Awesome! Easy to understand. One request, I get the folder of ( myData, labels and source code of cv2) but can not find the source code of python that you introduced at the first. & I Follow the link in the description and enroll to get access to all code and files.
Sir I find it much easier to learn when you code the program through the video and we follow along rather than you just explaning through it. Great video anyway, I'm learning a lot of the tricks.
For anyone getting errors despite copying the exact same code, try specifying the version for the packages you install. For keras use 2.3.1and for tensorflow use 2.0.0, like he uses in the next video. th-cam.com/video/y1ZrOs9s2QA/w-d-xo.html
@@go4real wow I can’t remember what version of Python I used back then but I must have been lucky to use the right one! Super glad it works out for you and thanks for the tip!
Mam u had replayed on traffic sign detection video that the code worked, I need help on that at the time of test the size of video capture frame is small in this How to increase it?
First of all, I respect you for these educational videos. How many problems will there be, I would be happy if you answer: 1) Can I do this training with my own different data? 2) I tried to do but I encountered the following error: "AssertionError: The dimesions of the Training images are wrong "What is the solution to the problem? 3) Can you share the pictures of these videos? Best regards.
@@murtazasworkshop HI Sir i am getting an error when i try to run my model as shown below WARNING:tensorflow:From D:\Capstone\venv\Lib\site-packages\keras\src\backend.py:873: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead. 2023-11-17 00:20:30.282309: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: SSE SSE2 SSE3 SSE4.1 SSE4.2 AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. WARNING:absl:`lr` is deprecated in Keras optimizer, please use `learning_rate` or use the legacy optimizer, e.g.,tf.keras.optimizers.legacy.Adam. Traceback (most recent call last): File "D:\Capstone\TrafficSign.py", line 182, in history = model.fit_generator(dataGen.flow(X_train, y_train, batch_size=batch_size_val), ^^^^^^^^^^^^^^^ File "D:\Capstone\venv\Lib\site-packages\keras\src\engine\training.py", line 3506, in summary raise ValueError( ValueError: This model has not yet been built. Build the model first by calling `build()` or by calling the model on a batch of data. Process finished with exit code 1 please go through and reply soon thanks your learner
Very good explanation has been done, I was trying to do this traffic sign project, but the line code (history=model.fit....) is not visible valudaty_data. Can you please tell me the complete line of it? It would b very helpful
I have never used keras. Where can i learn keras to understand this application better? is the deep learning fundamentals course on the DeepLizard channel good enough?
Hello Sir, really loved the video thanks for this awesome video. Sir, I was thinking to re-implement it with SVM so can you guide me on how can I do this? Do I need to change the only classifier or other changes will be required also? I will be grateful.
File "drive/My Drive/road_sign_1/TrafficSign_Main.py", line 67, in assert(X_train.shape[1:]==(imageDimesions))," The dimesions of the Training images are wrong " AssertionError: The dimesions of the Training images are wrong How to solve this error please help
i used 142 categories in place of 43 categories and there is an error coming " The dimesions of the Training images are wrong " can u plse help me how to solve it
My car often gets 50 and 60 mixed up. I think I’m the uk the 5 can look very close to 6 on our road signs, but when it makes mistakes it’s not obvious why
WARNING:tensorflow:Your input ran out of data; interrupting training. Make sure that your dataset or generator can generate at least `steps_per_epoch * epochs` batches (in this case, 10870 batches). You may need to use the repeat() function when building your dataset.
