- Видео 27
- Просмотров 8 441
Anil Bhatt
Добавлен 26 сен 2008
ImageAlchemy StableDiffusion Demo
Huggingface link for this app : huggingface.co/spaces/neuralorbs/ImageAlchemy-StableDiffusion
Просмотров: 2
Видео
Pythia Dialog Gen App Demo
Просмотров 18Год назад
Huggingface link for this app : huggingface.co/spaces/neuralorbs/DialogGen
GPT Passage Generator -NanoGPT Demo
Просмотров 46Год назад
Huggingface link for this video : huggingface.co/spaces/anilbhatt1/GPT-Passage-Generator
Fastsam Segmenter Demo
Просмотров 49Год назад
Huggingface Link for this app : huggingface.co/spaces/anilbhatt1/FastSAM-Segmenter
Controlnet Stable Diffusion Canny Demo
Просмотров 57Год назад
Huggingface spaces link : huggingface.co/spaces/neuralorbs/Controlnet-Stable-Diffusion
Clip Image Search HF app demo
Просмотров 11Год назад
Link to huggingface app : huggingface.co/spaces/anilbhatt1/CLIP-Image-Search
Jnana Huggingface Spaces Demo
Просмотров 63Год назад
- Jñāna-Phi2-Multimodal-Conversation-Agent is a gradio app hosted on huggingface spaces - huggingface.co/spaces/neuralorbs/Jnana-Phi2-Multimodal-Conversation-Agent - Github : github.com/anilbhatt1/Jnana_phi2_multimodal_llm - Detailed Blog : tinyurl.com/jnana-blog - Jñāna is capable of accepting inputs in the form of image/audio/text or a combination of any of these 3 - Jñāna uses microsoft/phi2...
phi2 dialog gen - Hugging face space built on microsoft/phi-2 qlora optimized AI model
Просмотров 141Год назад
Video of hugging face space that uses qlora optimized microsoft/phi-2 model. Model was fine-tuned on openassistant-guanaco dataset. phi-2 is a small language model with 2.7b parms. qLORA is a fine-tuning technique where original model's parameters are first quantized to 4-bit values & frozen. Then LORA adapters are injected into model's layers. While fine-tuning, only adapter weights that are i...
Car driving with T3D (Twin Delayed Deep Detereministic Policy Gradient)
Просмотров 10Год назад
This is the video of a car driving through the streets trained using Twin Delayed Deep Detereministic Policy Gradient (popularly called T3D) -a reinforcement learning technique. Github : github.com/anilbhatt1/ERA1_S25_T3D_With_Car
Reinforcement Learning with Q DeepLearning Networks
Просмотров 215Год назад
Github link : github.com/anilbhatt1/ERA1_S24_QLearning_With_Car This 3 minute video shows our RL agent (car) learning to navigate from point to point using Q Learning - a reinforcement learning technique. Q learning here uses a fully connected deep learning network. Deep learning network predicts Q states based on which 3 actions are taken by the agent - move forward, turn left or turn right . ...
V5-Create Codepipeline-Automatic Deployment to EC2
Просмотров 2022 года назад
In this video, we are creating a codepipeline that will help to automatically deploy the code changes to EC2 individual instance. Code change is done and upon git push to AWS codecommit repo, code pipeline gets automatically triggered that will take care of deployment. No need to do AWS CLI push and manually create deployment if codepipelines are enabled. Reference article to set-up AWS code pi...
V4-Create Deployment-AWS Push to S3-Manual Deploy to EC2
Просмотров 2282 года назад
In this video, - Deployment Group is created with EC2 instance (correct region) created in previous video V3. - Code is pushed to S3 bucket via AWS CLI command for the application (correct region) - Create deployment to use the S3 revision tag obtained from previous step - Deploying to EC2 individual instance. This is a manual deployment as deployment is created manually. Github reference for c...
V3 Failed AWS CLI S3 Push EC2 Relaunch with existing Keypair
Просмотров 1642 года назад
In this video, we create an application but in wrong region. Also, EC2 instance created in earlier video V2 was in wrong region. Due to the same, AWS CLI push to S3 bucket keeps failing. Hence, EC2 instance is terminated and recreated in correct region. Then this EC2 instance is launched with existing keypair. Github reference for code : github.com/anilbhatt1/emlo_s11_ec2_autoscale_codepipeline...
V2-EC2 Connect-EC2 Prerequisites-Push to Codecommit Repo
Просмотров 3762 года назад
In this video, following items are demoed: - Connect to EC2 instance created in V1. Newly downloaded keypair was used to connect via Ubuntu instance hosted in WSL. - Installing npm prerequisites to make EC2 machine ready to host the application - Pushing the application files to AWS codecommit repo created in V1 Github reference for code : github.com/anilbhatt1/emlo_s11_ec2_autoscale_codepipeli...
V1-Codecommit-S3-IAM Roles-EC2 Instance
Просмотров 1,2 тыс.2 года назад
V1-Codecommit-S3-IAM Roles-EC2 Instance
V7-Modify Deployment Group-Automate Deployment to Autoscale Instances
Просмотров 1622 года назад
V7-Modify Deployment Group-Automate Deployment to Autoscale Instances
V6-Create Autoscale Groups-AMI-Launch Config-Load Balancer -Target Grp
Просмотров 1302 года назад
V6-Create Autoscale Groups-AMI-Launch Config-Load Balancer -Target Grp
Part 3 CIFAR100 Resnet34 Training & Inferencing with 4 GPUs AWS Sagemaker Instance and WANDB logging
Просмотров 2312 года назад
Part 3 CIFAR100 Resnet34 Training & Inferencing with 4 GPUs AWS Sagemaker Instance and WANDB logging
Part 2 CIFAR100 Pytorch Lightning Training in Colab
Просмотров 8912 года назад
Part 2 CIFAR100 Pytorch Lightning Training in Colab
Part 1 AWS Sagemaker Notebook Instance Creation
Просмотров 3892 года назад
Part 1 AWS Sagemaker Notebook Instance Creation
CIFAR100 training using Pytorch Lightning on AWS Sagemaker Spot Instance with 4 GPUs
Просмотров 4543 года назад
CIFAR100 training using Pytorch Lightning on AWS Sagemaker Spot Instance with 4 GPUs
Finding Nemo Video Yolov3 Output With Audio
Просмотров 3914 года назад
Finding Nemo Video Yolov3 Output With Audio
But these filters (colored blocks) should have the same depth as the input, so they should be represented as a 1 x 1 x input_depth Matrices.
you ruined it by rotating the axis
P r o m o S M 😂
why not share the code bro?
wow.
Can you share the code?
This 30 seconds is amazing. Been spending hours trying to actually see an example of how 1x1 conv reduces dimensions to a fixed number of output channels. Thank you!!!!
Thank you so much for such a wonderful tutorial. Well explained.
promosm 😭
I tried the whole thing. My changes are getting reflected in every instance other than the original one after autoscaling. What could be the reason? The security group is the same as other instances.
Can you please add tutorials on step functions and lambda?
Why did you choose ipv4 instead of ipv6 for the inbound rules?
Very nice and extremely helpful!
Thanks for the detailed video
It would be helpful if you could add the link to the repo for the nodejs code so that people who watch this can replicate the steps with ease
Hi , nodejs code can be found in the github repo provided in video description.
Could you please copy paste autodeploy commands in the commentbox?
Hi, Added a new file 'commands.txt' that lists out all the command used in the playlist. You can find this in github repo provided in the description.
Hi! Thank you so much for your video! may I know how long the training took?
Awesome 👍