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

This TensorFlow tutorial will take you through the TensorFlow code to perform object detection in a video. TensorFlow object detection API which is an open source framework built on top of TensorFlow that makes it easy to construct, train and deploy object detection models and also it provides a collection of detection models pre-trained on the COCO dataset, the Kitti dataset, and the Open Images dataset. One among the many detection models is the combination of single shot detectors (SSDs) and MobileNets architecture which is fast, efficient and does not require the huge computational capability to accomplish the object detection task, an example of which can be seen in this tutorial. Now, let's get started and understand how object detection using TensorFlow works.

#DeepLearning #Datasciencecourse #DataScience #SimplilearnMachineLearning #DeepLearningCourse

➡️ About Post Graduate Program In AI And Machine Learning

This AI ML course is designed to enhance your career in AI and ML by demystifying concepts like machine learning, deep learning, NLP, computer vision, reinforcement learning, and more. You'll also have access to 4 live sessions, led by industry experts, covering the latest advancements in AI such as generative modeling, ChatGPT, OpenAI, and chatbots.

✅ Key Features

- Post Graduate Program certificate and Alumni Association membership
- Exclusive hackathons and Ask me Anything sessions by IBM
- 3 Capstones and 25+ Projects with industry data sets from Twitter, Uber, Mercedes Benz, and many more
- Master Classes delivered by Purdue faculty and IBM experts
- Simplilearn's JobAssist helps you get noticed by top hiring companies
- Gain access to 4 live online sessions on latest AI trends such as ChatGPT, generative AI, explainable AI, and more
- Learn about the applications of ChatGPT, OpenAI, Dall-E, Midjourney & other prominent tools

✅ Skills Covered

- ChatGPT
- Generative AI
- Explainable AI
- Generative Modeling
- Statistics
- Python
- Supervised Learning
- Unsupervised Learning
- NLP
- Neural Networks
- Computer Vision
- And Many More…

👉 Learn More At:

🔥🔥 Interested in Attending Live Classes? Call Us: IN - 18002127688 / US - [phone]

[SimplilearnOfficial]

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

[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!

[awaisahmadsiddiqi]

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?

[justchill]

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.

[hanweijie]

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?

[josepena]

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

[ericcute]

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.

[md.imranuddin]

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.

[aditisharma]

I have tried the object detection API for testing images by custom training the model.
Have tried using the model
Have trained the model and exported the graph. But while testing it using Object Detection API I am getting error, as given below:

KeyError Traceback (most recent call last)
in <module>
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

in run_inference_for_single_image(image, graph)
29 = tf.expand_dims(
30 detection_masks_reframed, 0)
---> 31 image_tensor =
32
33 # Run inference

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):

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):

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?

[bassmaammine]

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

[arunkummarjain]

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

[sbarter]

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

[sreejasatya]

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

[zishanahmedshaikh]

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

[aditisagar]

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

[saloninevagi]

How to interface the CCTV with tensorflow????

[mayarelsmanodi]

@Simplilearn can you plz send me the code

[pjsulko]

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

[saidsalim]

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

[nilmarpublio]

@Simplilearn can you plz send me the code