Greetings! Sir I have seen your youtube vedio regarding THE GERMAN TRAFFIC SIGN RECOGNIATION BENCHMARK which is very interesting vedio I need this project then i have downloaded three things: 1) Labels 2) Data set 3) training source code But the problem is how I join these three things to run a project please need a guide to run this project to step by step. Thanks & regards
Hello, I get the following output: Traceback (most recent call last): File "C:/Users/damie/PycharmProjects/pythonProject/training.py", line 214, in pickle.dump(model, pickle_out) TypeError: cannot pickle '_thread.RLock' object This is for training the data
Probably not because this neural network is trained to classify/categorize images only. If you have a picture of a street with a few cars, people and a road sign it won't be recognized. The reason is that you would need a network that can also identify a road sign and localize it (e.g. drawing a rectangle over the road sign and then after that classify it.) The problem is that this neural network can not perform this first step so you have to give the network a full sized image where you can only see the road sign. If you want to build a network that suits your needs you should look for sth like "YOLO object detection". (Correct me if I'm wrong)
Yes,it will recognise but u need to locate that sign first in that image and than but cropping other part and apply this classification. in simple u have to locate the sign first and then apply this classification.I had already implemented this and my model detecting and recognising sign 95% accurate.if u need further more information contact me at chiragjariwala09@gmail.com
Thank you for this interesting video. How does it work under real conditions when you are driving in a car? Backlight? Darkness, only the lights of your car? Multiple signs at once?
@@abhishekkumarsingh7352 We have to perform Color based/shape based/hybrid segmentation, edge detection, classify it as a traffic sign. Then we perform classification of what specific traffic sign it is.
Hi Murtaza I need your help that project traffic sign classification CNN project which version of keras library would rather to use because of that library does not fix my computer architecture and one problem is in library keras of object Sequential there is no get_distribution_strategy argument please help me What should I do ?
hi, i am doing an autonomous vehicle with neural network project. However i am using raspberry pi and arduino for this project, and i also want it to detect traffic lights, if i have my dataset for traffic lights can i include it and what changes would i have to do? Please HELP!
In your case its better to use Haar Cascade as RPi would be quiet slow for CNN. You can use a pretrained caascade or cutom caascade. Here is the tutorial for it. th-cam.com/video/dZ4itBvIjVY/w-d-xo.html
I have one question!! There is too less image for train in class 0.so i copy all that picture and paste it again in that folder and make it around 1200 as other folders have .can train my model good? I mean copying picture will work?
I have updated the link. You can find the code and files to download in the Traffic Sign Classification section www.murtazahassan.com/courses/opencv-projects/
WARNING:tensorflow:Your input ran out of data; interrupting training. Make sure that your dataset or generator can generate at least `steps_per_epoch * epochs` batches (in this case, 20000 batches). You may need to use the repeat() function when building your dataset. can anyone help me out with the repeat() fun
I want to do a change and I can't do it for a few days. I wanna change instead of output text for output image with sign. Every time when i try to do I get error. Can you help me pleas ? How can I put the imagine in main Windows ?
Great video! I execuded the same code with the same dataset but I got an error on Train file: pickle.dump(model, pickle_out) TypeError: cannot pickle 'weakref' object Can you help me, please?
use this for importing from keras.models import load_model remove the load and dump (replace this) model.save('my_model.h5') # creates a HDF5 file 'my_model.h5' model= load_model('my_model.h5')
@@Razor_7024 I tried this way, but whenever I run the test file I always got the path error. I can't find my trained model in the directory. so can you help me to solve this problem. thank you.
from keras.models import load_model model.save('my_model.h5') # creates a HDF5 file 'my_model.h5' model1 = load_model('my_model.h5') paste this in trainning file by removing pickle dump model= load_model('my_model.h5') use in testing file replace of pickle load
Can you state which python version as tensorflow is not compatible with the latest 3.8.1 ?? Pandas is showing an error. Can you put a picture of all the packages you have installed ??
