Jeff Heaton

6 ай бұрын

Introduction to Natural Language Processing and Hugging Face (11.1)

Пікірлер

@ApolytusКүн бұрын

I've done everything you do in the video exactly and yet I get a "False".

@jacobusstrydom70172 күн бұрын

Thanks man this was a good video. Nothing as frustrating as installing Tensorflow on windows.

@PuiuM3u2 күн бұрын

Can we use that video card to crack the passwords ? Like big library brute force atack 💙Please make a video abut 'it!

@theccieguy2 күн бұрын

Thanks Jeff

@thiagoamaralf2 күн бұрын

Thank you so much I feel so grateful for this course =)

@datalabwork2 күн бұрын

Watching your videos (old) somewhere 5 years ago, now I am having a few papers on it. Thank you for providing an interesting walk- around....🎉 Keep it up 💪

@crleon873 күн бұрын

One key step is: reboot before test the tf installation.

@TheOneShadyCat5 күн бұрын

The graphics are OK I guess..

@L_tlu6 күн бұрын

there is no option for background execution

@Miesiu6 күн бұрын

3:30 - What H/W go I need even with 1CPU but for 3pcs eg. RTX 3090 ?

@saribmalik9856 күн бұрын

Can I use a ryzen 5 3600 in biggener deep learning and ai It's weak but it allows me to get a 3060 in my budget

@syuxtun17347 күн бұрын

I'm new to this field. but i am very interested because i have been an opportunity to learn more in the I.T Field.

@user-ib3ps2qd4w7 күн бұрын

Stake players be like

@user-uq9cv3xe3v9 күн бұрын

Can somebody Please tell is it needed for the VS code C++ Step? I will code using Python only. So what is the need?

@arisioz10 күн бұрын

The infamous "Data Paralyzation"

@ElinLiu082311 күн бұрын

Hi Sir,i have watch the all content. So i have i quession: Is Quad TITAN V still can be use as a budget limit solution ?

@rolandmackintosh516313 күн бұрын

Can I get your keyboard model? I like the sound it makes! would like to buy one

@saranshbhandari157313 күн бұрын

This is awesome, I learned more from this video than my collage courses.

@saranshbhandari157313 күн бұрын

I have a doubt, how much time you have invested to rip apart the code completely and fully understand it?

@jamesf269714 күн бұрын

I am wondering is it better to buy a 40series or 2 20 or 30 series for ai?

@deepstatecia15 күн бұрын

What does it mean when they say an ai model (like for example gpt) has trillion parameters. is it trillion input nodes in the neural network or trillion question+answer cases fed into the model when trained?

@andrabotean16 күн бұрын

Hi Jeff, thanks for the great video! It was very helpful to me! I am struggling with an import from tensorflow, because the contrib module is deprecated. So I am wondering how I can make this code work? I also tried several suggestions from stackoverflow like downgrading tensorflow to a 1.x version which gives me an error. So I am wondering what the best solution might be? Thanks a lot! Andra import tensorflow as tf import numpy as np print(tf.__version__) from tensorflow.contrib.learn.python.learn.datasets import base # Data files IRIS_TRAINING = "iris_training.csv" IRIS_TEST = "iris_test.csv" # Load datasets. training_set = base.load_csv_with_header(filename=IRIS_TRAINING, features_dtype=np.float32, target_dtype=np.int) test_set = base.load_csv_with_header(filename=IRIS_TEST, features_dtype=np.float32, target_dtype=np.int) # Specify that all features have real-value data feature_name = "flower_features" feature_columns = [tf.feature_column.numeric_column(feature_name, shape=[4])] classifier = tf.estimator.LinearClassifier( feature_columns=feature_columns, n_classes=3, model_dir="/tmp/iris_model") def input_fn(dataset): def _fn(): features = {feature_name: tf.constant(dataset.data)} label = tf.constant(dataset.target) return features, label return _fn # Fit model. classifier.train(input_fn=input_fn(training_set), steps=1000) print('fit done') # Evaluate accuracy. accuracy_score = classifier.evaluate(input_fn=input_fn(test_set), steps=100)["accuracy"] print(' Accuracy: {0:f}'.format(accuracy_score)) # Export the model for serving feature_spec = {'flower_features': tf.FixedLenFeature(shape=[4], dtype=np.float32)} serving_fn = tf.estimator.export.build_parsing_serving_input_receiver_fn(feature_spec) classifier.export_savedmodel(export_dir_base='/tmp/iris_model' + '/export', serving_input_receiver_fn=serving_fn)

