Our Community is getting an upgrade! To get everything ready for the relaunch, we’ll be placing the site in read-only mode starting September 21st.
We really appreciate your understanding while we get things set up behind the scenes. Catch up on all the exciting details about the move here.
Need help or have questions? Drop us a line at [email protected]

Cloudera Community

Community Articles

Find and share helpful community-sourced technical articles.
cancel
Turn on suggestions
Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.
Showing results for 
Show  only  | Search instead for 
Did you mean: 
Advanced Search
Announcements
Share your experience with Cloudera on G2 and get a $25 Amazon Gift card.
Hi, I'm CLEO! Something exciting is coming to the Community. Stay Tuned!

Integrating NVIDIA Jetson TX1 Running TensorRT into Deep Learning DataFlows with Apache MiniFi Part 2 of 4 : Classifying Images with ImageNet

avatar
author-rank TimothySpann author-rank
Master Guru

Created on ‎09-09-2017 01:56 PM - edited ‎08-17-2019 11:08 AM

Part 1: Installation and Setup

Part 2: Classifying Images with ImageNet

34725-jetsontx1top.jpg

34726-jetsontx1logo.png

Use This Project: https://github.com/dusty-nv/jetson-inference

This will create a C++ executable to run Classification for ImageNet with TensorRT.

Shell Call Example

root@tegra-ubuntu:/media/nvidia/96ed93f9-7c40-4999-85ba-3eb24262d0a5/jetson-inference-master/build/aarch64/bin# ./runclassify.sh
imagenet-console
  args (3):  0 [/media/nvidia/96ed93f9-7c40-4999-85ba-3eb24262d0a5/jetson-inference-master/build/aarch64/bin/imagenet-console]  1 [backupimages/granny_smith_1.jpg]  2 [images/output_0.jpg]




imageNet -- loading classification network model from:
         -- prototxt     networks/googlenet.prototxt
         -- model        networks/bvlc_googlenet.caffemodel
         -- class_labels networks/ilsvrc12_synset_words.txt
         -- input_blob   'data'
         -- output_blob  'prob'
         -- batch_size   2