I have added the reference images to this link under the name packages(1) and packages(2). github.com/murtazahassan/OpenCV-Python-Tutorials-for-Beginners/tree/master/Advance/TrafficSignsCNN/Images
Can you tell me which processor are you using ?? I am using i5-4200u(on my laptop) and it doesn't go beyond reading the csv file (line 73 of Traffictest main)
use this for importing from keras.models import load_model remove the load and dump (replace this) model.save('my_model.h5') # creates a HDF5 file 'my_model.h5' model= load_model('my_model.h5')
Hello everyone, I have a problem when i train a data set in this videos. WARNING:tensorflow:Your input ran out of data; interrupting training. Make sure that your dataset or generator can generate at least `steps_per_epoch * epochs` batches (in this case, 20000 batches). You may need to use the repeat() function when building your dataset. If you know how to resolve my problem please comment below
Awesome! Easy to understand. One request, can I get the link to the datasets? I have tried all the links in the comment section(which you have provided). Either it says Error 404 or it is unable to download.
Are you using custom data or the same ? Compare your console output with this. github.com/murtazahassan/OpenCV-Python-Tutorials-for-Beginners/blob/master/Advance/TrafficSignsCNN/Images/Console%20(1).PNG
Thanks for this very informative and clear lesson. I try exactly the same code but in while loop it trys to recognize everytime and gives predictions even my face front of it. As you guess it's all wrong predictions. Also when i show real signs(from my phone) it also predicts regardless what has been showed as it done the same for my face. Besides when i see the result screen, it's a little bit laggy. Is it because of my computers device feature or i did something wrong?
Its not clear what might be the cause. You can post question with some details and files on my discord channel if you need furrther assistance. discord.gg/bFVMkzf
Getting error like this while training: tensorflow:Your input ran out of data; interrupting training. Make sure that your dataset or generator can generate at least `steps_per_epoch * epochs` batches (in this case, 20000 batches). You may need to use the repeat() function when building your dataset. How resolve this?
@@mert8010 The issue was resolved by using an earlier version of pycharm. I had to search to find the solution and posted it in this comment section. The new version had bugs in it apparently
add this under the Split Data Section steps_per_epoch_val = len(X_train)//batch_size_val validation_steps = len(X_test)//batch_size_val @All In One @Kaizen
interesting video as usual, but i have problem while saving ... File "D:/Workspaces/GDP_AI/Traffic_signs/Network_training.py", line 215, in pickle.dump(model,pickle_out) TypeError: can't pickle _thread.RLock objects I do not know what is the problem
![Real time Shape Detection using Contours [9] | OpenCV Python Tutorials for Beginners 2020](http://i.ytimg.com/vi/Fchzk1lDt7Q/mqdefault.jpg)
Good job, very detailed stuff. Keep it up!
Awesome! Easy to understand. One request, I get the folder of ( myData, labels and source code of cv2) but can not find the source code of python that you introduced at the first. & I Follow the link in the description and enroll to get access to all code and files.
The gratitude for you work to help teach and really get us proficient in programing and process flow, You may change and enhance many of our lives.
i was wondering if we could incorporate this with the same program used to run the robocar?
It is great, and I like how your computer fans went mad at 12:09 😂
Thanks a lot for this video Murtaza, the code worked great!
ma'am downloading link is not working now ,so plz can you help me?
@@ManishSharma-sc7cl Code - www.computervision.zone/courses/opencv-projects/lesson/code-5/
Downloads - www.computervision.zone/courses/opencv-projects/lesson/download-files-2/
@@tanujak98 ma’am after clicked on link it shows the page can’t be found.
It looks like nothing was found at this location.
@@ManishSharma-sc7cl have you tried signing up for an account first? The link is working fine for me...
@@tanujak98 hi can you share the file u have downloaded with me, the page cant be found
Sir I find it much easier to learn when you code the program through the video and we follow along rather than you just explaning through it. Great video anyway, I'm learning a lot of the tricks.
You değerce more subscriber, this is very inspiring channel 😍
For anyone getting errors despite copying the exact same code, try specifying the version for the packages you install. For keras use 2.3.1and for tensorflow use 2.0.0, like he uses in the next video. th-cam.com/video/y1ZrOs9s2QA/w-d-xo.html
Thank you so much! It works!
can u share ur pickle file
Thank you
@@go4real wow I can’t remember what version of Python I used back then but I must have been lucky to use the right one! Super glad it works out for you and thanks for the tip!
