I have compiled the hello AI world / imagenet app on my nano (in a docker container running Jetpack 4.3) and I am having an unusual problem. The imagenet app seems to start just fine, but I don’t see anything on the display. it appears to just be running in the background. Any ideas what I am missing? It is using a CSI camera as a source, which I have confirmed works in gstreamer on the nano when just displaying to the screen. Below are the log outputs from imagenet:
[gstreamer] initialized gstreamer, version 1.14.5.0
[gstreamer] gstCamera -- attempting to create device csi://0
[gstreamer] gstCamera pipeline string:
[gstreamer] nvarguscamerasrc sensor-id=0 ! video/x-raw(memory:NVMM), width=(int)1280, height=(int)720, framerate=30/1, format=(string)NV12 ! nvvidconv flip-method=2 ! video/x-raw ! appsink name=mysink
[gstreamer] gstCamera successfully created device csi://0
[video] created gstCamera from csi://0
------------------------------------------------
gstCamera video options:
------------------------------------------------
-- URI: csi://0
- protocol: csi
- location: 0
-- deviceType: csi
-- ioType: input
-- codec: raw
-- width: 1280
-- height: 720
-- frameRate: 30.000000
-- bitRate: 0
-- numBuffers: 4
-- zeroCopy: true
-- flipMethod: rotate-180
-- loop: 0
------------------------------------------------
[OpenGL] glDisplay -- X screen 0 resolution: 1280x800
[OpenGL] glDisplay -- X window resolution: 1280x800
[OpenGL] glDisplay -- display device initialized (1280x800)
[video] created glDisplay from display://0
------------------------------------------------
glDisplay video options:
------------------------------------------------
-- URI: display://0
- protocol: display
- location: 0
-- deviceType: display
-- ioType: output
-- codec: raw
-- width: 1280
-- height: 800
-- frameRate: 0.000000
-- bitRate: 0
-- numBuffers: 4
-- zeroCopy: true
-- flipMethod: none
-- loop: 0
------------------------------------------------
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 1
[TRT] TensorRT version 6.0.1
[TRT] loading NVIDIA plugins...
[TRT] Plugin Creator registration succeeded - GridAnchor_TRT
[TRT] Plugin Creator registration succeeded - GridAnchorRect_TRT
[TRT] Plugin Creator registration succeeded - NMS_TRT
[TRT] Plugin Creator registration succeeded - Reorg_TRT
[TRT] Plugin Creator registration succeeded - Region_TRT
[TRT] Plugin Creator registration succeeded - Clip_TRT
[TRT] Plugin Creator registration succeeded - LReLU_TRT
[TRT] Plugin Creator registration succeeded - PriorBox_TRT
[TRT] Plugin Creator registration succeeded - Normalize_TRT
[TRT] Plugin Creator registration succeeded - RPROI_TRT
[TRT] Plugin Creator registration succeeded - BatchedNMS_TRT
[TRT] Could not register plugin creator: FlattenConcat_TRT in namespace:
[TRT] detected model format - caffe (extension '.caffemodel')
[TRT] desired precision specified for GPU: FASTEST
[TRT] requested fasted precision for device GPU without providing valid calibrator, disabling INT8
[TRT] native precisions detected for GPU: FP32, FP16
[TRT] selecting fastest native precision for GPU: FP16
[TRT] attempting to open engine cache file /usr/local/bin/networks/bvlc_googlenet.caffemodel.1.1.6001.GPU.FP16.engine
[TRT] cache file not found, profiling network model on device GPU
[TRT] device GPU, loading /usr/local/bin/networks/googlenet.prototxt /usr/local/bin/networks/bvlc_googlenet.caffemodel
[TRT] device GPU, configuring network builder
[TRT] device GPU, building FP16: ON
[TRT] device GPU, building INT8: OFF
[TRT] device GPU, building CUDA engine (this may take a few minutes the first time a network is loaded)
[TRT] Applying generic optimizations to the graph for inference.
