How to Train custom Object Detection Neural Network using TensorFlow 2.3 on Google Colab Free GPU

  Рет қаралды 68,243

When Maths Meet Coding

When Maths Meet Coding

Күн бұрын

Пікірлер: 265
@ashwinbabu4113
@ashwinbabu4113 3 жыл бұрын
i have been searching for good object detection video for so long. its really great, I loved it. thankyou
@susantasharma
@susantasharma 3 жыл бұрын
One of the complete video on this topic. Thanks for sharing.
@MahmoudMahmoudTobi
@MahmoudMahmoudTobi 4 жыл бұрын
I can tell you had a lot of fun making this. Thanks for the tutorial and the easy setup file!.
@zanuarer4019
@zanuarer4019 3 жыл бұрын
It is helped me a lot, Thank you very much! I trained using faster-rcnn and tensorflow 2.
@Sandeepsharma-mc1er
@Sandeepsharma-mc1er 4 жыл бұрын
After trying many tutorials this tutorial helps me lot !! Nicely explained!!
@JemmyWu
@JemmyWu 3 жыл бұрын
Awesome! It's indeed the best guide for learning Colab TF2. Thank you so much!
@whenmathsmeetcoding1836
@whenmathsmeetcoding1836 3 жыл бұрын
Thanks
@sakshamp4488
@sakshamp4488 2 жыл бұрын
amazing videos sir !!!
@kenzilamberto1981
@kenzilamberto1981 3 жыл бұрын
Your videos are best at explaining, thank you brother
@petergoergen9991
@petergoergen9991 3 жыл бұрын
Das funktioniert super, vielen Dank!
@thekunafamuncher1173
@thekunafamuncher1173 3 жыл бұрын
Thanks Jay! Fantastic tutorial!
@geraldmusandirire5446
@geraldmusandirire5446 4 жыл бұрын
Best video online !!!!! Thank you !
@saidmaroun7272
@saidmaroun7272 3 жыл бұрын
thank you very your explanations, the video was so great and well presented. keep up the great work
@rafifrahman
@rafifrahman 3 жыл бұрын
Great Tutorial! Thank you so much😍
@whenmathsmeetcoding1836
@whenmathsmeetcoding1836 3 жыл бұрын
Glad it was helpful!
@gogakakabadze
@gogakakabadze 3 жыл бұрын
You are super bro, really super, thank you very much !
@amandal6943
@amandal6943 3 жыл бұрын
Thank you so much you are amazing!!!!
@objectdetection4636
@objectdetection4636 3 жыл бұрын
Much Respect! great tutorial
@gautamkinfo
@gautamkinfo 3 жыл бұрын
the power sell is does not working at my system. it's open power sell window and then crash...
@vinayakdumbre2828
@vinayakdumbre2828 3 жыл бұрын
Thank you sir, actually it helped me.
@utku_yucel
@utku_yucel 4 жыл бұрын
Thanks for the video!
@giorgosiotis1557
@giorgosiotis1557 4 жыл бұрын
You are Great. Thank YOU VERY MUCH.
@robinrai341
@robinrai341 3 жыл бұрын
thanks for amazing tutorial sir i trained the image up to 9000 steps with minimum loses but not detecing the image it just show the test images
@rahulitsrahull
@rahulitsrahull 3 жыл бұрын
Hello Jay.... this is a great tutorial. If you could upload a video on how to convert the saved pb file into TFlite model, it would be much helpful. Thanks
@NusratJahan-jw7vk
@NusratJahan-jw7vk 3 жыл бұрын
thanks a looootttttttttttttttttttttttttttttttttttttttttttttttt......you are the best
@whenmathsmeetcoding1836
@whenmathsmeetcoding1836 3 жыл бұрын
Welcome 😊
@chanhwasheng5454
@chanhwasheng5454 3 жыл бұрын
Hi, can i know what is the problem with this? When installing the Visual C++, it keeps telling me that I have missing packages or damaged packages for setup. I clicked either option for downloading the packages but to no avail. Can you help me on this?
@PunithRamu
@PunithRamu 3 жыл бұрын
Even am having same issues
@mymessage11
@mymessage11 3 жыл бұрын
same problem here
@jimmypark1791
@jimmypark1791 3 жыл бұрын
Same problem here
@Moahid6
@Moahid6 3 жыл бұрын
I got this error at 34:08 minute in the video (when the code !python exporter_main..etc) ""No checkpoint specified (save_path=None); nothing is being restored.") AssertionError: No checkpoint specified (save_path=None); nothing is being restored." any help!