[GIE]  attempting to open cache file networks/bvlc_googlenet.caffemodel.2.tensorcache
[GIE]  loading network profile from cache... networks/bvlc_googlenet.caffemodel.2.tensorcache
[GIE]  platform has FP16 support.
[GIE]  networks/bvlc_googlenet.caffemodel loaded
[GIE]  CUDA engine context initialized with 2 bindings
[GIE]  networks/bvlc_googlenet.caffemodel input  binding index:  0
[GIE]  networks/bvlc_googlenet.caffemodel input  dims (b=2 c=3 h=224 w=224) size=1204224
[cuda]  cudaAllocMapped 1204224 bytes, CPU 0x100ce0000 GPU 0x100ce0000
[GIE]  networks/bvlc_googlenet.caffemodel output 0 prob  binding index:  1
[GIE]  networks/bvlc_googlenet.caffemodel output 0 prob  dims (b=2 c=1000 h=1 w=1) size=8000
[cuda]  cudaAllocMapped 8000 bytes, CPU 0x100e20000 GPU 0x100e20000
networks/bvlc_googlenet.caffemodel initialized.
[GIE]  networks/bvlc_googlenet.caffemodel loaded
imageNet -- loaded 1000 class info entries
networks/bvlc_googlenet.caffemodel initialized.
loaded image  backupimages/granny_smith_1.jpg  (1000 x 1000)  16000000 bytes
[cuda]  cudaAllocMapped 16000000 bytes, CPU 0x100f20000 GPU 0x100f20000
[GIE]  layer conv1/7x7_s2 + conv1/relu_7x7 input reformatter 0 - 1.207813 ms
[GIE]  layer conv1/7x7_s2 + conv1/relu_7x7 - 6.144531 ms
[GIE]  layer pool1/3x3_s2 - 1.301354 ms
[GIE]  layer pool1/norm1 - 0.412240 ms
[GIE]  layer conv2/3x3_reduce + conv2/relu_3x3_reduce - 0.737552 ms
[GIE]  layer conv2/3x3 + conv2/relu_3x3 - 11.184843 ms
[GIE]  layer conv2/norm2 - 1.052657 ms
[GIE]  layer pool2/3x3_s2 - 0.946510 ms
[GIE]  layer inception_3a/1x1 + inception_3a/relu_1x1 || inception_3a/3x3_reduce + inception_3a/relu_3x3_reduce || inception_3a/5x5_reduce + inception_3a/relu_5x5_reduce - 1.299844 ms
[GIE]  layer inception_3a/3x3 + inception_3a/relu_3x3 - 3.431562 ms
[GIE]  layer inception_3a/5x5 + inception_3a/relu_5x5 - 0.697657 ms
[GIE]  layer inception_3a/pool - 0.449479 ms
[GIE]  layer inception_3a/pool_proj + inception_3a/relu_pool_proj - 0.542916 ms
[GIE]  layer inception_3a/1x1 copy - 0.074375 ms
[GIE]  layer inception_3b/1x1 + inception_3b/relu_1x1 || inception_3b/3x3_reduce + inception_3b/relu_3x3_reduce || inception_3b/5x5_reduce + inception_3b/relu_5x5_reduce - 2.582917 ms
[GIE]  layer inception_3b/3x3 + inception_3b/relu_3x3 - 6.324167 ms
[GIE]  layer inception_3b/5x5 + inception_3b/relu_5x5 - 3.262968 ms
[GIE]  layer inception_3b/pool - 0.586719 ms
[GIE]  layer inception_3b/pool_proj + inception_3b/relu_pool_proj - 0.657552 ms
[GIE]  layer inception_3b/1x1 copy - 0.111511 ms
[GIE]  layer pool3/3x3_s2 - 0.608333 ms
[GIE]  layer inception_4a/1x1 + inception_4a/relu_1x1 || inception_4a/3x3_reduce + inception_4a/relu_3x3_reduce || inception_4a/5x5_reduce + inception_4a/relu_5x5_reduce - 1.589531 ms
[GIE]  layer inception_4a/3x3 + inception_4a/relu_3x3 - 1.027396 ms
[GIE]  layer inception_4a/5x5 + inception_4a/relu_5x5 - 0.420052 ms
[GIE]  layer inception_4a/pool - 0.306563 ms
[GIE]  layer inception_4a/pool_proj + inception_4a/relu_pool_proj - 0.464583 ms
[GIE]  layer inception_4a/1x1 copy - 0.060417 ms
[GIE]  layer inception_4b/1x1 + inception_4b/relu_1x1 || inception_4b/3x3_reduce + inception_4b/relu_3x3_reduce || inception_4b/5x5_reduce + inception_4b/relu_5x5_reduce - 1.416875 ms
[GIE]  layer inception_4b/3x3 + inception_4b/relu_3x3 - 1.157135 ms
[GIE]  layer inception_4b/5x5 + inception_4b/relu_5x5 - 0.555886 ms
[GIE]  layer inception_4b/pool - 0.331354 ms
[GIE]  layer inception_4b/pool_proj + inception_4b/relu_pool_proj - 0.485677 ms
[GIE]  layer inception_4b/1x1 copy - 0.056041 ms
[GIE]  layer inception_4c/1x1 + inception_4c/relu_1x1 || inception_4c/3x3_reduce + inception_4c/relu_3x3_reduce || inception_4c/5x5_reduce + inception_4c/relu_5x5_reduce - 1.454011 ms
[GIE]  layer inception_4c/3x3 + inception_4c/relu_3x3 - 2.771198 ms
[GIE]  layer inception_4c/5x5 + inception_4c/relu_5x5 - 0.554844 ms
[GIE]  layer inception_4c/pool - 0.502604 ms
[GIE]  layer inception_4c/pool_proj + inception_4c/relu_pool_proj - 0.486198 ms
[GIE]  layer inception_4c/1x1 copy - 0.050833 ms
[GIE]  layer inception_4d/1x1 + inception_4d/relu_1x1 || inception_4d/3x3_reduce + inception_4d/relu_3x3_reduce || inception_4d/5x5_reduce + inception_4d/relu_5x5_reduce - 1.419271 ms
[GIE]  layer inception_4d/3x3 + inception_4d/relu_3x3 - 1.781406 ms
[GIE]  layer inception_4d/5x5 + inception_4d/relu_5x5 - 0.680052 ms
[GIE]  layer inception_4d/pool - 0.333542 ms
[GIE]  layer inception_4d/pool_proj + inception_4d/relu_pool_proj - 0.483854 ms
[GIE]  layer inception_4d/1x1 copy - 0.048229 ms
[GIE]  layer inception_4e/1x1 + inception_4e/relu_1x1 || inception_4e/3x3_reduce + inception_4e/relu_3x3_reduce || inception_4e/5x5_reduce + inception_4e/relu_5x5_reduce - 2.225573 ms
[GIE]  layer inception_4e/3x3 + inception_4e/relu_3x3 - 4.142656 ms
[GIE]  layer inception_4e/5x5 + inception_4e/relu_5x5 - 0.954427 ms
[GIE]  layer inception_4e/pool - 0.332917 ms
[GIE]  layer inception_4e/pool_proj + inception_4e/relu_pool_proj - 0.667344 ms
[GIE]  layer inception_4e/1x1 copy - 0.071666 ms
[GIE]  layer pool4/3x3_s2 - 0.275625 ms
[GIE]  layer inception_5a/1x1 + inception_5a/relu_1x1 || inception_5a/3x3_reduce + inception_5a/relu_3x3_reduce || inception_5a/5x5_reduce + inception_5a/relu_5x5_reduce - 1.685417 ms
[GIE]  layer inception_5a/3x3 + inception_5a/relu_3x3 - 2.085990 ms
[GIE]  layer inception_5a/5x5 + inception_5a/relu_5x5 - 0.391198 ms
[GIE]  layer inception_5a/pool - 0.187552 ms
[GIE]  layer inception_5a/pool_proj + inception_5a/relu_pool_proj - 0.964791 ms
[GIE]  layer inception_5a/1x1 copy - 0.041094 ms
[GIE]  layer inception_5b/1x1 + inception_5b/relu_1x1 || inception_5b/3x3_reduce + inception_5b/relu_3x3_reduce || inception_5b/5x5_reduce + inception_5b/relu_5x5_reduce - 2.327656 ms
[GIE]  layer inception_5b/3x3 + inception_5b/relu_3x3 - 1.884532 ms
[GIE]  layer inception_5b/5x5 + inception_5b/relu_5x5 - 1.364895 ms
[GIE]  layer inception_5b/pool - 0.189219 ms
[GIE]  layer inception_5b/pool_proj + inception_5b/relu_pool_proj - 0.453490 ms
[GIE]  layer inception_5b/1x1 copy - 0.045781 ms
[GIE]  layer pool5/7x7_s1 - 0.743281 ms
[GIE]  layer loss3/classifier input reformatter 0 - 0.042552 ms
[GIE]  layer loss3/classifier - 0.848386 ms
[GIE]  layer loss3/classifier output reformatter 0 - 0.042969 ms
[GIE]  layer prob - 0.092343 ms
[GIE]  layer prob output reformatter 0 - 0.042552 ms
[GIE]  layer network time - 84.158958 ms
class 0948 - 1.000000  (Granny Smith)
imagenet-console:  'backupimages/granny_smith_1.jpg' -> 100.00000% class #948 (Granny Smith)
loaded image  fontmapA.png  (256 x 512)  2097152 bytes
[cuda]  cudaAllocMapped 2097152 bytes, CPU 0x101fa0000 GPU 0x101fa0000
[cuda]  cudaAllocMapped 8192 bytes, CPU 0x100e22000 GPU 0x100e22000
imagenet-console:  attempting to save output image to 'images/output_0.jpg'
imagenet-console:  completed saving 'images/output_0.jpg'


