng tôi is one of the most exciting fields that has garnered attention from so many. For the ones looking to make a career in this, there’s no better time than now to get started.Signing up for Deepracer will give you an access to a simulator. This further allows the user to select a track, code a reward function, and also adjust tuning parameters. With a default reward function with tuning parameters, one can start training the racer followed by evaluating its performance. AWS Deepracer is undoubtedly a great tool to get started and get acquainted with chúng tôi best way to learn anything is to see how it applies to the real-world. With tons of real-world examples of business, academics, and government organizations experimenting as well as succeeding with this innovative aspect of machine learning, a lot can be learned and understood. Some real-life examples that can help in this aspect are – a grocery store that employs a personalized and recommendation engine that uses reinforcement learning, army deploying vehicles in different parts of the battle area, a robot playing sports, to name a few.Needless to say, books are certainly one of the best ways to gain knowledge and expertise no matter what the field is. Some of the best books and papers to get going are –Some of the applications of RL are in the areas of –The crux of RL is how the agent is trained. Reinforcement learning is, without a doubt, cutting-edge technology and has the potential to transform the world. It is one of those ways that can make a machine creative
The MWC 2023 has been one interesting place to be. Besides the plenty of 5G-related announcements, the Spanish city of Barcelona has also given us a treat to some of the future innovations in the smartphone industry – the foldable phones.
First on stage was Samsung with the Galaxy Fold that was received by a raucous crowd. With its inward-folding design that leaves a mere 4.6-inch screen on a single panel, the Fold doesn’t look like a great device in this age of 6-inch screens and given Samsung’s lead in the smartphone business, this wasn’t a good sign going forward.
But then came Huawei with what looks like a better take on foldable phones’ design – the Huawei Mate X. The screen folds on the outside leaving users with plenty of display real estate on not just one but two panels as well as nearly no bezels. The screen becomes even much bigger when unfolded.
Huawei Mate X specs
Unfolded: 8-inch 8:7 AMOLED foldable display (2480 x 2200, 414ppi)
Folded: Dual-screen 6.6-inch 19.5:9 AMOLED display (2480 x 1148) + 6.38-inch 25:9 AMOLED display (2480×982)
Kirin 980 processor
Balong 5000 5G modem
512GB expandable storage, up to 256GB
Tri-lens main camera: 40MP (wide-angle) + 16MP (ultra-wide) + 8MP (telephoto)
Android 9 Pie with EMUI 9.1.1
Extras: 5G connectivity (1GB movie in 3 seconds), 55W Huawei SuperCharge (85% in 30 minutes), NPU, NFC, Fingerprint in power button, USB-C, Bluetooth 5.0, etc.
This massive unit can take ages to charge from 0-100% with standard charging technology, but Huawei has something else it calls Super Charge, promising an impressive 55W fast charging to juice the unit from 0-85% in just 30 minutes.
The thicker phone edge houses a quad-lens camera setup and since the lenses are aligned on the edge, the phone doesn’t essentially have distinct front and back cameras. But when the phone is folded, screens appear on either side, meaning you can still capture a perfect selfie. This same edge also houses the USB-C port and a power button that also doubles up as a fingerprint scanner.
How Huawei managed to make the Mate X such a thin phone still amazes. When unfolded, it measures just 5.4mm thick. Look around and when you find a thinner smartphone than this, pat us on the back. Even the 11mm thickness when folded is still ideal in the current setup.
What makes this whole design story about the Huawei Mate X such interesting is the fact that the devices shown on stage are still early designs. That said, we are likely to see a more complete product when the handset arrives later this year.
Huawei Mate X pricing and availability
Speaking of which, the Huawei Mate X is expected to be ready for commercial adoption in mid-2023 priced at a staggering €2,299. This would make it one of the most expensive smartphones yet, but to further justify this price tag, Huawei has included a 5G modem in the handset, becoming the first from the company to offer crazy fast internet speeds.
The phone is coming to Europe, but the exact market availability will depend on how 5G-ready these markets are. The phone has been confirmed to come in one paint job – Interstellar Blue.