@phyowutyeekhine555
@phyowutyeekhine555 2 жыл бұрын
Did u manage to solve it?
@m.imamfaruqbudiman2019
@m.imamfaruqbudiman2019 4 жыл бұрын
Thank's you very muchh AWESOME !!
@chinmaysathe23
@chinmaysathe23 3 жыл бұрын
Thanx for the upload ❤️
@RakeshKumar-bm2dr
@RakeshKumar-bm2dr 3 жыл бұрын
hello please help me. I am facing a error tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcudart.so.11.0 Traceback (most recent call last): File "model_main_tf2.py", line 32, in from object_detection import model_lib_v2 ModuleNotFoundError: No module named 'object_detection' please help me i am new in python
@marianabuhattoum
@marianabuhattoum 3 жыл бұрын
33:15 I got "Invalid argument: input must be 4-dimensional[1,1,600,800,3] " how can I change the dimensions ?
@mr.millenniamachine1826
@mr.millenniamachine1826 3 жыл бұрын
Thank you. How to improve detection time to about 0.1 sec per frame? Please help.
@wiyadayawai9083
@wiyadayawai9083 4 жыл бұрын
Thank you so much. :)
@whataday3910
@whataday3910 4 жыл бұрын
Can you do a video about good training parameters for Yolo? Maybe you can explain the Yolo Cfg and tell us what parameter is especially important for learning and good detection
@sheetal3955
@sheetal3955 4 жыл бұрын
Hi Jay! while doing Step 9. Try out your object detector for images. I am facing this error-- in the line -- "detection_model=tf.saved_model.load('C:/Users/dell/Documents/Tensorflow/models/research/object_detection/inference_graph-20201219T121406Z-001/inference_graph/saved_model')" the error is-- "FailedPreconditionError: Error while reading resource variable WeightSharedConvolutionalBoxPredictor/WeightSharedConvolutionalBoxHead/BoxPredictor/kernel_159624 from Container: localhost. This could mean that the variable was uninitialized. Not found: Container localhost does not exist. (Could not find resource: localhost/WeightSharedConvolutionalBoxPredictor/WeightSharedConvolutionalBoxHead/BoxPredictor/kernel_159624) [Op:ReadVariableOp]"
@nicolasachury9217
@nicolasachury9217 4 жыл бұрын
First of all, thanks for the amazing tutorial!!! I would like to ask you the following: I trained my model using Google Colab and I interrupted the processes after 30 min. Now the results are not what I was expecting, so I want to train the model much longer. How can I resume the training process using the checkpoints? any insight from you would be highly appreciated!
@বাউণ্ডুলেঅনুপ
@বাউণ্ডুলেঅনুপ 4 жыл бұрын
Well explained!! Great job. Adding a python file for measuring model accuracy, would be great addition to the GitHub Repo.
@deeppatel7779
@deeppatel7779 4 жыл бұрын
Well we r getting only loss information how to get Accuracy information
@stevencarrell83
@stevencarrell83 3 жыл бұрын
@@deeppatel7779 mAP mean average precision
@ImranAli-qs1xn
@ImranAli-qs1xn 4 жыл бұрын
@Jay Bhatt will the power shell create a new environment ...and what does happen when python already installed on computer ???
@anilkoluacik
@anilkoluacik 3 жыл бұрын
setup file is either missing or damaged while installing vs c++ build tools. Pls help me to handle this issue.
@DLooperLive
@DLooperLive 4 жыл бұрын
Can You please tell me which is the best object detection model for solving image captchas ? faster rcnn or efficientNet ?
@whenmathsmeetcoding1836
@whenmathsmeetcoding1836 4 жыл бұрын
please checkout the largest video on channel I have compered all object detection models with examples
@DLooperLive
@DLooperLive 4 жыл бұрын
@@whenmathsmeetcoding1836 Thank you I will check
@deepakkumaryadav2381
@deepakkumaryadav2381 4 жыл бұрын
sir please make a video "A Fire Detection Using ANN AND FPA Algorithm" on machine learning using python
@deepakkumartahsildaryadav7505
@deepakkumartahsildaryadav7505 4 жыл бұрын
Yes sir please this topic cover
@zmonx_gg
@zmonx_gg 3 жыл бұрын
I have the question. In last step of the train model on colab. I want to know how to measure or find the accuracy of that model?
