📌 Видео
📌 Урок 1 / Урок2 / Урок3 / Урок4 / Урок5
📌 Colab
@tensorflowblog
Are you interested in diving deep into the world of machine learning and artificial intelligence? Look no further! The TensorFlow Telegram channel, with the username @tensorflowblog, is your go-to source for all things related to TensorFlow, Python, machine learning, AI, and more. With a community of like-minded individuals, this channel provides valuable resources, tips, tutorials, and discussions to help you stay updated and enhance your knowledge in the field. Whether you're a beginner looking to get started or an experienced professional seeking to expand your skills, this channel has something for everyone. Don't miss out on the opportunity to join the conversation and be part of this insightful community. For any questions or queries, feel free to reach out to the admin at @haarrp. You can also check out our affiliated channels like @pythonl for Python-related content, @ai_machinelearning_big_data for machine learning resources, @ArtificialIntelligencedl for AI updates, and @datascienceiot for insightful ML books. Join the TensorFlow Telegram channel today and take your knowledge to new heights!
30 Dec, 15:33
14 Dec, 16:19
11 Sep, 19:01
# Clone repository:
git clone https://github.com/TheMody/No-learning-rates-needed-Introducing-SALSA-Stable-Armijo-Line-Search-Adaptation.git
# Create & activate env:
conda env create -f environment.yml
conda activate sls3
# Install dependencies:
pip install pytorch numpy transformers datasets tensorflow-datasets wandb
# NOTE: custom optimizer is in \salsa\SaLSA.py,comparison version are in \salsa\adam_sls.py:
from salsa.SaLSA import SaLSA
self.optimizer = SaLSA(model.parameters())
# NOTE: typical pytorch forward pass needs to be changed to:
def closure(backwards = False):
y_pred = model(x)
loss = criterion(y_pred, y)
if backwards: loss.backward()
return loss
optimizer.zero_grad()
loss = optimizer.step(closure = closure)
02 May, 06:49
09 Apr, 16:58
29 Mar, 08:03
16 Mar, 09:27
14 Mar, 10:04
14 Mar, 09:49
13 Feb, 18:19
07 Feb, 11:42
TensorFlow GNN 1.0 (TF-GNN)
, проверенной на практике библиотеки для построения GNN в масштабе.03 Feb, 07:00
19 Jan, 04:58
06 Dec, 03:51
03 Dec, 02:14
17 Nov, 19:48
10 Nov, 21:27
04 Nov, 12:21