[TRT] Original: 141 layers
[TRT] After dead-layer removal: 141 layers
[TRT] After scale fusion: 141 layers
[TRT] Fusing conv1/7x7_s2 with conv1/relu_7x7
[TRT] Fusing conv2/3x3_reduce with conv2/relu_3x3_reduce
[TRT] Fusing conv2/3x3 with conv2/relu_3x3
[TRT] Fusing inception_3a/1x1 with inception_3a/relu_1x1
[TRT] Fusing inception_3a/3x3_reduce with inception_3a/relu_3x3_reduce
[TRT] Fusing inception_3a/3x3 with inception_3a/relu_3x3
[TRT] Fusing inception_3a/5x5_reduce with inception_3a/relu_5x5_reduce
[TRT] Fusing inception_3a/5x5 with inception_3a/relu_5x5
[TRT] Fusing inception_3a/pool_proj with inception_3a/relu_pool_proj
[TRT] Fusing inception_3b/1x1 with inception_3b/relu_1x1
[TRT] Fusing inception_3b/3x3_reduce with inception_3b/relu_3x3_reduce
[TRT] Fusing inception_3b/3x3 with inception_3b/relu_3x3
[TRT] Fusing inception_3b/5x5_reduce with inception_3b/relu_5x5_reduce
[TRT] Fusing inception_3b/5x5 with inception_3b/relu_5x5
[TRT] Fusing inception_3b/pool_proj with inception_3b/relu_pool_proj
[TRT] Fusing inception_4a/1x1 with inception_4a/relu_1x1
[TRT] Fusing inception_4a/3x3_reduce with inception_4a/relu_3x3_reduce
[TRT] Fusing inception_4a/3x3 with inception_4a/relu_3x3
[TRT] Fusing inception_4a/5x5_reduce with inception_4a/relu_5x5_reduce
[TRT] Fusing inception_4a/5x5 with inception_4a/relu_5x5
[TRT] Fusing inception_4a/pool_proj with inception_4a/relu_pool_proj
[TRT] Fusing inception_4b/1x1 with inception_4b/relu_1x1
[TRT] Fusing inception_4b/3x3_reduce with inception_4b/relu_3x3_reduce
[TRT] Fusing inception_4b/3x3 with inception_4b/relu_3x3
[TRT] Fusing inception_4b/5x5_reduce with inception_4b/relu_5x5_reduce
[TRT] Fusing inception_4b/5x5 with inception_4b/relu_5x5
[TRT] Fusing inception_4b/pool_proj with inception_4b/relu_pool_proj
[TRT] Fusing inception_4c/1x1 with inception_4c/relu_1x1
[TRT] Fusing inception_4c/3x3_reduce with inception_4c/relu_3x3_reduce
[TRT] Fusing inception_4c/3x3 with inception_4c/relu_3x3
[TRT] Fusing inception_4c/5x5_reduce with inception_4c/relu_5x5_reduce
[TRT] Fusing inception_4c/5x5 with inception_4c/relu_5x5
[TRT] Fusing inception_4c/pool_proj with inception_4c/relu_pool_proj
[TRT] Fusing inception_4d/1x1 with inception_4d/relu_1x1
[TRT] Fusing inception_4d/3x3_reduce with inception_4d/relu_3x3_reduce
[TRT] Fusing inception_4d/3x3 with inception_4d/relu_3x3
[TRT] Fusing inception_4d/5x5_reduce with inception_4d/relu_5x5_reduce
[TRT] Fusing inception_4d/5x5 with inception_4d/relu_5x5
[TRT] Fusing inception_4d/pool_proj with inception_4d/relu_pool_proj
[TRT] Fusing inception_4e/1x1 with inception_4e/relu_1x1
[TRT] Fusing inception_4e/3x3_reduce with inception_4e/relu_3x3_reduce
[TRT] Fusing inception_4e/3x3 with inception_4e/relu_3x3
[TRT] Fusing inception_4e/5x5_reduce with inception_4e/relu_5x5_reduce
[TRT] Fusing inception_4e/5x5 with inception_4e/relu_5x5
[TRT] Fusing inception_4e/pool_proj with inception_4e/relu_pool_proj
[TRT] Fusing inception_5a/1x1 with inception_5a/relu_1x1
[TRT] Fusing inception_5a/3x3_reduce with inception_5a/relu_3x3_reduce
[TRT] Fusing inception_5a/3x3 with inception_5a/relu_3x3
[TRT] Fusing inception_5a/5x5_reduce with inception_5a/relu_5x5_reduce
[TRT] Fusing inception_5a/5x5 with inception_5a/relu_5x5
[TRT] Fusing inception_5a/pool_proj with inception_5a/relu_pool_proj
[TRT] Fusing inception_5b/1x1 with inception_5b/relu_1x1
[TRT] Fusing inception_5b/3x3_reduce with inception_5b/relu_3x3_reduce
[TRT] Fusing inception_5b/3x3 with inception_5b/relu_3x3
[TRT] Fusing inception_5b/5x5_reduce with inception_5b/relu_5x5_reduce
[TRT] Fusing inception_5b/5x5 with inception_5b/relu_5x5
[TRT] Fusing inception_5b/pool_proj with inception_5b/relu_pool_proj
[TRT] After vertical fusions: 84 layers
[TRT] After final dead-layer removal: 84 layers