@nourheneaouidi8383
@nourheneaouidi8383 2 жыл бұрын
did you found out how ?
@RakeshKumar-bm2dr
@RakeshKumar-bm2dr 3 жыл бұрын
I am getting this error please help me 2021-05-22 09:02:45.459641: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcudart.so.11.0 Traceback (most recent call last): File "model_main_tf2.py", line 32, in from object_detection import model_lib_v2 ModuleNotFoundError: No module named 'object_detection'
@gaaloulmohamed5535
@gaaloulmohamed5535 4 жыл бұрын
BigWork & BigRespect for the powershell installation Thanks
@annie157
@annie157 2 жыл бұрын
Hi, can you please guide me on how can I find the confusion matrix, if I am using ssd_mobnet model of object detection API?
@hanishlakhani9544
@hanishlakhani9544 3 жыл бұрын
Thanks for a wonderful tutorial. I was able train successfully on my PC but training same program i.e. "!python model_main_tf2.py -pipeline_config_path=training/ssd_mobilenet_v2_fpnlite_640x640_coco17_tpu-8.config --model_dir=training -alsologtostderr" over colab threw a warning "tensorflow:Collective ops is not configured at program startup. Some performance features may not be enabled" and program stopped without training." Program stopped :( without training. Plz help.
@lajinsaji8863
@lajinsaji8863 3 жыл бұрын
I'm getting an error while training that says: 2021-03-16 08:38:07.184481: I tensorflow/core/kernels/data/shuffle_dataset_op.cc:177] Filling up shuffle buffer (this may take a while): 392 of 2048 2021-03-16 08:38:17.643263: I tensorflow/core/kernels/data/shuffle_dataset_op.cc:177] Filling up shuffle buffer (this may take a while): 696 of 2048 2021-03-16 08:38:27.345481: I tensorflow/core/kernels/data/shuffle_dataset_op.cc:177] Filling up shuffle buffer (this may take a while): 726 of 2048 ^C Then the training gets automatically stopped. Can anybody pls tell me what the cause could be?
@leamon9024
@leamon9024 3 жыл бұрын
Thanks for all the hard work and the effort, Jay. One question: In tensorflow object detection API, I know I can start training my model from scratch by running command like python ./object_detection/model_main_tf2.py --pipeline_config_path=/content/drive/MyDrive/Colab_SSD_Facemask/ssd_resnet50_v1_fpn_640x640_coco17_tpu-8_colab.config --model_dir=/content/drive/MyDrive/Colab_SSD_Facemask/training_process --alsologtostderr But how do I re-train my model from the last trained weights so that I don't have to start over everytime if there's an interrupt during the training? Say I have ckpt-1.index, and ckpt-2.index, which are generated during last training, already.
@saravananbalaguru1065
@saravananbalaguru1065 3 жыл бұрын
Hi, Nice details on object detection. Is there a way to count the objects detected in image and/or in a video/Camera using the Custom training model. Thanks Saravanan
@bhamenjoyangom7243
@bhamenjoyangom7243 3 жыл бұрын
After running the training command I got the following error: Traceback (most recent call last): File "model_main_tf2.py", line 113, in tf.compat.v1.app.run() File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/platform/app.py", line 40, in run _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef) File "/usr/local/lib/python3.7/dist-packages/absl/app.py", line 300, in run _run_main(main, args) File "/usr/local/lib/python3.7/dist-packages/absl/app.py", line 251, in _run_main sys.exit(main(argv)) File "model_main_tf2.py", line 110, in main record_summaries=FLAGS.record_summaries) File "/content/drive/My Drive/Tf2/object_detection/object_detection/model_lib_v2.py", line 538, in train_loop train_dataset_fn) File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/util/deprecation.py", line 340, in new_func return func(*args, **kwargs) File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py", line 1143, in experimental_distribute_datasets_from_function return self.distribute_datasets_from_function(dataset_fn, options) File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py", line 1135, in distribute_datasets_from_function dataset_fn, options) File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/mirrored_strategy.py", line 547, in _distribute_datasets_from_function options) File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/input_lib.py", line 162, in get_distributed_datasets_from_function input_contexts, strategy, options) File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/input_lib.py", line 1273, in __init__ self._input_contexts, self._input_workers, dataset_fn)) File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/input_lib.py", line 