Analyzing Models with TensorBoard - Deep Learning with Python, TensorFlow and Keras p.4

[@chtouroumahdi5990]

My day routine : 1) Open youtube 2) Check sentdex new tutorials !! Thank you for this amazing work !!

[@kastin83]

Wow hitting CMD from file explorer path just saved me a huge amount of time, no more batch files. awesome shortcut. thanks for the tip!

[@ozan3550]

if you get a "Failed to create a directory" error as a windows user i fixed it by changing "/" to "\\" in log_dir.its looks like this now = TensorBoard(log_dir=" C:\\logs\\{}".format(NAME))

[@rabieamelad1513]

thank you very much, your comment save my life

[@asyrafzlkln1701]

Thanks alot bro :)

[@ongliyan2880]

thanks

[@apremgeorge]

That awesome share man, you saved the day

[@apremgeorge]

Also we can use without format Name = f"tfModels-{int(time.time())}" tensorboard = TensorBoard(log_dir=f"logs\\{Name}")

[@henryhsueh3553]

The best tutorial ever! BTW, for 2020 mac user, if you cannot run the: tensorboard --logdir=logs/, use the pip install grpcio==1.24.3

[@scootscoot2k]

"I really hope that didnt kill my recording"... doesnt check :P This video series is great btw!

[@sentdex]

Can't check without hitting stop. Then I'd have to... *shudders* edit. Might as well just finish and hope for the best :D

[@scootscoot2k]

up next teach charles to edit? that actually would be super cool

[@dmmd5329]

If you get "ValueError: Failed to find data adapter that can handle input" use import numpy as np X = np.asarray(pickle.load(open("X.pickle", "rb"))) y = np.asarray(pickle.load(open("y.pickle", "rb")))

[@bibimylosam]

You are a lifesaver bro. Thanks for the help!

[@shauryavardhan7225]

You effin Lifesaver !! THANK YOU!

[@contractorwolf]

seriously, that was the best explanation for how to use tensorboard, thx

[@LucidProgramming]

Great video as always, Harrison. Thank you very much for taking the time to make such high-quality content. Cheers.

[@IgnacioErro]

7:42 "one more time" -> "un mas tiempo" LOL! Nice tutorial!

[@felixsnz7764]

una vez mas

[@houdadj8747]

if you get a AttributeError: module 'tensorflow' has no attribute 'Session' / or ConfigProto / or GPUOptions then you must change it to : tf.compat.v1.GPUOptions /tf.compat.v1.Session/tf.compat.v1.ConfigProto

[@alokkr029]

where I have to do this change

[@honedippo]

@@alokkr029 gpu_options = tf.compat.v1.GPUOptions(per_process_gpu_memory_fraction=0.333) sess = tf.compat.v1.Session(config=tf.compat.v1.ConfigProto(gpu_options = gpu_options))

[@cabezaotomi]

"One more time" -> "Un maś tiempo" wrong -> "Una vez más" right Awesome tutorial series man :D

[@sentdex]

So imma be prob still sayin un mas tiempo still xD. It's official Sentish language, sir!

[@Glatium]

for window user remove "/" for tensorflow directory path to tensorboard = TensorBoard(log_dir="logs{}".format(NAME)) . At the beginning kindly include log_dir = os.path.join( "logs", "fit", datetime.datetime.now().strftime("%Y%m%d-%H%M%S"), )

[@Evan_242]

Really really useful ,thank you Harrison, you're awesome.

[@virajdattkohir4767]

Was eagerly waiting for this, thank you @sentdex !!

[@sentdex]

Happy to share!

[@jonathangerard745]

Thank You Sir, this tutorial helped me a lot!!! I really am a big fan of your videos.

[@dxamphetamin]

are you planning on doing something about genetic/evolutionary algorithms? In future, maybe evolutionary neural nets?

