TensorFlow Object Detection API Tutorial | Object Detection API | TensorFlow Tutorial | Simplilearn

[@SimplilearnOfficial]

"🔥Caltech Post Graduate Program In AI And Machine Learning - www.simplilearn.com/artificial-intelligence-masters-program-training-course?BUAPN3Y&Comments&KZbin 🔥IITK - Professional Certificate Course in Generative AI and Machine Learning (India Only) - www.simplilearn.com/iitk-professional-certificate-course-ai-machine-learning?BUAPN3Y&Comments&KZbin 🔥Purdue - Post Graduate Program in AI and Machine Learning - www.simplilearn.com/pgp-ai-machine-learning-certification-training-course?BUAPN3Y&Comments&KZbin 🔥IITG - Professional Certificate Program in Generative AI and Machine Learning (India Only) - www.simplilearn.com/iitg-generative-ai-machine-learning-program?BUAPN3Y&Comments&KZbin 🔥Caltech - AI & Machine Learning Bootcamp (US Only) - www.simplilearn.com/ai-machine-learning-bootcamp?BUAPN3Y&Comments&KZbin"

[@awaisahmadsiddiqi6505]

Thank you for such a nice tutorial I have a question though. what part of the code is needed to be modified if we need bounding boxes for fewer classes? e.g . I only want to detect cats and cups. and want to ignore anything else?

[@SimplilearnOfficial]

This is a general TensorFlow API code which is trained to detect specific objects from the video. Code cannot be modified to detect only cats and cups. Hope that helps!

[@JulianPegoraro]

@@SimplilearnOfficial BS! you just have to check the "class" values returned from the network (at "sess.run") and only work with those of cats and cups.

[@justchill99902]

Hi! Thank you for this specific video! However, please fix the audio as it is too sharp for the ears! Is it possible to train and run a model for let's say object detection on Virtual Machine? I saw you are also using a VM so I want to ask if it is efficient.

[@SimplilearnOfficial]

Hi Nirbhay, It is possible to train and run a Deep Learning model on a Virtual Machine. In this video, we have used Ubuntu local system for training our Object Detection API. Since this Object Detection is on a video, it is not easy to play a video on the VM using any media player. The frames in the video don't play properly on the VM. However, VM is efficient if you want to carry out object detection on images.

[@sathwikyazwa5992]

How to print the objects detected??

[@SimplilearnOfficial]

Tensorflow API does not allow you to print the objects detected. It only detects those features on which the API is trained on.

[@sbarter]

can not import name 'label_map_util' from utils. doesn't appear to be any such module

[@SimplilearnOfficial]

Hi Stephen, It will great if you can send the exact error message you are getting. That will help us solve your problem better.

[@sbarter]

Simplilearn it took me 3 days but I figured it out. Strangely when trying to import that specific module it tries accessing it from a separate folder called object detection seed rather than the original models folder. Many others had the same issue though my case seems unique. I have no idea when that folder was created or why it decided that is where to access the utils folder but I'm just glad it works now

[@justchill99902]

What did you do to make it work?

[@bassmaammine6585]

Is it possible to add the non_maximum_suppression function? if yes how can we do that ?

[@SimplilearnOfficial]

Yes, it is possible to add non_max_suppression function. It accepts several parameters like boxes, scores, max_output_size, iou_threshold, score_threshold, name. Here, max_output_size is a scalar integer Tensor representing the maximum number of boxes to be selected by non-max suppression. iou_threshold is a float representing the threshold for deciding whether boxes overlap too much with respect to IOU and score_threshold is a float representing the threshold for deciding when to remove boxes based on the score. Hope that helps.

[@bassmaammine6585]

Thank you for the reply. I tried this but I'm getting the following error " ValueError: Shape must be rank 2 but is rank 3 for 'non_max_suppression/NonMaxSuppressionV3' (op: 'NonMaxSuppressionV3') with input shapes: [1,500,4], [1,500], [], [], []. " Any idea how to handle that?

[@josepena2165]

Hi, nice tutotial, im a beginner and i would like to know, how can i agree a notification when it recognized two elements?. thanks

[@hanweijie8092]

What type of object detection algorithm is used in TensorFlow Object Detection API? For example: assuming if I'm using the Faster_RCNN_NAS as my base network, does the algorithm automatically uses to Region Network Proposal approach?

[@akshayjha4785]

Is there a link for the code please?

[@SimplilearnOfficial]

Hi Akshay, thanks for watching our video. It will be great if you can share your email ID with us so that we can send the python code to your email ID immediately. Thanks.