shutting down...

Input File

34766-tim.jpg

Output File

34765-output-tim-1.jpg

The output image contains the highest probability of what's in the image. This one says sunscreen which is a bit weird, I am guessing because my original image is very sunny.

Source Code

https://github.com/tspannhw/jetsontx1-TensorRT

Resources

  1. http://www.jetsonhacks.com/2017/01/28/install-samsung-ssd-on-nvidia-jetson-tx1/
  2. https://github.com/PhilipChicco/pedestrianSys
  3. https://github.com/jetsonhacks?tab=repositories
  4. https://github.com/Netzeband/JetsonTX1_im2txt
  5. https://github.com/DJTobias/Cherry-Autonomous-Racecar
  6. https://github.com/jetsonhacks/postFlashTX1
  7. https://github.com/jetsonhacks/installTensorFlowTX1
  8. http://www.jetsonhacks.com/2016/12/21/jetson-tx1-swap-file-and-development-preparation/
2,164 Views
Announcements
Community Announcements
Community Upgrade Announcement
What's New @ Cloudera
Announcing Cloudera Flow Management Operator for Kubernetes ...
What's New @ Cloudera
Announcing Cloudera Streams Messaging Operator for Kubernete...
Community Announcements
July 2026 Community Highlights
Community Announcements
June 2026 Community Highlights
View More Announcements
Version history
Last update:
‎08-17-2019 11:08 AM
Updated by:
Master Guru Master Guru
Contributors