Видео

your screen is to far, can't see the code well

Hi.It was wonderfuil tutorial. Every thing went well when I tested my trained model with ( detect_from_image.py) .When I wanted to load the model with (detect_from_webcam.py) it gave me this error: return ops.EagerTensor(value, ctx.device_name, dtype) ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type NoneType).Please help me

I haven't popped in an SD card yet and followed along but thank you for this video, this is likely what I'll do with my project because it's so abstract otherwise. Thanks for showing errors you ran into as well, subscribed.

Thanks man it works!!

I want to detect something similar but will have 2 different classes Yes and No, instead of detecting random items.. How to go about it?

It was a great tutorial, ı couldn't do with other tutorials, but now it worked

Thank you. Im a newby and have got my Pi working with a connected screen etc but haven't tried remove access yet. I was intending too but found the pi runs like a dog, takes ages to load up google for example so I hate to think what it would be like running under VNC, even if its no better it still would be unusable in my opinion. Is this an issue with pi running a GUI?

Hi, you didnt posted those commands i nthe descrptiion below.

gracias nuevo suscriptor me sirvio mucho

I got this error "ValueError: Cannot assign value to variable ' conv5_block1_1_conv/kernel:0': Shape mismatch.The variable shape (1, 1, 1024, 512), and the assigned value shape (1, 1, 1088, 256) are incompatible." when trying to train using faster RCNN. in the train and test image. the image size is 295x440. is it because my images are too small?

They are charging now... at VNC

Bruh You are a Real Life Saver Thanks Mann!!

Hello Ben, you are a legend!! Thank you so much, i was struggling to connect with my raspberry, this video helped me a lot!!

I got this error in colab: AttributeError: module 'keras._tf_keras.keras.layers' has no attribute 'experimental'

thanks that was straight forward, can you set up the pi headless again using kali linux please

hi @Arth X I am working on the same project can u help me??

so quick question ben greenfield. does this also work with a rasberry pi 3 model B+ or just pi 3?

Thank you very much Ben! This video was super useful

Went through the detection process, trying to get through this. Very helpful With this one, I see some *.py files in the git, but no images or examples that can be used to follow along. Is there another git somewhere? do you do any consulting?

Thanks for making this video. Very helpful.

Worked for me. Initially I faced some issues with the python version and protobuf. But after some version changing according to what is in video, all worked fine. Thank you for your detailed explanations through the video.

Thanks!

Dunno what to say but thank you very much. +1 Sub gained!

stuck at this error in testing .please help (tf2) E:\TF2\models esearch>python object_detection/builders/model_builder_tf2_test.py 2024-06-19 22:59:02.230552: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cudart64_110.dll'; dlerror: cudart64_110.dll not found 2024-06-19 22:59:02.230858: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine. Traceback (most recent call last): File "E:\TF2\models esearch\object_detection\builders\model_builder_tf2_test.py", line 24, in <module> from object_detection.builders import model_builder File "C:\Users\Public\anaconda3\envs\tf2\lib\site-packages\object_detection\builders\model_builder.py", line 23, in <module> from object_detection.builders import anchor_generator_builder File "C:\Users\Public\anaconda3\envs\tf2\lib\site-packages\object_detection\builders\anchor_generator_builder.py", line 26, in <module> from object_detection.protos import anchor_generator_pb2 File "C:\Users\Public\anaconda3\envs\tf2\lib\site-packages\object_detection\protos\anchor_generator_pb2.py", line 9, in <module> from google.protobuf.internal import builder as _builder ImportError: cannot import name 'builder' from 'google.protobuf.internal' (C:\Users\Public\anaconda3\envs\tf2\lib\site-packages\google\protobuf\internal\__init__.py)

