ນີ້ແມ່ນແອັບ Linux ທີ່ມີຊື່ວ່າ TensorNetwork ເຊິ່ງລຸ້ນຫຼ້າສຸດສາມາດດາວໂຫຼດໄດ້ເປັນ tensornetwork-0.4.6.tar.gz. ມັນສາມາດດໍາເນີນການອອນໄລນ໌ຢູ່ໃນ OnWorks ຜູ້ໃຫ້ບໍລິການໂຮດຕິ້ງຟຣີສໍາລັບບ່ອນເຮັດວຽກ.
Download and run online this app named TensorNetwork with OnWorks for free.
ປະຕິບັດຕາມຄໍາແນະນໍາເຫຼົ່ານີ້ເພື່ອດໍາເນີນການ app ນີ້:
- 1. ດາວໂຫຼດຄໍາຮ້ອງສະຫມັກນີ້ໃນ PC ຂອງທ່ານ.
- 2. ໃສ່ໃນຕົວຈັດການໄຟລ໌ຂອງພວກເຮົາ https://www.onworks.net/myfiles.php?username=XXXXX ດ້ວຍຊື່ຜູ້ໃຊ້ທີ່ທ່ານຕ້ອງການ.
- 3. ອັບໂຫລດແອັບພລິເຄຊັນນີ້ຢູ່ໃນຕົວຈັດການໄຟລ໌ດັ່ງກ່າວ.
- 4. ເລີ່ມ OnWorks Linux ອອນລາຍ ຫຼື Windows online emulator ຫຼື MACOS online emulator ຈາກເວັບໄຊທ໌ນີ້.
- 5. ຈາກ OnWorks Linux OS ທີ່ເຈົ້າຫາກໍ່ເລີ່ມຕົ້ນ, ໄປທີ່ຕົວຈັດການໄຟລ໌ຂອງພວກເຮົາ https://www.onworks.net/myfiles.php?username=XXXXX ດ້ວຍຊື່ຜູ້ໃຊ້ທີ່ທ່ານຕ້ອງການ.
- 6. ດາວນ໌ໂຫລດຄໍາຮ້ອງສະຫມັກ, ຕິດຕັ້ງມັນແລະດໍາເນີນການ.
ໜ້າ ຈໍ
Ad
TensorNetwork
ລາຍລະອຽດ
TensorNetwork is a high-level library for building and contracting tensor networks—graphical factorizations of large tensors that underpin many algorithms in physics and machine learning. It abstracts networks as nodes and edges, then compiles efficient contraction orders across multiple numeric backends so users can focus on model structure rather than index bookkeeping. Common network families (MPS/TT, PEPS, MERA, tree networks) are expressed with concise APIs that encourage experimentation and comparison. The library provides automatic path finding and cost estimation, exposing when contractions will explode in memory and suggesting better orders. Because it supports backends such as NumPy, TensorFlow, PyTorch, and JAX, the same model can run on CPUs, GPUs, or TPUs with minimal code changes. Tutorials and visualization helpers make it easier to understand how network topology affects expressive power and computational cost.
ຄຸນລັກສະນະ
- Graph-based API for nodes, edges, and contractions
- Automatic path finding and contraction-cost estimation
- Ready-made builders for MPS/TT, PEPS, MERA, and tree networks
- Pluggable backends: NumPy, TensorFlow, PyTorch, JAX
- Visualization utilities for network structure and flows
- GPU/TPU acceleration with identical high-level code
ພາສາການຂຽນໂປຣແກຣມ
Python
ປະເພດ
This is an application that can also be fetched from https://sourceforge.net/projects/tensornetwork.mirror/. It has been hosted in OnWorks in order to be run online in an easiest way from one of our free Operative Systems.