Mam u had replayed on traffic sign detection video that the code worked,
I need help on that at the time of test the size of video capture frame is small in this
How to increase it?
Excellent subject and great video
Another question, would it be too difficult to implement the detection part to this project? For it to work in real life
did you do that?
First of all, I respect you for these educational videos. How many problems will there be, I would be happy if you answer:
1) Can I do this training with my own different data?
2) I tried to do but I encountered the following error: "AssertionError: The dimesions of the Training images are wrong
"What is the solution to the problem?
3) Can you share the pictures of these videos?
Best regards.
for custom data try this tutorial.
th-cam.com/video/y1ZrOs9s2QA/w-d-xo.html
Really impressive and thank you.
A successful project that I have accomplished and achieved excellent results
Can you guide me?
DUDE GREAT VIDEOS.
please : could you explain the right method to install tensorflow with pycharm
because there are many errors
Thanks Sir, I love your tutorial so much
You are most welcome
@@murtazasworkshop Hello sir can you please help me in error while running this project
@@murtazasworkshop
HI Sir
i am getting an error when i try to run my model as shown below
WARNING:tensorflow:From D:\Capstone\venv\Lib\site-packages\keras\src\backend.py:873: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.
2023-11-17 00:20:30.282309: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: SSE SSE2 SSE3 SSE4.1 SSE4.2 AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
WARNING:absl:`lr` is deprecated in Keras optimizer, please use `learning_rate` or use the legacy optimizer, e.g.,tf.keras.optimizers.legacy.Adam.
Traceback (most recent call last):
File "D:\Capstone\TrafficSign.py", line 182, in
history = model.fit_generator(dataGen.flow(X_train, y_train, batch_size=batch_size_val),
^^^^^^^^^^^^^^^
File "D:\Capstone\venv\Lib\site-packages\keras\src\engine\training.py", line 3506, in summary
raise ValueError(
ValueError: This model has not yet been built. Build the model first by calling `build()` or by calling the model on a batch of data.
Process finished with exit code 1
please go through and reply soon
thanks
your learner
I like your videos and subscribed your channel. Keep post more videos Thanks !
Thank you, I will
Very good explanation has been done, I was trying to do this traffic sign project, but the line code (history=model.fit....) is not visible valudaty_data. Can you please tell me the complete line of it? It would b very helpful
Try install keras version 2.3.1, it's worked for me
Parabéns! Congratulations!
Fantastic!
How you use keras... Gives me error in keras.model and other packages.... Also I installed all the packages correctly... List the packages pls
very good explanation,
can you send me code
Can we please have access to the files with the images of road signs, so we can download it. Thank you.
I have never used keras. Where can i learn keras to understand this application better? is the deep learning fundamentals course on the DeepLizard channel good enough?
Hello Sir, really loved the video thanks for this awesome video. Sir, I was thinking to re-implement it with SVM so can you guide me on how can I do this? Do I need to change the only classifier or other changes will be required also? I will be grateful.
try with sklearn , it would be simpler
@@murtazasworkshop please share GitHub link🙏🏻🙏🏻🙏🏻🙏🏻
File "drive/My Drive/road_sign_1/TrafficSign_Main.py", line 67, in
assert(X_train.shape[1:]==(imageDimesions))," The dimesions of the Training images are wrong "
AssertionError: The dimesions of the Training images are wrong
How to solve this error please help
I am getting the same error. Is your error solved ?? If yes please help me in this.