1936, in _create_datasets_from_function_with_input_context dataset = dataset_fn(ctx) File "/content/drive/My Drive/Tf2/object_detection/object_detection/model_lib_v2.py", line 533, in train_dataset_fn input_context=input_context) File "/content/drive/My Drive/Tf2/object_detection/object_detection/inputs.py", line 898, in train_input reduce_to_frame_fn=reduce_to_frame_fn) File "/content/drive/My Drive/Tf2/object_detection/object_detection/builders/dataset_builder.py", line 210, in build decoder = decoder_builder.build(input_reader_config) File "/content/drive/My Drive/Tf2/object_detection/object_detection/builders/decoder_builder.py", line 64, in build load_keypoint_depth_features=input_reader_config File "/content/drive/My Drive/Tf2/object_detection/object_detection/data_decoders/tf_example_decoder.py", line 416, in __init__ default_value=''), File "/content/drive/My Drive/Tf2/object_detection/object_detection/data_decoders/tf_example_decoder.py", line 89, in __init__ label_map_proto_file, use_display_name=False) File "/content/drive/My Drive/Tf2/object_detection/object_detection/utils/label_map_util.py", line 201, in get_label_map_dict label_map = load_labelmap(label_map_path_or_proto) File "/content/drive/My Drive/Tf2/object_detection/object_detection/utils/label_map_util.py", line 168, in load_labelmap label_map_string = fid.read() File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/lib/io/file_io.py", line 117, in read self._preread_check() File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/lib/io/file_io.py", line 80, in _preread_check compat.path_to_str(self.__name), 1024 * 512) tensorflow.python.framework.errors_impl.NotFoundError: PATH_TO_BE_CONFIGURED/label_map.txt; No such file or directory
@jonaswall18
@jonaswall18 3 жыл бұрын
I have the same probelm.. anyone can help with this?
@tftmobilechannel5590
@tftmobilechannel5590 3 жыл бұрын
@@jonaswall18 Traceback (most recent call last): File "exporter_main_v2.py", line 165, in app.run(main) File "/usr/local/lib/python3.7/dist-packages/absl/app.py", line 303, in run _run_main(main, args) File "/usr/local/lib/python3.7/dist-packages/absl/app.py", line 251, in _run_main sys.exit(main(argv)) File "exporter_main_v2.py", line 161, in main FLAGS.side_input_types, FLAGS.side_input_names) File "/content/drive/My Drive/0. Project/Tf2/object_detection/object_detection/exporter_lib_v2.py", line 272, in export_inference_graph status.assert_existing_objects_matched() File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/training/tracking/util.py", line 905, in assert_existing_objects_matched "No checkpoint specified (save_path=None); nothing is being restored.") AssertionError: No checkpoint specified (save_path=None); nothing is being restored. i got too :(
@lakshit6429
@lakshit6429 4 жыл бұрын
Hey that’s well explained but I have one question, If I want to store the captured cards into csv in sequence of their detection how can I do that???
@zoroXgamings
@zoroXgamings 4 жыл бұрын
open a excel file inside the detection function and print the detection values , you can check how to write data in excel file using python
@farazahmad9079
@farazahmad9079 3 жыл бұрын
Thanks
@annannhat3761
@annannhat3761 3 жыл бұрын
thank you for the tutorial, my loss=nan after a few minutes of training, what could be the cause of this problem?
@mihirkulkarni373
@mihirkulkarni373 4 жыл бұрын
hello sir ,its a very nice video , in my case labelimg is not opening pyrcc5 and pyqt5 both are present what should i do now
@crackITnow
@crackITnow 3 жыл бұрын
Getting error a lot times while using "pip install pycocotools". Anyone can help??
@christinakannole9658
@christinakannole9658 3 жыл бұрын
just like me, any solution?
@phyowutyeekhine555
@phyowutyeekhine555 2 жыл бұрын
Use google colab
@diegoperalta5023
@diegoperalta5023 4 жыл бұрын
Hello, sir. At the moment of making the detection of only 1 object in my image, there appear overlapping boxes. How can I fix this error? Great, perfect tutorial!! Greetings from México!
@shankarmohanakrishnan391
@shankarmohanakrishnan391 3 жыл бұрын
Can you tell me what is number of min training steps needed for this detection? I tried with 1000 steps but its not detecting the objects. Any idea ?
@berndriedel563
@berndriedel563 3 жыл бұрын
That´s great! I managed to follow all steps. The only issue I have is that my GPU is not really used for training. Only 1-3% of my 3080 are used. Any hint?
@waqarahmed2866
@waqarahmed2866 2 жыл бұрын
Did you find a fix for this issue?