[TRT] Merging layers: 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
[TRT] Merging layers: 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
[TRT] Merging layers: 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
[TRT] Merging layers: 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
[TRT] Merging layers: 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
[TRT] Merging layers: 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
[TRT] Merging layers: 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
[TRT] Merging layers: 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
[TRT] Merging layers: 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
[TRT] After tensor merging: 66 layers
[TRT] Eliminating concatenation inception_3a/output
[TRT] Generating copy for 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 to inception_3a/output
[TRT] Retargeting inception_3a/3x3 to inception_3a/output
[TRT] Retargeting inception_3a/5x5 to inception_3a/output
[TRT] Retargeting inception_3a/pool_proj to inception_3a/output
[TRT] Eliminating concatenation inception_3b/output
[TRT] Generating copy for 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 to inception_3b/output
[TRT] Retargeting inception_3b/3x3 to inception_3b/output
[TRT] Retargeting inception_3b/5x5 to inception_3b/output
[TRT] Retargeting inception_3b/pool_proj to inception_3b/output
[TRT] Eliminating concatenation inception_4a/output
[TRT] Generating copy for 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 to inception_4a/output
[TRT] Retargeting inception_4a/3x3 to inception_4a/output
[TRT] Retargeting inception_4a/5x5 to inception_4a/output
[TRT] Retargeting inception_4a/pool_proj to inception_4a/output
[TRT] Eliminating concatenation inception_4b/output
[TRT] Generating copy for 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 to inception_4b/output
[TRT] Retargeting inception_4b/3x3 to inception_4b/output
[TRT] Retargeting inception_4b/5x5 to inception_4b/output
[TRT] Retargeting inception_4b/pool_proj to inception_4b/output
[TRT] Eliminating concatenation inception_4c/output
[TRT] Generating copy for 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 to inception_4c/output
[TRT] Retargeting inception_4c/3x3 to inception_4c/output
[TRT] Retargeting inception_4c/5x5 to inception_4c/output
[TRT] Retargeting inception_4c/pool_proj to inception_4c/output
[TRT] Eliminating concatenation inception_4d/output
[TRT] Generating copy for 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 to inception_4d/output
[TRT] Retargeting inception_4d/3x3 to inception_4d/output
[TRT] Retargeting inception_4d/5x5 to inception_4d/output
[TRT] Retargeting inception_4d/pool_proj to inception_4d/output
[TRT] Eliminating concatenation inception_4e/output
[TRT] Generating copy for 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 to inception_4e/output
[TRT] Retargeting inception_4e/3x3 to inception_4e/output
[TRT] Retargeting inception_4e/5x5 to inception_4e/output
[TRT] Retargeting inception_4e/pool_proj to inception_4e/output
[TRT] Eliminating concatenation inception_5a/output
[TRT] Generating copy for 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 to inception_5a/output
[TRT] Retargeting inception_5a/3x3 to inception_5a/output
[TRT] Retargeting inception_5a/5x5 to inception_5a/output
[TRT] Retargeting inception_5a/pool_proj to inception_5a/output
[TRT] Eliminating concatenation inception_5b/output
[TRT] Generating copy for 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 to inception_5b/output
[TRT] Retargeting inception_5b/3x3 to inception_5b/output
[TRT] Retargeting inception_5b/5x5 to inception_5b/output
[TRT] Retargeting inception_5b/pool_proj to inception_5b/output
[TRT] After concat removal: 66 layers
[TRT] Graph construction and optimization completed in 0.0414486 seconds.