Related: Foldable Android Phones: How popular OEMs stand at the moment
This article was published as a part of the Data Science BlogathonTable of Contents:
What is CNN, Why is it important
Fundamentals of CNN
Various Convolutional Neural Networks
Data Augmentation and Transfer Learning
Code example using Keras
Ever since I learned about CNN, it has become one of my favorite topics in Deep Learning, so in this article, I am going to explain everything related to CNN. “Using this we can provide machines with vision. Now vision, I believe is one of the most important senses that we pose. Sighted people rely on vision for everyday tasks such as navigation, recognize objects, recognize complex human emotions and behavior” these are some of the words of Professor Alexander Amini from ‘MIT Introduction to Deep Learning 6.S191’. Since CNN has been specifically designed for visual tasks (say object recognition) so I can say that CNN is a type of Neural Network that is most often applied to image processing problems.
It can be used to detect and recognize faces, can be used in the medical sector to classify various diseases instantly, another example where CNN can be used is autonomous/self-driving cars.Biological Inspiration
Photo by MIKHAIL VASILYEV on Unsplash
Let’s try to understand this from the historical perspective first. Hubel and Wiesel, two neuroscientists who got their Nobel prize in medicine mostly focused their research on visual tasks, so in an experiment done in 1959, they anesthetized a cat and inserted a microelectrode into its primary visual cortex. They then project a series of light bars on the screen installed in front of the cat. Interestingly they observed that some neurons showed some activity when this light bar was presented at a specific angle while other neurons got activated to some different angle of light bars. What they found was that there were different neurons for different tasks such as edge detection, motion detection, depth detection, and so on. CNN is inspired by this biological idea and research done on this area.
Having known the basic idea of CNN le us try to understand it in more detail.Fundamentals of CNN 1. Convolution
As you might have guessed from the name itself convolution convols/merge two functions or information to produce a third function/information.
Let’s consider this gray-scaled image of 6×6 dimensions. Since the machine can only understand binary language, this image would appear to be a 6×6 matrix with all 0s on the left half and all 255 on the right half, since it is a grayscale image. The RHS 3×3 matrix is known as kernel/ filter/ mask/ operator, and the * operator is a convolution operator (here it is Sobel edge detector). We now have a 4×4 matrix after doing component-wise multiplication and addition. When we normalize this matrix, we receive an image with an edge highlighted in it.2. Padding (p)
What if we want the output matrix to have the same dimensions as the input matrix i.e. (nxn). If you substitute n = 6 from the above formula, you will get an output matrix of size 4×4. If you want the output matrix to be of size 6×6 then it is quite obvious that the input matrix should be of size 8×8, so to change the dimensions of the input matrix, there is a concept of padding. If a pad one extra layer to each side then the initial dimension would be increased by 2 i.e. now n = 8 which will give the output matrix dimension to be 6.
Now the question arises what value should I fill this extra layer with?
There are two approaches to it:
Zero – Padding
Same-value Padding3. Stride (s)
Basically, the stride is nothing but shifting a kernel matrix over the input matrix by a specific number of cells at a time. It helps to reduce the size of the output matrix.
Finally, the formula combining all these would be: (n x n) * (k x k), padding = p, stride = s ⇒ (((n – k + 2p)
NOTE: Here Convolution in Color Images
So far we have looked at the convolution operation, padding, and stride on a greyscale image, what if the image is a colorful image? A color image can be represented as a 3D tensor since it has 3 matrices of Red, Green, and Blue stacked on top of each other. These RGB matrices are often referred to as 3 channels since most of the concepts in image processing are derived from signal processing in electronics and telecommunications major. Hence we can represent this 3D tensor as NxMxC where C is the no. of channels which is equal to 3 for color images.
Similar to the convolution in 2D matrices, convolution in 3D matrices is also component-wise multiplication followed by addition. One thing to keep in mind here is that the kernel should also have the same number of channels as the input matrix.
Formula: (N x N x C) * (K x K x C) ⇒ (N – K + 1) x (N – K + 1) x 1
NOTE: Convolution of a 3D matrix results in a 2D matrix.Convolution layer
Unlike image processing where we use predefined kernels like the Sobel edge detector, in CNN we try to learn these kernels.
