The GAN architecture employed in this study is an adaptation of ''pix2pix'' by Isola et al. [10] . A copy of pix2pix was obtained from GitHub (https://github.com/junyanz/ pytorch-CycleGAN-and-pix2pix.git) and implemented in Google Colaboratory (https://www.colab.research.google. com), a cloud service for the remote execution of hardware-intensive code. The network was trained on an Nvidia Tesla P100 16GB GPU for 250,000 iterations, i.e., the full training set was processed by the GAN 181.4 times. All hardware was hosted by Google Colaboratory.
Tesla p100 16gb gpu
Manufactured by NVIDIA
The Tesla P100 16GB GPU is a high-performance graphics processing unit (GPU) designed for data center and scientific computing applications. It features 16GB of HBM2 memory and is based on NVIDIA's Pascal architecture, delivering exceptional performance and energy efficiency for a wide range of compute-intensive tasks.
Automatically generated - may contain errors
Lab products found in correlation
4 protocols using tesla p100 16gb gpu
1
GAN-Based Image-to-Image Translation
2
Deep Learning Image Preprocessing on Linux
Check if the same lab product or an alternative is used in the 5 most similar protocols
+ Expand
Image preprocessing and deep learning models are implemented using MATLAB 2017b (MathWorks Inc., Natick, Massachusetts) environment. The execution of the network is performed on a Linux-based Intel Xeon Processors x86_64 (x86_64 indicates Intel Xeon 64-bit platform; architecture based on Intel 8086 CPU) with a CUDA-capable NVIDIA™ Tesla P100 16GB GPU.
3
Optimized Deep Learning for Multi-Label Image Classification
Check if the same lab product or an alternative is used in the 5 most similar protocols
+ Expand
For this study, we built three operation branch networks based on models: Resnet50 [40 ] and Densenet121 [53 ], which were pre-trained on ImageNet [54 ]. Fine-tuning was performed with those models. Adam [55 ] used the optimization algorithm. First, 100 epoch learning was performed, with early stopping occurring to prevent overfitting when the classification accuracy for a validation dataset was the highest. We also used grid search to seek the optimal parameters for the initial value of the learning rate. This search space was set as {10–5, 10–4,10–3}. To reduce the influence of the imbalanced data, the inverse ratios of the number of data were weighted respectively to the cross-entropy loss of the attention branch and the perception branch. In addition, a multi-label binary cross-entropy loss was used to train the NIH14 dataset. Furthermore, all images were augmented using gamma correction, horizontal flipping, rotation, and pixel shift. Images enhanced using these techniques are presented in Fig. 4 .![]()
Examples of augmented images. Left, original image. Middle left, gama correction. Middle, horizontal flip. Middle right, rotation. Right, pixel shift
4
Evaluating Neural Network Performance for Magnetic Pulse Prediction
Check if the same lab product or an alternative is used in the 5 most similar protocols
+ Expand
The NN construction, see Figure 1b, consisted only of an image input layer (size 64x64); three fully connected layers of sizes 4096, 3000, and 1278; and rectifier linear unit layers in between; and lastly a regression layer of size 1278, which constitutes the output and matches the size of the target.
The DL was done with the stochastic-gradient-descent-with-momentum algorithm in MATLAB 2018a (Mathworks, Natick, MA). Parameters like number of epochs, L 2 regularization, minibatch sizes, learn rate etc. are tabularized in Table 1. The parameters were investigated by starting from the MATLAB default value and if need be adjusted until a reasonable convergence was observed. Hence, our DL success criteria were elimination of overfitting and establishing convergence, and otherwise to use equal parameters for the NNs we compared directly.
The DL was run on a workstation with an NVIDIA Tesla P100 16GB GPU.
We generally use peak amplitudes and the NRMSE to evaluate performance of each trained NN by comparing actual and desired magnetizations derived from DL-predicted and TM-calculated pulses belonging to the test subset and with exemplar demonstrations. With the library size assessment, we also compare the NRMSE of DL-predicted pulses against TM-calculated pulses. For statistical assessment, we employed the Wilcoxon rank-sum test.
The DL was done with the stochastic-gradient-descent-with-momentum algorithm in MATLAB 2018a (Mathworks, Natick, MA). Parameters like number of epochs, L 2 regularization, minibatch sizes, learn rate etc. are tabularized in Table 1. The parameters were investigated by starting from the MATLAB default value and if need be adjusted until a reasonable convergence was observed. Hence, our DL success criteria were elimination of overfitting and establishing convergence, and otherwise to use equal parameters for the NNs we compared directly.
The DL was run on a workstation with an NVIDIA Tesla P100 16GB GPU.
We generally use peak amplitudes and the NRMSE to evaluate performance of each trained NN by comparing actual and desired magnetizations derived from DL-predicted and TM-calculated pulses belonging to the test subset and with exemplar demonstrations. With the library size assessment, we also compare the NRMSE of DL-predicted pulses against TM-calculated pulses. For statistical assessment, we employed the Wilcoxon rank-sum test.
About PubCompare
Our mission is to provide scientists with the largest repository of trustworthy protocols and intelligent analytical tools, thereby offering them extensive information to design robust protocols aimed at minimizing the risk of failures.
We believe that the most crucial aspect is to grant scientists access to a wide range of reliable sources and new useful tools that surpass human capabilities.
However, we trust in allowing scientists to determine how to construct their own protocols based on this information, as they are the experts in their field.
Ready to get started?
Sign up for free.
Registration takes 20 seconds.
Available from any computer
No download required
Revolutionizing how scientists
search and build protocols!