[TRT] Constructing optimization profile number 0 out of 1
--------------- Timing Runner: <reformat> (Reformat)
[TRT] Tactic: 1002 time 1.07091
[TRT] Tactic: 0 time 0.919375
[TRT] Fastest Tactic: 0 Time: 0.919375
[TRT] --------------- Timing Runner: <reformat> (Reformat)
[TRT] Tactic: 1002 time 5.04237
[TRT] Tactic: 0 time 0.332031
[TRT] Fastest Tactic: 0 Time: 0.332031
[TRT] *************** Autotuning format combination: Float(1,224,50176,150528) -> Float(1,112,12544,802816) ***************
[TRT] --------------- Timing Runner: conv1/7x7_s2 + conv1/relu_7x7 (LegacySASSConvolution)
[TRT] Tactic: 0 time 3.55414
[TRT] Fastest Tactic: 0 Time: 3.55414
[TRT] --------------- Timing Runner: conv1/7x7_s2 + conv1/relu_7x7 (FusedConvActConvolution)
[TRT] Tactic: 1 time 6.32964
[TRT] Tactic: 49 time 3.71888
[TRT] Tactic: 128 time 3.72315
[TRT] Fastest Tactic: 49 Time: 3.71888
[TRT] --------------- Timing Runner: conv1/7x7_s2 + conv1/relu_7x7 (CaskConvolution)
[TRT] conv1/7x7_s2 + conv1/relu_7x7 (scudnn) Set Tactic Name: maxwell_scudnn_128x32_relu_medium_nn_v1
[TRT] Tactic: 1062367460111450758 time 2.52573
[TRT] conv1/7x7_s2 + conv1/relu_7x7 (scudnn) Set Tactic Name: maxwell_scudnn_128x64_relu_large_nn_v1
[TRT] Tactic: 4337000649858996379 time 2.03492
[TRT] conv1/7x7_s2 + conv1/relu_7x7 (scudnn) Set Tactic Name: maxwell_scudnn_128x128_relu_medium_nn_v1
[TRT] Tactic: 4501471010995462441 time 3.93099
[TRT] conv1/7x7_s2 + conv1/relu_7x7 (scudnn) Set Tactic Name: maxwell_scudnn_128x64_relu_medium_nn_v1
[TRT] Tactic: 6645123197870846056 time 2.00141
[TRT] conv1/7x7_s2 + conv1/relu_7x7 (scudnn) Set Tactic Name: maxwell_scudnn_128x128_relu_large_nn_v1
[TRT] Tactic: -9137461792520977713 time 3.96133
[TRT] conv1/7x7_s2 + conv1/relu_7x7 (scudnn) Set Tactic Name: maxwell_scudnn_128x32_relu_large_nn_v1
[TRT] Tactic: -6092040395344634144 time 2.59784
[TRT] Fastest Tactic: 6645123197870846056 Time: 2.00141
[TRT] --------------- Timing Runner: conv1/7x7_s2 + conv1/relu_7x7 (CudaConvolution)
[TRT] Tactic: 0 time 4.6825
^Creceived SIGINT
[TRT] Tactic: 1 time 2.61185
[TRT] Tactic: 2 time 4.2749
[TRT] Fastest Tactic: 1 Time: 2.61185
[TRT] --------------- Timing Runner: conv1/7x7_s2 + conv1/relu_7x7 (CudaDepthwiseConvolution)
[TRT] CudaDepthwiseConvolution has no valid tactics for this config, skipping
[TRT] >>>>>>>>>>>>>>> Chose Runner Type: CaskConvolution Tactic: 6645123197870846056
[TRT] conv1/7x7_s2 + conv1/relu_7x7 (scudnn) Set Tactic Name: maxwell_scudnn_128x64_relu_medium_nn_v1
[TRT]
[TRT] *************** Autotuning format combination: Half(1,224,50176,150528) -> Half(1,112,12544,802816) ***************
[TRT] --------------- Timing Runner: conv1/7x7_s2 + conv1/relu_7x7 (FusedConvActConvolution)
[TRT] FusedConvActConvolution has no valid tactics for this config, skipping
[TRT] --------------- Timing Runner: conv1/7x7_s2 + conv1/relu_7x7 (CaskConvolution)
[TRT] CaskConvolution has no valid tactics for this config, skipping