[@stipevickovic9837]

@@SimplilearnOfficial Can you send code on [e-mail] ? Thanks!

[@SimplilearnOfficial]

Hi Stipe, thanks for watching our video. We have sent the requested source code to your mail ID. Do, subscribe to our channel and do not forget to hit the bell icon for never missing another update. Cheers :)

[@xeeonn]

@@SimplilearnOfficial can you please share the code with me ? Thanks .

[@SimplilearnOfficial]

Hi Shri, thanks for watching our video. We have sent the requested source code to your mail ID. Do, subscribe to our channel and do not forget to hit the bell icon for never missing another update. Cheers :)

[@saloninevagi519]

How to interface the CCTV with tensorflow????

[@arunkummarjain9741]

I am getting an error "ModuleNotFoundError: No module named 'utils'". How to resolve this?

[@SimplilearnOfficial]

"Hi Arun, Here is a link that will help you solve this issue: stackoverflow.com/questions/45741254/importerror-no-module-named-utils?rq=1"

[@SimplilearnOfficial]

Thanks for watching the video. The link for the dataset used in the video is provided in the description. Thanks!

[@aditisharma8398]

I have tried the object detection API for testing images by custom training the model. Have tried using the model "faster_rcnn_inception_v2_coco_2018_01_28" Have trained the model and exported the graph. But while testing it using Object Detection API "object_detection_tutorial.ipynb" I am getting error, as given below: KeyError Traceback (most recent call last) in 7 image_np_expanded = np.expand_dims(image_np, axis=0) 8 # Actual detection. ----> 9 output_dict = run_inference_for_single_image(image_np, detection_graph) 10 # Visualization of the results of a detection. 11 vis_util.visualize_boxes_and_labels_on_image_array( in run_inference_for_single_image(image, graph) 29 tensor_dict['detection_masks'] = tf.expand_dims( 30 detection_masks_reframed, 0) ---> 31 image_tensor = tf.get_default_graph().get_tensor_by_name('image_tensor:0') 32 33 # Run inference c:\users\hp\appdata\local\programs\python\python36\lib\site-packages\tensorflow\python\framework\ops.py in get_tensor_by_name(self, name) 3787 raise TypeError("Tensor names are strings (or similar), not %s." % 3788 type(name).__name__) -> 3789 return self.as_graph_element(name, allow_tensor=True, allow_operation=False) 3790 3791 def _get_tensor_by_tf_output(self, tf_output): c:\users\hp\appdata\local\programs\python\python36\lib\site-packages\tensorflow\python\framework\ops.py in as_graph_element(self, obj, allow_tensor, allow_operation) 3611 3612 with self._lock: -> 3613 return self._as_graph_element_locked(obj, allow_tensor, allow_operation) 3614 3615 def _as_graph_element_locked(self, obj, allow_tensor, allow_operation): c:\users\hp\appdata\local\programs\python\python36\lib\site-packages\tensorflow\python\framework\ops.py in _as_graph_element_locked(self, obj, allow_tensor, allow_operation) 3653 raise KeyError("The name %s refers to a Tensor which does not " 3654 "exist. The operation, %s, does not exist in the " -> 3655 "graph." % (repr(name), repr(op_name))) 3656 try: 3657 return op.outputs[out_n] KeyError: "The name 'image_tensor:0' refers to a Tensor which does not exist. The operation, 'image_tensor', does not exist in the graph." What should be done to solve this?

[@ericcute6471]

Hello. Thanks for your videos. Can you help me on how to save the detected object from a live feed and automatically save it as .jpg file whenever a specific object is detected e.g. Person and at the same time, it saves into .CSV file which contains “Person” as text? Thank you in advance.

[@SimplilearnOfficial]

Hello Jean, thanks for viewing our tutorial. It would be helpful if you will provide your email ID to us so that we could send the requested dataset promptly. On the off chance that you need your email ID to be kept hidden from others, we can do that also. Hope that helps.

[@zishanahmedshaikh]

There was the reflection of car on the water which resulted in the second Bounding box in the cat video

[@SimplilearnOfficial]

Exactly. It was because of the reflection of the car on the water that led to the Object Detection API classifying it as a car. Like and share our video with your peers and also do not forget to subscribe to our channel for not missing video updates. We will be coming up with more such videos. Cheers!

[@zishanahmedshaikh]

Subscribed. Could you please make a tutorial on using TFlite with Object detection API?

