Gtx 970

Manufactured by NVIDIA

Sourced in United States

The NVIDIA GTX 970 is a high-performance graphics processing unit (GPU) designed for desktop computers. It features 1,664 CUDA cores, a base clock speed of 1,050 MHz, and 4GB of GDDR5 video memory. The GTX 970 is capable of delivering excellent graphics processing power for a variety of professional and consumer applications.

Automatically generated - may contain errors

Lab products found in correlation

Brainproducts 5 amp 16, by Brain Products (1 mentions) Core i5 6600k, by NVIDIA (1 mentions) Cuda 7, by NVIDIA (1 mentions)

Spelling variants of this product

GeForce GTX 970 (12 citations)

4 protocols using gtx 970

Automated Muscle Segmentation via U-Net

Check if the same lab product or an alternative is used in the 5 most similar protocols

For each of the 12 ROIs, a distinct U-Net neural network (6-layer depth) was created and trained using Matlab DeepLearning Toolbox extension. The training was performed on a NVIDIA GTX 970 (4 GB DDR) CPU. The initial learning rate was set at 10⁻³, using the Adam optimizer, with a maximum of 300 epochs. The output of all 10 CNN trained for automatic segmentation of muscle groups, was pooled to constitute the muscle ROI. The DLASA was then confirmed on the 49 slices of the testing set. The automatic segmentation performance was evaluated using Dice’s formula as previously published [14 (link),28 (link)]:

D i c e = \frac{2 (A \cap M)}{A + M}

where A corresponds to the automatic segmentation matrix, M the manual segmentation matrix, and ∩ the intersection.

Jullien M., Tessoulin B., Ghesquières H., Oberic L., Morschhauser F., Tilly H., Ribrag V., Lamy T., Thieblemont C., Villemagne B., Gressin R., Bouabdallah K., Haioun C., Damaj G., Fornecker L.M., Schiano De Colella J.M., Feugier P., Hermine O., Cartron G., Bonnet C., André M., Bailly C., Casasnovas R.O, & Le Gouill S. (2021). Deep-Learning Assessed Muscular Hypodensity Independently Predicts Mortality in DLBCL Patients Younger Than 60 Years. Cancers, 13(18), 4503.

+ Open protocol

+ Expand

Birdsong Recognition Using DCNN

Check if the same lab product or an alternative is used in the 5 most similar protocols

All computations and sound recording were implemented in the custom written java and cuda program. The source code is available at https://github.com/takuya-koumura/birdsong-recognition. Training of the DCNN and recognition were conducted using cuDCNN library on graphic processors (GTX 970 or 980, NVIDIA, United States).

Koumura T, & Okanoya K. (2016). Automatic Recognition of Element Classes and Boundaries in the Birdsong with Variable Sequences. PLoS ONE, 11(7), e0159188.

+ Open protocol

+ Expand

Immersive Virtual Environment Experiment

Check if the same lab product or an alternative is used in the 5 most similar protocols

The virtual environment was rendered in Unreal Engine 4.12 (Epic Games, Cary, NC, United States) using assets from the Open World Demo Collection and was displayed on a HTC Vive (HTC, New Taipei City, Taiwan) with a resolution of 1080 pixels × 1200 pixels per eye at 90 Hz, and a 100° field of view. The experiment ran on a Windows 10 64-bit machine with an Intel Core i5-6600k, 16 GB RAM and a Nvidia GTX 970. A Sennheiser HD 439 (Sennheiser, Wedemark-Wennebostel, Germany) was used for audio presentation. Physiological signals (electrodermal activity, electrocardiogram) were recorded by a Brainproducts V-AMP 16 and the Vision Recorder 1.2 software (Brain Products, Munich, Germany).

Gromer D., Reinke M., Christner I, & Pauli P. (2019). Causal Interactive Links Between Presence and Fear in Virtual Reality Height Exposure. Frontiers in Psychology, 10, 141.

+ Open protocol

+ Expand

Cone-Beam CT Reconstruction Benchmarks

Check if the same lab product or an alternative is used in the 5 most similar protocols

Icon uses a 780 × 720 pixel flat panel detector, with resolution of 0.368 × 0.368 mm². In all scans 334 projections are acquired from about 200° rotation around the phantom or patients. The reconstructed images have 448 × 448 × 448 voxels with size of 0.5 × 0.5 × 0.5 mm³. The images used in this paper include a CatPhan 503 (The Phantom Laboratory, Inc., Salem, NY, USA) scanned in Elekta (Stockholm, Sweden) at 90 kVp and 25 mA × 40 ms projections, and 11 clinical SRS images scanned in University Hospital La Timone (Marseille, France), at 90 kVp and 10 mA × 40 ms projections. It should be noted that the source of clinical images used in the present study was the same source as the study described in previous SDIR work.3To accelerate the reconstruction, all methods are implemented in‐house with CUDA to run on an NVIDIA GPU (GTX970, CUDA7.5), and are compiled with Matlab as MEX files. The natively reconstructed images from the Icon system were generated using filtered backprojection (FBP) with a standard FDK approach12 and are denoted as “FDK” throughout the Results section. For more details on the reconstruction implementation, the readers are referred to previous SDIR work.3

Hashemi S., Huynh C., Sahgal A., Song W.Y., Nordström H., Eriksson M., Mainprize J.G., Lee Y, & Ruschin M. (2018). Cone‐Beam CT image contrast and attenuation‐map linearity improvement (CALI) for brain stereotactic radiosurgery procedures. Journal of Applied Clinical Medical Physics, 19(6), 200-208.

+ Open protocol

+ Expand

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?

Revolutionizing how scientists
search and build protocols!