[TRT] --------------- Timing Runner: conv1/7x7_s2 + conv1/relu_7x7 (CudaConvolution)
[TRT] Tactic: 0 time 4.32685
[TRT] Tactic: 1 time 2.27575
[TRT] Tactic: 2 time 3.47664
[TRT] Fastest Tactic: 1 Time: 2.27575
[TRT] --------------- Timing Runner: conv1/7x7_s2 + conv1/relu_7x7 (CudaDepthwiseConvolution)
[TRT] CudaDepthwiseConvolution has no valid tactics for this config, skipping
[TRT] >>>>>>>>>>>>>>> Chose Runner Type: CudaConvolution Tactic: 1
[TRT]
[TRT] *************** Autotuning format combination: Half(1,224,50176:2,100352) -> Half(1,112,12544:2,401408) ***************
[TRT] --------------- Timing Runner: conv1/7x7_s2 + conv1/relu_7x7 (LegacySASSConvolution)
[TRT] Tactic: 0 time 1.10445
[TRT] Fastest Tactic: 0 Time: 1.10445
[TRT] --------------- Timing Runner: conv1/7x7_s2 + conv1/relu_7x7 (FusedConvActConvolution)
[TRT] FusedConvActConvolution has no valid tactics for this config, skipping
[TRT] --------------- Timing Runner: conv1/7x7_s2 + conv1/relu_7x7 (CaskConvolution)
[TRT] conv1/7x7_s2 + conv1/relu_7x7 (hcudnn) Set Tactic Name: maxwell_fp16x2_hcudnn_fp16x2_128x32_relu_medium_nn_v1
[TRT] Tactic: 3564772625446233998 time 1.44518
[TRT] conv1/7x7_s2 + conv1/relu_7x7 (hcudnn) Set Tactic Name: maxwell_fp16x2_hcudnn_fp16x2_128x32_relu_large_nn_v1
[TRT] Tactic: 3650389455493082349 time 1.48325
[TRT] conv1/7x7_s2 + conv1/relu_7x7 (hcudnn) Set Tactic Name: maxwell_fp16x2_hcudnn_fp16x2_128x64_relu_medium_nn_v1
[TRT] Tactic: 7205456024582378848 time 1.12039
[TRT] conv1/7x7_s2 + conv1/relu_7x7 (hcudnn) Set Tactic Name: maxwell_fp16x2_hcudnn_fp16x2_128x64_relu_large_nn_v1
[TRT] Tactic: -6490690591794140522 time 1.12956
[TRT] conv1/7x7_s2 + conv1/relu_7x7 (hcudnn) Set Tactic Name: maxwell_fp16x2_hcudnn_fp16x2_128x128_relu_large_nn_v1
[TRT] Tactic: -4686027666808657977 time 2.21453
[TRT] conv1/7x7_s2 + conv1/relu_7x7 (hcudnn) Set Tactic Name: maxwell_fp16x2_hcudnn_fp16x2_128x128_relu_medium_nn_v1
[TRT] Tactic: -3898373634979201110 time 2.1975
[TRT] Fastest Tactic: 7205456024582378848 Time: 1.12039
[TRT] --------------- Timing Runner: conv1/7x7_s2 + conv1/relu_7x7 (CudaConvolution)
[TRT] CudaConvolution has no valid tactics for this config, skipping
[TRT] --------------- Timing Runner: conv1/7x7_s2 + conv1/relu_7x7 (CudaDepthwiseConvolution)
[TRT] CudaDepthwiseConvolution has no valid tactics for this config, skipping
[TRT] >>>>>>>>>>>>>>> Chose Runner Type: LegacySASSConvolution Tactic: 0
[TRT]
[TRT] --------------- Timing Runner: <reformat> (Reformat)
[TRT] Tactic: 1002 time 0.561328
[TRT] Tactic: 0 time 0.820338
[TRT] Fastest Tactic: 1002 Time: 0.561328
[TRT] --------------- Timing Runner: <reformat> (Reformat)
[TRT] Tactic: 1002 time 1.69521
[TRT] Tactic: 0 time 0.657552
[TRT] Fastest Tactic: 0 Time: 0.657552
[TRT] --------------- Timing Runner: <reformat> (Reformat)
[TRT] Tactic: 1002 time 0.568229
[TRT] Tactic: 0 time 0.696745
[TRT] Fastest Tactic: 1002 Time: 0.568229
[TRT] --------------- Timing Runner: <reformat> (Reformat)
[TRT] Tactic: 1002 time 1.69677
[TRT] