Final models were generated using fast.ai v1.0.55 library (https://github.com/fastai/fastai ), PyTorch on two NVIDIA TITAN RTX GPUs. Initial experiments were conducted using NVIDIA Tesla V100s, NVIDIA Quadro P6000s, NVIDIA Quadro M5000s, NVIDIA Titan Vs, NVIDIA GeForce GTX 1080s, or NVIDIA GeForce RTX 2080Ti GPUs.
Quadro m5000
Manufactured by NVIDIA
The NVIDIA Quadro M5000 is a professional-grade graphics card designed for high-performance workstation applications. It features 8GB of GDDR5 memory, 2,048 CUDA cores, and a maximum power draw of 150W. The Quadro M5000 is capable of driving up to four 4K displays simultaneously.
Automatically generated - may contain errors
Lab products found in correlation
Titan rtx gpu, by NVIDIA (2 mentions)
Quadro p6000, by NVIDIA (2 mentions)
Titan vs, by NVIDIA (2 mentions)
Tesla v100, by NVIDIA (2 mentions)
Geforce rtx 2080 ti, by NVIDIA (2 mentions)
Workstation z840, by NVIDIA (2 mentions)
Hp workstation z840, by NVIDIA (2 mentions)
Rift cv1, by Oculus (1 mentions)
7 protocols using quadro m5000
1
Fast.ai Deep Learning Protocol
2
Fast.ai Deep Learning Protocol
3
High-resolution 3D Imaging and Analysis Protocol
4
Immersive Virtual Environment Projection
Check if the same lab product or an alternative is used in the 5 most similar protocols
+ Expand
The visual stimuli were projected onto a cylindrical, acoustically transparent screen using three projectors (NEC U321H). The projected arc encompassed 300°. A graphics card (Nvidia Quadro m5000) performed the warping necessary for projecting onto a cylindrical screen. This process was calibrated manually. The virtual visual environments were created in Blender (version 2.78a; Roosendaal, 1995 ) and were rendered using the built-in game engine of this software package. A simulation of movement parallax was added to potentially increase the presence and involvement of the participants. This changed the visual perspective according to the small sways and slight translations the participants made. The position of the virtual camera and the virtual listening position (see next section) were displaced by half of the physical displacement of the head to account for the displacement relative to the projection screen and loudspeakers. That is, a head translation of 10 cm would be equivalent to a camera/listening position translation of 5 cm in the virtual environments.
5
High-resolution 3D Imaging and Analysis Protocol
Check if the same lab product or an alternative is used in the 5 most similar protocols
+ Expand
Processing, data analysis, 3D rendering and video generation for the rest of the data were done on an HP workstation Z840, with 8 core Xeon processor, 196 GB RAM, and Nvidia Quadro k5000 graphics card and HP workstation Z840 dual Xeon 256 GB DDR4 RAM, nVidia Quadro M5000 8GB graphic card. We used Imaris, Amira, and Fiji (ImageJ2) for 3D and 2D image visualization. Tile scans were stitched by Fiji’s stitching plugin49. Stitched images were saved in tiff format and optionally compressed in LZW format to enable fast processing. We removed tiles with acquisition errors using Fiji’s TrakEM2 plugin and Imglib2library. In case of tiling errors in z dimension, we used TeraStitcher (Version, 1.10, https://abria.github.io/TeraStitcher/ ) with its default settings to globally optimize the tiled volumes and reconstruct the entire dataset. To increase the quality of the images we used the following functions in Fiji: to enhance the contrast of microglia cells (Fig. 1n and Supplementary Fig. 2a-f ) we used “Enhance Local Contrast (CLAHE)”, to equalize the images (Fig. 4a,b and Supplementary Fig. 2a-f ) we used “Pseudo Flat-Field Correction”, to enhance the contrast over the background of the axonal terminals in Fig 4c,d (yellow and green boxes) we used the custom-made macro for Fiji that we utilized to generate the pre-processed data for NeuroGPS-Tree (see next paragraph: Neuron tracing )
6
Virtual Reality Driving Simulation
Check if the same lab product or an alternative is used in the 5 most similar protocols
+ Expand
The experiment ran on a desktop with Intel(R) Xeon(R) CPU E5-1620 v4 (@ 3.5 GHz) processor, 16 GB RAM, NVIDIA Quadro M5000 graphics card, and Windows 10 Enterprise operating system. Unity version 5.5.0f3 Personal, combined with the Oculus Rift CV1 head-mounted display, integrated headphones, and a constellation tracking camera were used for providing the virtual environment at a resolution of 2,160 × 1,200 pixels.
Background noise and driving sounds were implemented. The driving sounds were the same for each vehicle. The frequency and the volume of the driving sound depended on distance and velocity.
Background noise and driving sounds were implemented. The driving sounds were the same for each vehicle. The frequency and the volume of the driving sound depended on distance and velocity.
7
Training Deep Learning Models on GPU
Check if the same lab product or an alternative is used in the 5 most similar protocols
+ Expand
We have trained our networks running on a single NVidia Quadro M5000 GPU and implemented our models with stochastic gradient descent with momentum in Torch7 (http://torch.ch ). Torch7 is a versatile numeric computing framework and machine learning library that extends Lua. We paid attention to exploring the hyperparameter space of models to identify a compact model with good generalization performance. Our experiments used momentum with a decay of 0.98. We used a learning rate of 0.002, and decayed every epoch using an exponential rate of 0.97.
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!