@KaijaKFanpages19 күн бұрын

I am SO FRUSTRATED that there is no native support. I do not think that I am ever willing to move into Linux world. Found it frustrating, overly difficult and taking long hours during the night in the university, so I basically gave up on Linux years and years ago. Maybe that was a mistake I now find, but I am just too damn old to move over anymore.

@jakobw13520 күн бұрын

Can you put two GPU's from TWO DIFFERENT MANUFACTURERS, and hook them up to the same monitor?

@windschattengeber20 күн бұрын

RL is already used to solve incredible hard problems. One of the most important application is its use in organic chemistry for retrosynthesis. Another example is path planning in the milling process (5-axis milling machines with more then one head). Or optimizing of the bin packing into containers. Until now it is only hard to do because the models are comparable slow learners, the way to success is less straight forward and you need to find a way to simulate or model the relevant part of the real world environment where the problem to solve exists. A breakthrough in RL would be in my eyes more exiting than the current one of LLM's.

@rildodemarqui21 күн бұрын

Well explained. Congrats!

@HeatonResearch22 күн бұрын

You can now do this directly in CoLab, without additional install: developer.nvidia.com/blog/rapids-cudf-instantly-accelerates-pandas-up-to-50x-on-google-colab/?ncid=ref-inor-177218

@nathanbanks235423 күн бұрын

Some real world robots are trained in a simulator using reinforcement learning which is pretty cool. But I guess this the self-driving car example only with hands and/or legs.

@zoe.tsekas23 күн бұрын

I do like RL a lot and can see so many applicable use cases. I have been using Ray, specifically RLlib as a framework that comes with some algos OOTB Dr. Heaton would love to see more material from your channel on RL!

@nicholasflower883623 күн бұрын

The master of everything ML! used to use your c# ML libraries in the 90s!

@xlr555usa23 күн бұрын

Im working on consumer grade gpus in parralel, with ollama3 > llama3. No one except Bill Gates can afford H100 gpus plus Im hearing many cloud companies are using old Nvidia Titan / 1080ti gpus. It is always best to use the same make of gpu with vram the same.

@jiteshprajapati3623 күн бұрын

yml file link is missing. please update

@MikeG-js1jt24 күн бұрын

Is it just me, your camera, or are your hands remarkably "tiny"

@TamannaIUrmi24 күн бұрын

Very helpful. The most helpful resource I found online on this topic.

@eranfeit26 күн бұрын

Very nice. Look at my video . This is not reinforcement learning, How ever , it use AI to run Atari games in a new cool and modern way : kzread.info/head/PLdkryDe59y4YaA2ZvUlF54g1U0J2BXkT9 Eran

@moravianlion310827 күн бұрын

Have anyone tried machine learning apps with ZLUDA on AMD cards? I run it in Blender, one of it's originally CUDA addon for terrain generation (Terrain Nodes) and also Automatic1111. AMDs are usually cheaper and on average have significantly more VRAM unlike their price range nvidia counterparts. ZLUDA works great on my 7900 xtx so far.

@TheFarmacySeedsNetwork29 күн бұрын

Thanks for the great explanation... I have 1 Quadro M5000 in... 2nd coming and SLI.... planning to switch to Nvlink eventually... Mostly do editing and big number crunching stuff. Installed a game to try it.... got bored playing in 5 minutes and went back to building... lol

@rssvg29 күн бұрын

"no reason to run this in linux" avoiding windows is a reason

@fisherh9111Ай бұрын

Panda bears are vegetarians who lay about and eat bamboo shoots. Polar bears are blood thirsty beasts that survive in some of the world’s harshest climates. Choose accordingly.