@karuneshpalekar5212
@karuneshpalekar5212 4 жыл бұрын
Can u also show how to convert the above model to tflite file .
@whenmathsmeetcoding1836
@whenmathsmeetcoding1836 4 жыл бұрын
Sure I am working on some edge computation content saty tuned video will be out soon..
@karuneshpalekar5212
@karuneshpalekar5212 4 жыл бұрын
@@whenmathsmeetcoding1836 can you just hint please , eagerly waiting for your well managed tutorial.
@whenmathsmeetcoding1836
@whenmathsmeetcoding1836 4 жыл бұрын
Please remind me tomorrow I am done with code development will give you git link to use that script.
@karuneshpalekar5212
@karuneshpalekar5212 4 жыл бұрын
@@whenmathsmeetcoding1836 Thank-You very much .I love this programming community , everyone so eager to spread knowledge
@karuneshpalekar5212
@karuneshpalekar5212 4 жыл бұрын
@@whenmathsmeetcoding1836 Can you please forward the git link
@joseantonioperalta8737
@joseantonioperalta8737 4 жыл бұрын
Why the training is not generating the meta files in the training folder? Only data and index
@geraldmusandirire5446
@geraldmusandirire5446 4 жыл бұрын
After I start training it gets stuck at: 2021-01-20 02:00:11.445726: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:116] None of the MLIR optimization passes are enabled (registered 2) 2021-01-20 02:00:11.453861: I tensorflow/core/platform/profile_utils/cpu_utils.cc:112] CPU Frequency: 2199995000 Hz
@geraldmusandirire5446
@geraldmusandirire5446 4 жыл бұрын
Nvm I didn't put Test files hahah
@saravananbalaguru1065
@saravananbalaguru1065 3 жыл бұрын
​@@geraldmusandirire5446 Hello Gerald, I find the same issue stuck at CPU Frequency. Can you please let me know what could be the fix. I have the test files in the test directory created and labelled and test.record was generated successfully but still I'm stuck after CPU Frequency..Hz
@geraldmusandirire5446
@geraldmusandirire5446 3 жыл бұрын
@@saravananbalaguru1065 did you put some images in the Test file? I put 80% in train and 20% in test
@saravananbalaguru1065
@saravananbalaguru1065 3 жыл бұрын
@@geraldmusandirire5446 Thanks for your quick response. I have put only 4 images test and another 4 in train. Not sure that is an issue. Will try 20/80 as you suggested. Thanks
@geraldmusandirire5446
@geraldmusandirire5446 3 жыл бұрын
@@saravananbalaguru1065 That’s what i did and i made new test.record and train.record files and it just worked
@pavankumarpotta4565
@pavankumarpotta4565 3 жыл бұрын
I am setup the environment The visual studio package is not getting installed it is throwing me an error
@ghaithkattan8597
@ghaithkattan8597 3 жыл бұрын
hello thank you for that video... wanna ask how can i print category name (class name)
@othmanali4232
@othmanali4232 3 жыл бұрын
thank you for the helpful tutorial, how can i re-train without having to compress and upload again?
@erickahumada4806
@erickahumada4806 3 жыл бұрын
Hi,. If I want to count the detected objects separately, how can I do it? I am detecting two objects an apple and a pineapple, and I want it to count each object separately.
@mycollection7864
@mycollection7864 3 жыл бұрын
ModuleNotFoundError: No module named 'tensorFlow' facing this issue again and again.. I also uninstall everything and again install... But still stuck.. Plz tell me some solution
@mycollection7864
@mycollection7864 3 жыл бұрын
At 16:24 of video
@jhoanmartinezsilva2609
@jhoanmartinezsilva2609 3 жыл бұрын
How I label data from video? It seems you get data from your laptop cam, how you did it?
@johnurena2863
@johnurena2863 3 жыл бұрын
i get an error when trying to install visual studio ( a setup package is either missing or damaged)
@ferdicelayir5351
@ferdicelayir5351 4 жыл бұрын
hi, thanks for your nicevideo. I have the fallowing error. Do you have any solution for this? thanks., File "C:\Python37\lib\site-packages\tensorflow\python\lib\io\file_io.py", line 80, in _preread_check compat.path_to_str(self.__name), 1024 * 512) UnicodeDecodeError: 'utf-8' codec can't decode byte 0xfd in position 90: invalid start byte
@Emre-zp2go
@Emre-zp2go 4 жыл бұрын
Did you solve the problem ? I have same problem,too
@jonaswall18
@jonaswall18 3 жыл бұрын
I have the same issue. Anyone able to solve this?