[@bernardoolisan1010]

if u are having this issue --------------------------------------------------------------------------- AttributeError Traceback (most recent call last) in 9 10 # this for run many models on the same time, by fractioning the vram u use, like an object detection ---> 11 gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.333) 12 sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options)) 13 AttributeError: module 'tensorflow' has no attribute 'GPUOptions' Try using this gpu_options = tf.compat.v1.GPUOptions(per_process_gpu_memory_fraction=0.333) sess = tf.compat.v1.Session(config=tf.compat.v1.ConfigProto(gpu_options=gpu_options))

[@sina7190]

Thank you so much this part helped A LOT.

[@praveshbudhathoki736]

got errors in cmd while running (tensorboard --logdir = logs/) then, use this that worked for me (tensorboard --logdir logs)

[@arcturus1140]

Me to

[@arcturus1140]

But your help doesn't work doesn't work

[@rahul-qo3fi]

This was great, Thank you!!

[@shadeofthetrees]

Sweet fancy Moses...I can definitely tell that I don't have a dedicated GPU. Each epoch is averaging around 115s, which is leaps and bounds slower than yours. Makes trial and error quite a bit more tedious.

[@nikosplugachev6610]

I love these tutorials!!!!!! I love keras!!!!!!! Unlike many other stupid tutorials, everything is explained very well and the code actually works!

[@christaylor8142]

Hey Sentdex, love you tutorials. Thank you for taking the time to put them up. Will you cover any PyTorch tutorials?

[@vighneshbalajianand4471]

Thank you @sentdex you are really awesome and this tutorial🔥🔥🔥🔥🔥

[@brooklyncheung8255]

That's incredible~ I'm waiting for ur next video.

[@jaydevsinhzankat8872]

when Sentdex runs this code it shows 17000 + samples but when I Run this it shows only 500 samples so how can I increase my samples no. please help me if anyone gets me. plzzzzzzzzzzzzz

[@nikosplugachev6610]

Try using pycharm CE to make the tutorials even better!

[@linho2872]

Keep going. it's very useful for me. Thanks a lot

[@khoapham3083]

Anh ơi, em bật cái tensorboard lên thì không thấy val_loss với val_acc, anh biết cách sửa ko ạ

[@divyanshshukla4991]

Great work. Keep us educating @sentdex

[@sentdex]

Will do!

[@flamespirit]

if you use from keras.callbacks import TensorBoard you don not have to initialize it ;) took me some time to figure that out

[@shanerooney7288]

I'm stuck at 9:34 I type everything into Command prompt. I copy the link. Type into Chrome. And go to TensorBoard. ..... *"No dashboards are active for the current data set."* Either: A) first time users of Tensorboard need to preform an extra step (which perhaps should have been included.) B) Using Tensorboard in Windows is slightly different than using on a Mac. Which is possibly the case since sentdex said _"anyway, on Windows it can get kind of finicky on you. Its weird"_ ...... C) I screwed up somewhere. This is always a possibility. I'm going to go look for other tutorials, since who knows if/when this will ever get a helpful reply :'( (This tutorial had been great up until that point. And will certainly be back for the rest of the video series after I fix the problem. However long that might take)

[@shanerooney7288]

Long story short: tensorboard --logdir=foo:"C:\Path\To\Files" Something about the use of semicolons within the window's file-path cases it to not work. Therefore putting *_foo:"_* before the file-path fixes it.

[@jerryc5716]

@@shanerooney7288 You're a hero, man. Thanks a bunch.

[@shanthoshkumar1547]

@@shanerooney7288 Thank you. It was helpful

[@davronsherbaev9133]

The reason why the server stopped on first attemp was that you put carret in CMD line. In windows it pauses the running process)

[@Tiveny26]

Could you make a segmentation cnn instead of a classification one afterwards? Im really interested in that

[@mathieuclerte5252]

Hi @sentdex, how likely are your tutorial series still "compatible" with TensorFlow 2.2 ?

[@relaxandnostress3625]

2:02 "Without the activation function becomes like a linear activation function". This is not correct. Linear activation function is still a legit activation function. W/ the activation function becomes a linear regression model.

[@solques36]

'tensorboard' is not recognized as an internal or external command, operable program or batch file. i got this error could u help me ? Thank u:)

[@mlg_rajgaming3406]

Same

[@CalvinL.Stevens]

do you also use the 1080ti for gaming or is it a pure workhorse?