Hi, I am stuck at a point where while I was training a custom model my execution stopped or paused at 2024-06-19 12:33:22.948786: W tensorflow/core/framework/dataset.cc:956] Input of GeneratorDatasetOp::Dataset will not be optimized because the dataset does not implement the AsGraphDefInternal() method needed to apply optimizations. Can anyone help me on how to resolve this. I'm using tensorflow==2.13.1

Thank you man ! If anyone had the error with GLIBCXX_3.4.29 while testing the code, all you have to do is run the command : python -m pip install --upgrade tflite-support==0.4.2 (downgrade from 0.4.4)

I have tried to test the install, 2 out of all pretrained model have error return tf.keras.applications.MobileNetV2(alpha=alpha, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ TypeError: MobileNetV2() got an unexpected keyword argument 'layers' (yes latest MobileNetV2 does not have layers argument) :( File "C:\Users\HP\anaconda3\envs\tensorflow\Lib\site-packages\keras\src\ops\operation.py", line 21, in __init__ raise ValueError( ValueError: Argument `name` must be a string and cannot contain character `/`. Received: name=stack_0/block_0/depthwise_conv2d (of type <class 'str'>) Would appreciate a lot of someone can help me with these.

For those with Attribute Error; cython source: The error message you encountered indicates that there was an issue while building the wheel for pyyaml, a dependency required by tf-models-official. This problem is often related to missing build tools or incompatible package versions. To resolve this, you can try the following steps: Ensure Build Tools are Installed: Make sure you have the necessary build tools installed. For Windows, you should have build-essential tools like Microsoft Visual C++ Build Tools. You can install them using the following steps: Download and install the Microsoft Visual C++ Build Tools. Upgrade pip, setuptools, and wheel: Ensure that you have the latest versions of pip, setuptools, and wheel installed. bash pip install --upgrade pip setuptools wheel Install pyyaml separately: Try installing pyyaml separately before installing the TensorFlow Object Detection API. bash pip install pyyaml==5.4.1 Install the Object Detection API: After installing pyyaml, try installing the TensorFlow Object Detection API again. bash pip install tf-models-official works for me

thanks a lot

The tensorflow addons have been discontinued, is there any alternative solution

Meaning Raspberry Pi as first release = Rpi 1? Cheers!

I'm getting errors with tf.keras.experimental thing during test at 13:40 did someone else have the same issue?

amazing tutorial man. thank you so much

If you're watching in on June 2024 and having the following error: ImportError: cannot import name 'builder' from 'google.protobuf.internal' (C:\Conda\envs\tf2\lib\site-packages\google\protobuf\internal\__init__.py) just when you're downloading protobuf from github and installing from conda, make sure to specify the version as 27.1 like in this video, otherwise it's going to cause issues!

Hey Ben. This is very helpful! Thank you so much. Would a program run remotely on the Pi if I minimize or close the VNC server? I am just curious before experimenting

Thank you

what happens if you put a country code different from where you are connecting to?

Wow - extremely cool!

bricked another sd card with the great imager sucks they have to be fat32

Really nice tutorial! Only thing to improve for he next ones is the font size, makes it difficult to read. Keep it up!

would this work to connect to the pi or could you connect to the pi right from the command line on another internet or how would you

code is obsolete, with TF 2.16 the colab does not work

From the training process, can we see the weight and bias results for each layer that will be used for test data?

Thank you! After watching many tutorials, yours finally worked!!

Thank You so much, you save me

Is that setting comes only for raspberryos ??

My students have been trying on a number of videos to use a custom model and it seems there's an error with the tflite generated from colab. "RuntimeError: Input tensor has type kTfLiteFloat32: it requires specifying NormalizationOpt ions metadata to preprocess input images." is there a specific version of tflite to generate or what could it be?

wow..my model needs 16 hrs..but with impressive result. Great tutorial.. need only some minor adaptions on my side..this will now be the base for some deeper experiments here

thanks for everything , but i did not find any images in the output folder after executing command, what can be the possible cause ?

VNC error "timed out waiting for a response from the computer" how to fix?