[@SimplilearnOfficial]

Hi Zishan, thanks for checking out our tutorial and for sharing the information. We will share your suggestion to the relevant department. Do subscribe to our channel to stay posted on upcoming tutorials. Cheers!

[@md.imranuddin1052]

Sir, Is it possible to increase the font size? For example when the cat will detect then show the output "Cat 80%", this font is very small, I want to Large font size. Need this code from GitHub Thank you.

[@SimplilearnOfficial]

Hello Imran, thanks for viewing our tutorial. It would be helpful if you will provide your email ID to us so that we could send the requested dataset promptly. On the off chance that you need your email ID to be kept hidden from others, we can do that also. Hope that helps.

[@aditisagar1357]

hlw sir... Is it possible to run this code on CPU system with 8 GB RAM.

[@SimplilearnOfficial]

Hi Aditi, it is possible to run this code on a CPU system with 8 GB RAM. It will be better if you try running this object detection API on an Ubuntu system because you need to install certain dependencies like "protobuf" and it is very easy to install these dependencies on Ubuntu. Hope that helps. Thanks.

[@sreejasatya8454]

Hi ....is there any link for the source code please??

[@SimplilearnOfficial]

Hello Sreeja, thanks for viewing our tutorial. It would be helpful if you will provide your email ID to us so that we could send the requested dataset promptly. On the off chance that you need your email ID to be kept hidden from others, we can do that also. Hope that helps.

[@gangabhavani468]

How to install object detection

[@SimplilearnOfficial]

Hi Ganga, you can check out this video to know how to install Object Detection: kzbin.info/www/bejne/e5vdppWmYqdradE.

[@mayarelsmanodi3342]

@Simplilearn can you plz send me the code

[@mayarelsmanodi3342]

[e-mail]

[@SimplilearnOfficial]

Hi Mayar, thanks for watching our video. We have sent the requested dataset to your mail ID. Do subscribe to our channel and do not forget to hit the bell icon for never missing another update. Cheers :)

[@rohitkr.9307]

ples provide the source code of this

[@SimplilearnOfficial]

Hello, thanks for viewing our tutorial and we hope it is helpful. It would be helpful if you will provide your email ID to us so that we could send the requested dataset promptly.

[@user-pj6su5lk6o]

Hi sir I am reshma I am doing the object detection for self driving cars

[@SimplilearnOfficial]

All the best!

[@SimplilearnOfficial]

Do you have any questions on this topic? Please share your feedback in the comment section below and we'll have our experts answer it for you. Thanks for watching the video. Cheers!

[@masoudmasoumimoghaddam3832]

the repository for this code? And I searched the web so much but I did not find any pretrained model specifically for car, bike, truck and ... detection (anything related to driving field) which helps better than generalized models in this specific area

[@SimplilearnOfficial]

Hi, thanks for watching our video. We have sent the requested dataset to your mail ID. Do show your love by subscribing to our channel using this link: kzbin.info and don't forget to hit the like button as well. Cheers!

[@swamykorimilli3107]

Hi sir, please sent the source code

[@SimplilearnOfficial]

Hello, thanks for viewing our tutorial. You can find your requested dataset in the video description. Hope that helps.

[@asdf-ef8if]

man please send me the source code

[@SimplilearnOfficial]

Hi, thanks for watching our video. We have sent the source code to your mail ID. Do show your support by subscribing our channel using this link: kzbin.info and don't forget to hit the like button as well. Cheers!

[@SimplilearnOfficial]

It would be helpful if you will provide your email ID to us so that we could send the requested dataset promptly. On the off chance that you need your email ID to be kept hidden from others, we can do that also. Hope that helps.

[@saidsalim5269]

hi @Simplilearn Can you please send me the source code at my mail please...thanks for sharing this alot

[@SimplilearnOfficial]

Hello Salim, thanks for viewing our tutorial. It would be helpful if you will provide your email ID to us so that we could send the requested dataset promptly. On the off chance that you need your email ID to be kept hidden from others, we can do that also. Hope that helps.

[@saidsalim5269]

[e-mail]

[@SimplilearnOfficial]

Hi Salim, thanks for sharing your email ID. We have sent the requested dataset to your mail ID. Do subscribe to our channel to stay posted on upcoming tutorials. Cheers!

[@nilmarpublio]

@Simplilearn can you plz send me the code

[@SimplilearnOfficial]

Hello Nilmar, thanks for viewing our tutorial and we hope it is helpful. It would be helpful if you will provide your email ID to us so that we could send the requested dataset promptly.

[@nilmarpublio]

@@SimplilearnOfficial [e-mail]