[@A14-o5f]

I get an error saying that a cirectory could not be created in relation to logs/Tagged-vs-untagged-cnn-64x2-1563446211\plugins\profile\2019-07-18_11-36-52 (with tagged-vs-untagged etc being my version of cats and dogs file name). Any ideas how to fix? This error is related to tensorflow.

[@karmitdhawan2658]

tensorboard=TensorBoard(log_dir='logs\{}'.format(NAME)) put a forward slash instead of backslash in logs, that solved the problem for me

[@ChaminduWeerasinghe]

try this if GPU options not worked : gpu_options = tf.compat.v1.GPUOptions(per_process_gpu_memory_fraction = 0.333) sess = tf.compat.v1.Session(config=tf.compat.v1.ConfigProto(gpu_options=gpu_options))

[@_spartian_]

Hey, insted of showing 4 graphs I am only able to see 2 (epoch_accuracy and epoch_loss) not like yours and also even after one run they showed up 2 (as train and validation) how can i see separate 4 graphs

[@amoghchavan6373]

hey bro same , i guess it is due to update in 2020. also i can not find the log file in my directory since i am using jupyter notebook (if you have the solution plzz tell) i used %load_ext tensorboard import tensorflow as tf import datetime, os logs_base_dir = "./logs" os.makedirs(logs_base_dir, exist_ok=True) %tensorboard --logdir {logs_base_dir} this to load tensorboard

[@_spartian_]

​@@amoghchavan6373 Sure, No it's not jupyter notebook's problem. You can do that with jupyter... You don't need to use OS for making directory. log_dir(argument) in tensorboard, will create path you specify. This is the code i'm using, NAME = "{}-conv-{}-nodes-{}-dense-{}".format(conv_layer, layer_size, dense_layer, datetime.datetime.now().strftime("%Y%m%d-%H%M%S")) tensorboard_callback = TensorBoard(log_dir="logs\\{}".format(NAME)) In my case i'm simply generating 'logs' folder(which is created by tensorboard) in jupyter notebook's folder where my code file is... Please check your log_dir argument. Your logs might be at that place. Hope this solves your problem. Ask if you still stuck there...

[@amoghchavan6373]

@@_spartian_ thank you for your help , also i have completed the entire model without any errors . if u need any help then let me know

[@bernardoolisan1010]

i love how u say "un mas tiempo", im from mexico and you say here "Otra vez"

[@dearheart2]

Nice videos, keep up the good work. If 573K joins, you should be able to add roughly 1/2 a million mugs to your collection each month.

[@sentdex]

The dream!

[@7characters]

I actually screamed out “YESSS!” at my work office when I got the notification for this... I’ve reached new lows (highs)

[@naveezalagarsamy9757]

awesome video man

[@dbccrc9643]

Anyone else 'tensorboard' is not recognized as an internal or external command, operable program or batch file. in CMD?

[@dbccrc9643]

Answer: stackoverflow.com/questions/47985835/tensorboard-is-not-recognized-as-an-internal-or-external-command

[@gau_rav_92]

Use localhost: instead

[@AbhishekKumar-mq1tt]

Thank u for this awesome video

[@alejandrozuniga1126]

Guys if you get an error importing Tensorboard it is because now it is called TensorBoard! Probs you can get an error if you do not change the name...

[@PavanKumar-jc1qn]

This was very helpful. How can I show an ROC curve on TensorBoard? Thank you

[@zombietechz8361]

Hey, I really loved the video. I just do not understand why you are only focusing on validation loss?

[@sentdex]

Because validation data is out of sample. In sample data accuracy is nice to know, but it's biased. This is data the machine has already seen. Validation data is our best example of real "live" data to know how the model might do in reality.

[@Wrathofgod220]

Got tensorflow to work with that one line missing activation function in sublime. I was pulling my hair out trying to figure out why the code from ep. 3 was running only a fraction of the time. good work! I still don't know what is wrong with version tensorflow 1.9 on anaconda but ever since I updated from 1.8, tensorflow.keras stopped working.