Here in CNN, we have multiple hyperparameters to play with, like kernel size K, padding p, stride s, and the number of kernels M.
In a real-world scenario, we have a series of convolution layers to train first the low-level features like edges, then mid-level features, then high-level features to get a fairly accurate model.Max-pooling
It is again a biologically inspired concept that introduces some invariance in the model. For example, the model should be in a position to detect a face in an input image no matter where it is located and no matter what its size is. This is achieved using pooling layers.
This is similar to the kernel we have seen above, here also we can apply the concept of strides, kernel size, etc.
Here in this example, we have a 2 x 2 max-pool kernel with stride as 2. It selects the maximum value from a patch. Another pooling is the mean/average pooling where we get the average value instead of the maximum value.Various Convolutional Neural Networks:
Inception Network, 2023
Before we move on to the code part, it is important that we understand what Data Augmentation and Transfer Learning mean.Data Augmentation
Since everyone wants their model to be a robust model but creating such a model would require a huge amount of data so Data Augmentation comes to the rescue here. It basically means adding more data to our dataset by rotating, scaling, cropping, flipping, shifting horizontally or vertically, zooming, stretching (shear operation), illumination conditions, etc on images (since CNN) to create more artificial data to train on.Transfer Learning
The main idea is to use a pre-trained model (which is trained on some dataset ‘X) on a dataset ‘Y’ without training it from scratch. Both in Keras and Tensorflow we have some pre-trained models like VGG16 that is trained on one of the largest object classification datasets ImageNet contained 1000 different categories and the total dataset size is 150GB.
Here we can use transfer learning in various ways like using Bottleneck features (i.e. taking output just at the flattening layer) or by freezing the initial layer that detects only edges, shapes, etc. and changing/learning the last few layers according to the new dataset or use the pre-trained model as the initial model to fine-tune the complete model based on the new dataset.Let’s Code from __future__ import print_function import keras from keras.datasets import mnist from keras.models import Sequential from keras.layers import Dense, Dropout, Flatten from keras.layers import Conv2D, MaxPooling2D from keras import backend as K batch_size = 128 num_classes = 10 epochs = 12 # input image dimensions img_rows, img_cols = 28, 28 # the data, split between train and test sets (x_train, y_train), (x_test, y_test) = mnist.load_data() if K.image_data_format() == 'channels_first': x_train = x_train.reshape(x_train.shape, 1, img_rows, img_cols) x_test = x_test.reshape(x_test.shape, 1, img_rows, img_cols) input_shape = (1, img_rows, img_cols) else: x_train = x_train.reshape(x_train.shape, img_rows, img_cols, 1) x_test = x_test.reshape(x_test.shape, img_rows, img_cols, 1) input_shape = (img_rows, img_cols, 1) x_train = x_train.astype('float32') x_test = x_test.astype('float32') x_train /= 255 x_test /= 255 print('x_train shape:', x_train.shape) print(x_train.shape, 'train samples') print(x_test.shape, 'test samples') # convert class vectors to binary class matrices y_train = keras.utils.to_categorical(y_train, num_classes) y_test = keras.utils.to_categorical(y_test, num_classes) model = Sequential() model.add(Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=input_shape)) model.add(Conv2D(64, (3, 3), activation='relu')) model.add(MaxPooling2D(pool_size=(2, 2))) model.add(Dropout(0.25)) model.add(Flatten()) model.add(Dense(128, activation='relu')) model.add(Dropout(0.5)) model.add(Dense(num_classes, activation='softmax')) optimizer=keras.optimizers.Adadelta(), metrics=['accuracy']) model.fit(x_train, y_train, batch_size=batch_size, epochs=epochs, verbose=1, validation_data=(x_test, y_test)) score = model.evaluate(x_test, y_test, verbose=0) print('Test loss:', score) print('Test accuracy:', score)
The media shown in this article are not owned by Analytics Vidhya and are used at the Author’s discretion.
Update the detailed information about Oppo R11 Specs: All You Need To Know on the Minhminhbmm.com website. We hope the article's content will meet your needs, and we will regularly update the information to provide you with the fastest and most accurate information. Have a great day!