@mucahityuksel4196
@mucahityuksel4196 3 жыл бұрын
sorunu çözdünüz mü?
@madhumalaghosh7885
@madhumalaghosh7885 2 жыл бұрын
ModuleNotFoundError: No module named 'tf_slim' , while running object_detection_tutorial.ipynb ... can you please guide me on this?
@jimmypark1791
@jimmypark1791 3 жыл бұрын
Also why do we need visual studio to run python in google colab?
@謝昀融-y8p
@謝昀融-y8p 4 жыл бұрын
Hello,thanks to your nice video. I'm on Windows7 I got an error while running Install-TensorFlow-Python3.7.ps1 with powershell C:\Users\kevin\Desktop\widows-object-detection-setup-main\widows-object-detection-setup-main\Install-TensorFlow-Python3.7.ps1:59 字元:19 [cmdletbinding
@satty22
@satty22 4 жыл бұрын
Good tutorial. Is it also possible to get x, y, w, h of the bounding boxes from this library?
@zoroXgamings
@zoroXgamings 4 жыл бұрын
you can get them by printing the detection_boxes
@rekhatomar3717
@rekhatomar3717 4 жыл бұрын
Hey Jay Please make a project on Adult and Nudity Detection in images using CNN and also use Transfer Learning This is my humble request to you
@zoroXgamings
@zoroXgamings 4 жыл бұрын
I can help , you can mail me
@rekhatomar3717
@rekhatomar3717 4 жыл бұрын
@@zoroXgamings please send your email
@TheMrtaytac
@TheMrtaytac 3 жыл бұрын
when loading label map i take this error UnicodeDecodeError: 'utf-8' codec can't decode byte 0xfd in position 113: invalid start byte
@jiteshaneja3892
@jiteshaneja3892 3 жыл бұрын
Hi, Can we run Object detection more than one time on the same data-set, example:, for the first time my object detection algorithm will detect the only person in detection, and in the second step it will detect either the person in the last detection is wearing a mask or cap? if Yes then can u please help with how??
@giorgosiotis1557
@giorgosiotis1557 4 жыл бұрын
I tried to run Install-TensorFlow-Python3.7.ps1 script on windows 10 but this script says errors. It never reached to complete the installation. what may be the reason ??
@pavankumarpotta4565
@pavankumarpotta4565 3 жыл бұрын
me too the setup is not getting installed atleast
@spicytuna08
@spicytuna08 3 жыл бұрын
there is so much dependencies to this project. it is like trying to finding a needle in a farm when something breaks. i hope this is not too much to ask. do you have something that we can load a jupyter notebook from your github account to colab and make the same thing. this method is building from windows and importing to colab. can we build straight from colab? is there a reason why this won't work? sorry if i asked you a stupid question. it looks like colab was not designed to work for TF Object detection get go. So this seems like a hack to make Colab to work for TF Object Detection. Why COlab did not make it TF Object Detection friendly in the first place?
@seharsana8867
@seharsana8867 2 жыл бұрын
Can you please guide me...i am facing error IMPORTERROR:cannot import name 'model_lib_v2' from object_detection
@malikgaming5715
@malikgaming5715 3 жыл бұрын
self._read_buf = _pywrap_file_io.BufferedInputStream( esearch\object_detection\images\labelmap.pbtxt : The filename, directory name, or volume label syntax is incorrect.ole_Detection_FYP\models ; no protocol option facing this error please help
@tirthankarroy2906
@tirthankarroy2906 2 жыл бұрын
I tried running the script but it doesn't seem to work,it keeps closing on its own.Is there any specific reason for that?