[@farzanevafaii5820]

hi! thanks for your video I just dont get something about using tensorboard, why dont we use matplotlib and draw our plots with that like always? what is the difference?

[@AlbertBonomo]

I was reading Conv2d reference from TensorFlow page and I can see that it has stride=, activation= and many other parameters that can be set to it. So, I wonder if we can eliminate the Activation() layer and use the activation= param of Conv2D instead ? Thanks for the video, it is great.

[@f_ftactics7928]

why do I only get epoch_accuracy and epoch_loss graphs? Any ideas? thanks.

[@jagadishparasuraman5392]

hey my screen shows the same too...Any ideas how to make it appear similar to this tutorial?

[@endlessformsmostbeautiful8442]

I got the same too, can not find a solution

[@sharkdeng9253]

very useful!

[@FlavorOfTheMonthChannel]

I fixed "Module 'tensorboard.util' has no attribute 'Retrier'" by doing "pip uninstall tensorboard" and "pip uninstall tensorflow-tensorboard", then running "pip install tensorflow-tensorboard". NOTE: different versions of tensorflow need different versions of tensorboard, for tensorboard to work properly. The modules are independent of eachother, but if your tensorboard isn't working, try getting your version to match up closer with your tensorflow version (i'm using tensorflow 1.5, and tensorboard 1.5.1)

[@aravindnaidu1286]

to get those graphs we can just simply use matplotlib library right???

[@ramzykaram296]

If you applied tutorial 3 on Google Colab as me, then the below code will work from you to have tensorboard running there. from datetime import datetime logdir = os.path.join("logs", datetime.now().strftime("%Y%m%d-%H%M%S")) tensorboard_callback = tf.keras.callbacks.TensorBoard(logdir, histogram_freq=1) model.fit(X, y, batch_size=batch_shape, validation_split=0.1, callbacks=[tensorboard_callback]) Then in a new cell use the below to open the TensorBoard %load_ext tensorboard %tensorboard --logdir logs

[@EricKim-c3i]

I have a question, I located my working directory and typed "tensorboard --logdir=logs/" as but i got this error "'tensorboard' is not recognized as an internal or external command, operable program or batch file." Can anyone help me?

[@VyreBET]

Can I Also try this on Pycharm IDE? Or do I Really need to Install SUblime?

[@NehaYadav1]

Hey Sentdex,What's the theme of Sublime text editor that you are using? I really liked it..Anyway great tutorial series as always!!

[@noreddinebelhaoua7659]

Hello when I'm using tensorboard i get this issue ProfilerNotRunningError: Cannot stop profiling. No profiler is running.

[@mehranzand2873]

you are the best

[@bijinmabraham3887]

I have trained a custom model with 3 classes, using SSD MobileNet in TensorFlpw, Is there a way to find the average precision of these individual classes ?

[@hhano50]

I would like to ask one question. I am using the exact route that you used. In each run, I am taking different values in accuracy and loss. That is why, the plots are different every time compared to the previous ones in TensorBoard. Is the training of data necessary again? or there is something different that we should also insert. Thank you.

[@bcook745]

Hi - great video. With the example given, my PC takes about 10 minutes per epoch, and wanted to know if you have any tips for speeding things up. I'm using a fairly dated Dell XPS8300, Intel Core i7-2600 CPU, 16 GB RAM, NVIDIA GeForce GT 545 display adapter. I'm using the CPU only version of Tensorflow. If I install the GPU version of tensorflow, will that help do you think? I'm trying to avoid buying a new PC!

[@ELarivie]

Hi ! long time fan. How is it possible that at the 11 minute mark you have validation loss and accuracy both increasing? Shouldn't they be 100% inversely correlated? Thanks!

[@anefuoche1053]

please what is the most recent way to do GPUOptions and Session? Apparently GPUOptions and Session are deprecated. I am getting errors that tensorflow does not have those as modules.

[@georgemcdonald3700]

POTENTIAL FIX FOR SOME: SUMMARY: I'm using an anaconda environment (added to PATH during installation of anaconda), running the gpu-version of tensorflow and launching jupyter notebook from inside this environment. I called this environment "tensorflow-gpuenv" (relevant for later step). Running tensorboard --logdir=logs, failed to execute for me. FIX: As instructed, open the the directory containing the logs folder in explorer and type cmd to open the prompt. type "activate tensorflow-gpuenv" (where tensorflow-gpuenv is the name of the environment you launched jupyter from within) type "tensorflow logdir=logs" you should get an address to paste into your searchbar now. For me, i could only load this url after copying the url with ctr-c (which it tells you will exit). I have yet to check if the other local host fixes, in this comment section, remove the need for this but i can view my models fine as is. hope this helps some.

[@lemyul]

"As instructed, open the the directory containing the logs folder in explorer " by logs folder, do you mean the folder with cats and dogs in it?

[@pulkitgaur4438]

I have a Question how did all the epochs ran simultaniously I get one epoch at a time

[@منةالرحمن]

hello, thank you How to load tensorboard in colab please i find empty web page

[@mahshidsoleymani1963]

Thank you for the great video . How can I plot accuracy for both train and validation set in one graph ?

[@anishthapaliya703]

import keras from matplotlib import pyplot as plt # history = model1.fit() plt.plot(history.history['acc']) plt.plot(history.history['val_acc']) plt.title('model accuracy') plt.ylabel('accuracy') plt.xlabel('epoch') plt.legend(['train', 'val'], loc='upper left') plt.show() plt.plot(history.history['loss']) plt.plot(history.history['val_loss']) plt.title('model loss') plt.ylabel('loss') plt.xlabel('epoch') plt.legend(['train', 'val'], loc='upper left') plt.show()

[@liangyumin9405]

Nice Tutorial

[@domenicobezuidenhout1587]

Hello Dex, I am having the weirdest issue with this. I will change nothing in my code except adding from tensorflow........ import tensorboard The minute i add this my loss goes from .08 to 1.6 and nothing in the underlying code has changed? I am extremely confused

[@kacemichakdi3048]

Hi sir, I hope that u are fine. When running in the (Anaconda) command prompt, correct environment, I get an error: AttributeError: module 'tensorboard' has no attribute SessionRunHook. Can you help me with this? Thank u for every thing ^_^.

[@noname-xq7zn]

Use tensorflow.compat.v1 worked for me

[@bond-hn4wd]

not matching prediction for cats, did with many pictures but the result was [[4.1456 (something)]]. did your codes as well but the result was the same, for dogs though the results were good. please help!

[@mauricioluisvega8342]

Is there a function that allows me to see the improvement in percentage? Supposedly, that percentage is reduced but I can see somehow.

[@anirudhsilverking5761]

No dashboards are active for the current data set. Please help

[@trickermaelstrom4418]

I have 1 question, How can I get the accuracy score for each class? I want to know from class 1 what accuracy I got, from class 2 what accuracy I got?

[@novianadiprasetyo391]

at this code I get an errror model.save('epic_num_reader.model') with description 1357 if not self._is_graph_network: 1358 raise NotImplementedError( -> 1359 'Currently `save` requires model to be a graph network. Consider ' 1360 'using `save_weights`, in order to save the weights of the model.') 1361 NotImplementedError: Currently `save` requires model to be a graph network. Consider using `save_weights`, in order to save the weights of the model. tensorflow version is '1.12.0'

[@GAment_11]

If anyone else has issues using Windows 10, Tensorflow 2.0, and Anaconda Prompt, I found this syntax works in the Firefox Browser (note, I am note in a Virtual Environment): tensorboard --logdir=.\logs\

[@brunobelloni7614]

Can I make a prediction with an R-CNN with that .model I trained by watching your previous videos? How do I do that? I want to see if I have two flowers in the same image. Thank you

[@eastwoodsamuel4]

%reload_ext tensorboard %tensorboard --logdir '/content/drive/My Drive/Colab Notebooks/Deep_Learning/logs' For those using Google Colab with mounted Drive

[@shashanksaurav4798]

can you make a video on tensorboard debugger plugin & also embedding visualizer . Thank you

[@pooja2323]

I get this error :- NotFoundError: Failed to create a directory: logs/Cats-vs-dogs-CNN\plugins\profile\2019-08-08_11-24-38; No such file or directory

[@anhkyao3586]

So do I.

[@FredPower_]

In the log_dir, change the / to \\ if you're running windows

[@abdulsemedyasin2975]

@@FredPower_ you saved my day thank you

[@DeepakKumar-uz4xy]

@@abdulsemedyasin2975 but not mine am also facing that problem

[@DeepakKumar-uz4xy]

@@abdulsemedyasin2975 File "", line 3, in raise_from tensorflow.python.framework.errors_impl.InvalidArgumentError: Failed to create a directory: logs/dogs-vs-cats-cnn-64*2-1578562165; Invalid argument [Op:CreateSummaryFileWriter]

[@kibbutztradelink2287]

ERROR:root:Internal Python error in the inspect module. Below is the traceback from this internal error. i cant find the error, please help upon it.

[@EverythingTechWithMustafa]

Use dark mode for all videos wherever possible

[@vinra5661]

do you know how to use tensorboard in google colab? i already tried this: !pip install tensorboardcolab from tensorboardcolab import TensorBoardColab, TensorBoardColabCallback tbc=TensorBoardColab() but, after adding the callback with model.fit(X, y, batch_size=32, epochs=1, validation_split=0.3, callbacks=[TensorBoardColabCallback(tbc)]) i get this errormessage: KeyError Traceback (most recent call last) in () 51 metrics=['accuracy']) 52 ---> 53 model.fit(X, y, batch_size=32, epochs=1, validation_split=0.3, callbacks=[TensorBoardColabCallback(tbc)]) i dont know why

[@anhkyao3586]

so do i.

[@nidhikundu3620]

AttributeError: module 'tensorflow.python.estimator.estimator_lib' has no attribute 'SessionRunHook' how to resolve this

[@Gissel1989]

when does the sc2 ai series come back? really liked it

[@dt28469]

How do you delete log files from there? It doesn't let me delete old runs

[@punks0325]

Why you have used sigmoid activation in dense ???

[@souha5188]

what should i do if the val_acc is too low than the accuracy ?

[@manishbatta6603]

i am new to deep learning and programming will is this the right way to start from here onward.Will i will be able to learn everything here?????? I know ML , n python i recently done this in 2 month program. please help

[@bernardoolisan1010]

@sentdex at minute 10:59 is it overfitting?

[@gianlucavernia9444]

My model gives me an accuracy of 1.000 which I think is not right. Also after creating the data I am left with about 12000 samples and I think that either dogs or cats were left out. Someone knows what is happening?

[@MohdAkmalZakiIO]

The line *tensorboard = TensorBoard(log_dir='logs/{}'.format(MODEL_NAME))* throws me error of invalid syntax. Why was it? TensorBoard 2.1

[@MohdAkmalZakiIO]

MODEL_NAME = "CNN_1-{}".format(int(time.time())

[@chetangodiya1]

Hey can you show how we can find two similar featured face and replace them with each other .... ?

[@alejandroarevalo8897]

When Im soppouse to write in my "cmd tensorboard --logdir=logs/" nothing but this shows up ValueError: Not a TBLoader or TBPlugin subclass: Can anyone help me?

[@dharmeshsharma]

Instead of Remove Dense layer why not try with dropout?

[@pratyushpradhan2612]

it shows "tensorboard' is not recognized as an internal or external command, operable program or batch file" , does anyone know how to solve it?

[@suleimanmustafa1473]

if your tensorflow installation was done using conda, then you can launch tensorboard from the Anaconda prompt as follows: activate tensorflow tensorboard --logdir=path to your log files

[@javitolez]

@@suleimanmustafa1473 tensorboard --logdir=c:/Usarios/Javier/logs/ ^ SyntaxError: invalid syntax How can i solve it?

[@suleimanmustafa1473]

@@javitolez you have to run this command from the terminal

[@javitolez]

@@suleimanmustafa1473 sorry for the delay just read the answerd. I will try this and tell you how was going. Really thank very much for your answerd. Best. Javier.