@@ruchipandey8851 you have to comment all this type of code
There are 5 or 6 line of same formet you have to convert them into comments or remove them
@@crictraveller9558 Thankyou, it helped me 😇
@@ruchipandey8851 Welcome 👍
@@ruchipandey8851 you need to change that line
pickle.dump(model,pickle_dump)
Sir, Can you please provide the versions of the libraries used here? Code is not running due to version issue
How you use keras... Gives me error in keras.model and other packages....
i used 142 categories in place of 43 categories and there is an error coming " The dimesions of the Training images are wrong
" can u plse help me how to solve it
My car often gets 50 and 60 mixed up. I think I’m the uk the 5 can look very close to 6 on our road signs, but when it makes mistakes it’s not obvious why
Hi, I was wondering where I could download the test data for the neural network as the link to your website if just showing an error
Loving the tutorial so far. But I do have a question. For some reason tensorflow is defaulting to using my CPU. Anyway to force it to use my GPU?
using the gpu version requires a few more steps. it will not run by default
hi, did you manage to change to gpu to train the models ?
@@murtazasworkshop hi sir, can you guide me on the steps to use gpu for the training ?
WARNING:tensorflow:Your input ran out of data; interrupting training. Make sure that your dataset or generator can generate at least `steps_per_epoch * epochs` batches (in this case, 10870 batches). You may need to use the repeat() function when building your dataset.
same error, any idea how to resolve?
@@dhruv5264 steps_per_epoch_val = len(X_train)//batch_size_val
validation_steps = len(X_test)//batch_size_val
paste it at split data section
@@chethangudal4062 It worked for me, but can you tell the logic behind it! Highly appreciate it!
Donno the logic sir I was randomly doings the above changes it worked. sorry
@@chethangudal4062 is it at the train part
Greetings!
Sir I have seen your youtube vedio regarding THE GERMAN TRAFFIC SIGN RECOGNIATION BENCHMARK
which is very interesting vedio I need this project then i have downloaded three things:
1) Labels
2) Data set
3) training source code
But the problem is how I join these three things to run a project please need a guide to run this project to step by step.
Thanks & regards
cool video i love your conten
guys how can i get this files he have ??
i need it fastly
Hello, I get the following output: Traceback (most recent call last):
File "C:/Users/damie/PycharmProjects/pythonProject/training.py", line 214, in
pickle.dump(model, pickle_out)
TypeError: cannot pickle '_thread.RLock' object
This is for training the data
Use the model.save method instead.
@@murtazasworkshop Hi sir, thank you a lot!
hi damien, could you please teach me how to install the right tensorflow for this project ?
sir why i am not able to access code of video on website despite logging in.
Which specifications would be the best for the cam ?
Bro we tried your method but we have an error that our accuracy graphs of train and loss are not generating.can you help us for that
having same error please help
Amazing video! My congratulations and thanks for sharing. Do yiu have any video about object detection?
Thanx. Yes there are a few depending upon what type of objects. If you want to detect most common objects check the yolo v3 series.
How can I download the code,please help me, thank you so much
I am working on making my own datasets for Indian traffic sign classifications.Can you suggest me any good idea.
Hello, love the video
Probably not because this neural network is trained to classify/categorize images only. If you have a picture of a street with a few cars, people and a road sign it won't be recognized. The reason is that you would need a network that can also identify a road sign and localize it (e.g. drawing a rectangle over the road sign and then after that classify it.) The problem is that this neural network can not perform this first step so you have to give the network a full sized image where you can only see the road sign.
If you want to build a network that suits your needs you should look for sth like "YOLO object detection". (Correct me if I'm wrong)
Yes,it will recognise but u need to locate that sign first in that image and than but cropping other part and apply this classification. in simple u have to locate the sign first and then apply this classification.I had already implemented this and my model detecting and recognising sign 95% accurate.if u need further more information contact me at chiragjariwala09@gmail.com
@@chiragjariwala3264 can you please share code with me
@@chiragjariwala3264 Hello Chirag. Could you please share the code with me
Thank you for this interesting video. How does it work under real conditions when you are driving in a car? Backlight? Darkness, only the lights of your car? Multiple signs at once?