@blackpearlaxom6261
@blackpearlaxom6261 3 жыл бұрын
Please help... Got this error after running "!python model_main_tf2.py --pipeline_config_path=training/ssd_efficientdet_d0_512x512_coco17_tpu-8.config --model_dir=training --alsologtostderr" tensorflow.python.framework.errors_impl.NotFoundError: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for efficientdet_d0_coco17_tpu-32/checkpoint/ckpt-0
@sujanpaul99
@sujanpaul99 3 жыл бұрын
How can i convert this inference graph to tflite? Please help me. I am stucked in my college project
@maazanis3998
@maazanis3998 2 жыл бұрын
can you tell me how we can make tfjs file of this model so I can use this in react native
@ayatkhaled5086
@ayatkhaled5086 2 жыл бұрын
hello please i nedd some help i got this error while iam run the detection code and i really want to get a solution tensorflow:Importing a function (__inference_bifpn_layer_call_and_return_conditional_losses_58639) with ops with custom gradients. Will likely fail if a gradient is requested. i am using raspberrypi 4
@burhanuddinlimdiwala6754
@burhanuddinlimdiwala6754 3 жыл бұрын
2021-03-25 20:20:23.547296: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:116] None of the MLIR optimization passes are enabled (registered 2) 2021-03-25 20:20:23.555927: I tensorflow/core/platform/profile_utils/cpu_utils.cc:112] CPU Frequency: 2199995000 Hz i am stuck please help me
@burhanuddinlimdiwala6754
@burhanuddinlimdiwala6754 3 жыл бұрын
got the solution nice tutorial..
@mucahityuksel4196
@mucahityuksel4196 3 жыл бұрын
@@burhanuddinlimdiwala6754 how? did you just wait?
@noureldienosama1545
@noureldienosama1545 4 жыл бұрын
Do I need to have git installed before running the jupyter notebook, because I am getting an error, says: 'git' is not recognized as an internal or external command, operable program or batch file.
@whenmathsmeetcoding1836
@whenmathsmeetcoding1836 4 жыл бұрын
yes sorry I missed out it in the video you should have git installed
@duseokchoi2312
@duseokchoi2312 2 жыл бұрын
anyone know whats idffernece between saved model under ssd..-tpu and inference graph/saved_model
@Revaldoi
@Revaldoi 3 жыл бұрын
can I run and create dataset model on macos?
@learnislam9577
@learnislam9577 3 жыл бұрын
hello sir. i don't have a GPU system should I run this on my laptop?
@rinolaharto9281
@rinolaharto9281 3 жыл бұрын
Thank you, Jay..this is awesome...I have subscribed and like your channels..please I have a problem with this.... tensorflow.python.framework.errors_impl.NotFoundError: images\labelmap.pbtxt; No such file or directory please help me..
@PulseofPassion12
@PulseofPassion12 2 жыл бұрын
. Please help me to fix this error .errors_impl.NotFoundError: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for efficientdet_d0_coco17_tpu-32\checkpoint\ckpt-0
@tanloc94
@tanloc94 4 жыл бұрын
2020-11-06 00:05:23.396749: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.1 Traceback (most recent call last): File "model_main_tf2.py", line 32, in from object_detection import model_lib_v2 ImportError: cannot import name 'model_lib_v2'
@mihirkulkarni373
@mihirkulkarni373 4 жыл бұрын
use sys command
@tftmobilechannel5590
@tftmobilechannel5590 3 жыл бұрын
@@mihirkulkarni373 What do you mean bro? Did you face this issue?
@mihirkulkarni373
@mihirkulkarni373 3 жыл бұрын
@@tftmobilechannel5590 yes
@tftmobilechannel5590
@tftmobilechannel5590 3 жыл бұрын
@@mihirkulkarni373 How did you fix it ?
@elune_fx
@elune_fx 3 жыл бұрын
Nice Video.! Now I'm stuck with google colab, on google colab there was a warning called ModuleNotFoundError: No module named 'object_detection' how can i solve this problem>?
@ankursoni8060
@ankursoni8060 3 жыл бұрын
He will never reply if you have doubt...he do the same with every one
@elune_fx
@elune_fx 3 жыл бұрын
@@ankursoni8060 i solved it by myself !! it was directory problem!! my bad :)
@mucahityuksel4196
@mucahityuksel4196 3 жыл бұрын
@@elune_fx how do you solve this pls help
@jojoseph8887
@jojoseph8887 3 жыл бұрын
@@elune_fx how did you solve this problem, pls help
@gunarakulangunaretnam3353
@gunarakulangunaretnam3353 4 жыл бұрын
Hi, It is an amazing tutorial. Thank you so much for this one. I want to know how to export inference graph based on training steps. For example I have trained data like (ckpt-51.index, ckpt-50.index, ckpt-49.index). I want to export the ckpt-49.index steps inference graph. How can I do this. I know that, we can do it in tensorflow 1.X. Please help me out of this problem.
@matassabaliauskas3732
@matassabaliauskas3732 4 жыл бұрын
When exporting inference graph on google collab, use this: - Change "ssd_mobilenet_v1_pets.config" to your config file - Change "training/model.ckpt-3207" to your latest checkpoint (i.e. "training/model.ckpt-51") - Note: I don't think this works on TF2, but it should work with TF1.X !python export_inference_graph.py --input_type image_tensor --pipeline_config_path training/ssd_mobilenet_v1_pets.config --trained_checkpoint_prefix training/model.ckpt-3207 --output_directory new_graph
@jyothilakshmikrishnakumar9398
@jyothilakshmikrishnakumar9398 3 жыл бұрын
I have the same doubt. Were you able to figure it out?. If yes, Kindly guide
@hrikicooray
@hrikicooray 3 жыл бұрын
Traceback (most recent call last): File "model_main_tf2.py", line 32, in from object_detection import model_lib_v2 ModuleNotFoundError: No module named 'object_detection
@Rubyrunner777
@Rubyrunner777 2 жыл бұрын
may you don't make folder name "object_detection"
@burhanuddinlimdiwala6754
@burhanuddinlimdiwala6754 3 жыл бұрын
Hi sir after inference graph how to create frozen model
@85krajek
@85krajek 4 жыл бұрын
hi @When Maths meets coding , When i run your script, i get this msg and script turn itself off.. any idea? Python was not found; run without arguments to install from the Microsoft Store, or disable this shortcut from Settings > Manage App Execution Aliases.
@deepangshudas8674
@deepangshudas8674 4 жыл бұрын
put the python path above the windows app path
@hafizasad8410
@hafizasad8410 3 жыл бұрын
I keep getting this issue every time I'm trying to train. File "C:\Python37\lib\site-packages\tensorflow\python\lib\io\file_io.py", line 80, in _preread_check compat.path_to_str(self.__name), 1024 * 512) esearch\object_detection\images\labelmap.pbtx : The filename, directory name, or volume label syntax is incorrect._detection\models-master ; no protocol option
@jimmypark1791
@jimmypark1791 3 жыл бұрын
Thank you for nice power shell script. while installing i got an error that the following file is damaged or can not be found. how can i solve this problem ? C:\temp_provision\packages\BuildTools_MSBuild_amd64\\BuildTools_MSBuild.msi
@akshayrajm5139
@akshayrajm5139 3 жыл бұрын
Getting this error during "detection_model = tf.saved_model.load('object_detection/inference_graph/saved_model')" any idea on how to fix this, am stuck with this. TensorBundle at object_detection/inference_graph/saved_model\variables\variables shard 0 (331442 bytes): Checksum does not match: stored 3958850664 vs. calculated on the restored bytes 759939483
@БахтиёржонПашшоев
@БахтиёржонПашшоев 3 жыл бұрын
tensorflow.python.framework.errors_impl.AlreadyExistsError: Another metric with the same name already exists. got this error while running on Colab, can you do something?
@techteens694
@techteens694 3 жыл бұрын
I am getting this error when I run the train command in google colab: Traceback (most recent call last): File "model_main_tf2.py", line 32, in from object_detection import model_lib_v2 ModuleNotFoundError: No module named 'object_detection' Can you please help
@mucahityuksel4196
@mucahityuksel4196 3 жыл бұрын
did you solve the problem?
@jojoseph8887
@jojoseph8887 3 жыл бұрын
Same problem
Train Neural Network by loading your images |TensorFlow, CNN, Keras tutorial
18:29
When Maths Meet Coding
Рет қаралды 328 М.
Quando A Diferença De Altura É Muito Grande 😲😂
00:12
Mari Maria
Рет қаралды 45 МЛН
The evil clown plays a prank on the angel
00:39
超人夫妇
Рет қаралды 53 МЛН
小丑女COCO的审判。#天使 #小丑 #超人不会飞
00:53
超人不会飞
Рет қаралды 16 МЛН
How to treat Acne💉
00:31
ISSEI / いっせい
Рет қаралды 108 МЛН
how to train YOLO v3, v4 for custom objects detection | using colab free GPU
35:34
When Maths Meet Coding
Рет қаралды 173 М.
Train YOLO to detect a custom object (online with free GPU)
27:56
How to train test and deploy Tensorlfow model on google colab using streamlit
58:42
Object Detection using OpenCV | Python | Tutorial for beginners 2020
29:29
DeepLearning_by_PhDScholar
Рет қаралды 251 М.
How to Install TensorFlow Object Detection Latest
22:22
When Maths Meet Coding
Рет қаралды 19 М.
Quando A Diferença De Altura É Muito Grande 😲😂
00:12
Mari Maria
Рет қаралды 45 МЛН