Classification alone is not enough for real world application. We have to add the element of detection
@@murtazasworkshop sir what kind of element of detection can you give example ?
@@abhishekkumarsingh7352 We have to perform Color based/shape based/hybrid segmentation, edge detection, classify it as a traffic sign. Then we perform classification of what specific traffic sign it is.
Hi, I am getting an error “AttributeError: ‘Sequential’ object has no attribute ‘_distribution_strategy'” Can you please help me.Thank you
were you able to resolve it?
discord.com/invite/bFVMkzf if not go to think link and help me asking the same issue.. if you already found a solution please let me know
@@sareek007 i am too facing a same issue have you solved it ?
Hi Murtaza I need your help that project traffic sign classification CNN project which version of keras library would rather to use because of that library does not fix my computer architecture and one problem is in library keras of object Sequential there is no get_distribution_strategy argument please help me What should I do ?
hi, i am doing an autonomous vehicle with neural network project. However i am using raspberry pi and arduino for this project, and i also want it to detect traffic lights, if i have my dataset for traffic lights can i include it and what changes would i have to do? Please HELP!
In your case its better to use Haar Cascade as RPi would be quiet slow for CNN. You can use a pretrained caascade or cutom caascade. Here is the tutorial for it. th-cam.com/video/dZ4itBvIjVY/w-d-xo.html
I am also doing same
Simpson chiwashira please guide me for this project
Can I use same method to train model for same project like you.
Thank you for wonderful video. Can you tell me how I can create the dataSet?
You can create with a webcam or by using google . I have discussed this further in this tutorial : th-cam.com/video/dZ4itBvIjVY/w-d-xo.html
if i dot hav knowledge about opencv so shall I go for this or should learn opencv before
Hello, is it possible to detect the weight and size of an object as well? Thanks!
the weight no.
I have one question!! There is too less image for train in class 0.so i copy all that picture and paste it again in that folder and make it around 1200 as other folders have .can train my model good? I mean copying picture will work?
Hi, can you please guide me on how to get the csv file ? Thank you
I have updated the link. You can find the code and files to download in the Traffic Sign Classification section
www.murtazahassan.com/courses/opencv-projects/
Thank you very much
Hello, thank you the video, but i have a question, how to stop the train ?
WARNING:tensorflow:Your input ran out of data; interrupting training. Make sure that your dataset or generator can generate at least `steps_per_epoch * epochs` batches (in this case, 20000 batches). You may need to use the repeat() function when building your dataset.
can anyone help me out with the repeat() fun
even i got the same warning
we need to use the older version of tensorflow as tensorflow keeps on uptading
Sir, from where we will get the dataset?
Could you tell me please, how can I plot distribution data after augmentation?
Very well, got a question, cv2.resize(32,32) will resize the frame very little size.any alternative to get big frame?
for tranining its better to keep the image size small other wise it will take too long to train.
Can i use laptop's front camera instead of webcam and if yes what changes am i supposed to do in code ?
Yes you can. You just have to change the camera id . If you just have the internal webcam and no external cameras, then the id should be 0.
Were u able to use laptop's front camera?
I will be gratefull to you if u can please mail me the code files at mmk.raichur@gmail.com thank you
I want to do a change and I can't do it for a few days. I wanna change instead of output text for output image with sign. Every time when i try to do I get error. Can you help me pleas ? How can I put the imagine in main Windows ?
I havent found the github repository link. Could you please share it?
Hi! can i have the pre-trained model? i copy the same code but it's not working for me, there are some errors...
Why the camera didn't work with me ? Did I should use an external camera or I can use the that in my laptop?
Good day! Could you tell me, please, am I able to compile "TrafficSign_Test.py" to "*.exe" file using pyinstaller? Thanks!
I am not sure . I did not try .
Great video! I execuded the same code with the same dataset but I got an error on Train file:
pickle.dump(model, pickle_out)
TypeError: cannot pickle 'weakref' object
Can you help me, please?
Did u resolve the error?Actually i m also getting the same error. After digging a lot i m not able to find the solution.
@@ch-bn6fy you I saved the model using model.save without pickle
use this for importing from keras.models import load_model
remove the load and dump (replace this)
model.save('my_model.h5') # creates a HDF5 file 'my_model.h5'
model= load_model('my_model.h5')
@@Razor_7024 I tried this way, but whenever I run the test file I always got the path error. I can't find my trained model in the directory. so can you help me to solve this problem. thank you.
When running Test.py, it says "eoferror ran out of input" for pickle.load function
error solve Hua kya bhai ????
@@kushagrabansal2300 I didn't find any solution to my error.
the link is no longer available can u plz mail me the source code mmk.raichur@gmail.com
from keras.models import load_model
model.save('my_model.h5') # creates a HDF5 file 'my_model.h5'
model1 = load_model('my_model.h5')
paste this in trainning file by removing pickle dump
model= load_model('my_model.h5')
use in testing file replace of pickle load
Can you state which python version as tensorflow is not compatible with the latest 3.8.1 ??
Pandas is showing an error.
Can you put a picture of all the packages you have installed ??
I have added the reference images to this link under the name packages(1) and packages(2). github.com/murtazahassan/OpenCV-Python-Tutorials-for-Beginners/tree/master/Advance/TrafficSignsCNN/Images
Can you tell me which processor are you using ??
I am using i5-4200u(on my laptop) and it doesn't go beyond reading the csv file (line 73 of Traffictest main)
@@adityaippili6734 I used i7-6820HK MSI GT80 Titan
@@murtazasworkshop I am facing this problem: EOFError: Ran out of input when I load model_trained.p file. Can you help me solve this problem?
Great job, Is the dataset available on kaggle? or where can I download it, please?
Hello, could you please attach the latest code for traffic sign recognition using camera. I couldnt run this code on my machine
Does anyone have the solution for TypeError: cannot pickle 'weakref' object
use this for importing from keras.models import load_model
remove the load and dump (replace this)
model.save('my_model.h5') # creates a HDF5 file 'my_model.h5'
model= load_model('my_model.h5')
TypeError: can't pickle _thread.RLock objects
this is the error I am getting when I was running this code..
can you help in solving this?
same error bro
Bro we can use other thing to save our model
Model.save('my_model.h5') instead of the whole pickel thing
We can aslo load easily with this instead of pickle look it up
But errors are still there related to running out of data set I had to reduce the no of steps per epoch causing reduction in accuracy😭😭
if I would testing an outher video (like when I driving a car) it is worked in test ?
Hello everyone, I have a problem when i train a data set in this videos.
WARNING:tensorflow:Your input ran out of data; interrupting training. Make sure that your dataset or generator can generate at least `steps_per_epoch * epochs` batches (in this case, 20000 batches). You may need to use the repeat() function when building your dataset.
If you know how to resolve my problem please comment below
remove the steps per epoch value.
Hi bro , i have same error did find the why ?
@@abdelhaktlili3860 Not yet bro, I did follow the guide however it didn't work
Awesome! Easy to understand. One request, can I get the link to the datasets? I have tried all the links in the comment section(which you have provided). Either it says Error 404 or it is unable to download.
Follow the link in the description and enroll to get access to all code and files.
@@murtazasworkshop Hi where to get the folder model_rtained.p please can you give could not find in the links
Hi where to get the folder model_rtained.p please can you give could not find in the links
I am getting an error like "input ran out of data". can u plz help me with it.
Hi... I got the same problem. Did you rectify your problem?
@@tarunbalaguru2398 same
@@dhruv5264 just remove the steps_per_epoch
Hi, i have watched your video, it's really excellent. How can i find the data ? Tks
Thank u
Is there another simpler method?
Sir, I'm getting assertion error, the dimensions of Training images are wrong
I've kept my imageDimensions as (32,32,3)
Are you using custom data or the same ? Compare your console output with this. github.com/murtazahassan/OpenCV-Python-Tutorials-for-Beginners/blob/master/Advance/TrafficSignsCNN/Images/Console%20(1).PNG
@@murtazasworkshop It's not working
which version of opencv are you using?
any help with this error: model = pickle.load(pickle_in)
ModuleNotFoundError: No module named 'keras.saving.pickle_utils'"
i have the same. Did u fix that?
The system cannot find the path specified:'myData'..why I am getting this error even after having my data file
Thanks for this very informative and clear lesson. I try exactly the same code but in while loop it trys to recognize everytime and gives predictions even my face front of it. As you guess it's all wrong predictions. Also when i show real signs(from my phone) it also predicts regardless what has been showed as it done the same for my face. Besides when i see the result screen, it's a little bit laggy. Is it because of my computers device feature or i did something wrong?
pressing to " q " for quit in while loop also doesn't work. For to stop it i need to interrupt and need to close screens by forcing them to close.
Its not clear what might be the cause. You can post question with some details and files on my discord channel if you need furrther assistance. discord.gg/bFVMkzf
@@murtazasworkshop Sir i joined but i can't send messages in channel or directly to you. I don't know how to unlock the full discord server.
Hello I also have the same problem did you find any solution for it. If yes please let me know
@@emreay9577 Same problem i am also facing please let me know if you find the solution for it
Can I write all these codes in one program? If possible how can I do that? Please suggest me
Sir the code for this is not available in the above mentioned link in description.. kindly guide me
Getting error like this while training:
tensorflow:Your input ran out of data; interrupting training. Make sure that your dataset or generator can generate at least `steps_per_epoch * epochs` batches (in this case, 20000 batches). You may need to use the repeat() function when building your dataset.
How resolve this?
Did you find a way to resolve this? I am having the same error
@@Kaizen_Roger try to reduce epoch
@@mert8010 The issue was resolved by using an earlier version of pycharm. I had to search to find the solution and posted it in this comment section. The new version had bugs in it apparently
add this under the Split Data Section
steps_per_epoch_val = len(X_train)//batch_size_val
validation_steps = len(X_test)//batch_size_val
@All In One @Kaizen
How am I going to resolve a problem saying that memory error: unable to allocate 20.6 gib for an array
Hey where can I find the model_trained.p file ?
same doubt!
@@rishikreddymusipatla4924 it gets saved in pycharm projects folder in which your code is saved
Is it possible to write the test code using pickle file in C++? Plz answer, thx.
Traffic signs are distinguished by
Color
Shape
Design
Symbol
Stop
Red and white
Hexagon
Current(1974-)
Text Shi
interesting video as usual, but i have problem while saving ...
File "D:/Workspaces/GDP_AI/Traffic_signs/Network_training.py", line 215, in
pickle.dump(model,pickle_out)
TypeError: can't pickle _thread.RLock objects
I do not know what is the problem
www.murtazahassan.com/forums/topic/traffic-signs-classification-using-convolution-neural-networks-cnn-opencv-pyth/
@@murtazasworkshop The above link you have posted here in the comment is not working. I am getting the same issue as well. Unable to pickle
Hello sir good day, can you make tutorial for traffic signs classifications using YOLO or MobilenetSSD? Thanks
how can i get the dataset of this project? its not downloadable which is in your website.
Can u please tell place for code and dataset description link not working
Please
Adam() takes no arguments error kindly give resolutions
Hi where to get the folder model_rtained.p please can you give could not find in the links
I'm getting an error for cv2.resize in testing code: Expected Ptr for argument '%s'
Please help me on how to go about it
make sure your directory is correct
From where do you get data of all sign boards
can we add more images to this data and evaluate?
sir can you please give the details of base papers you reffered for this project.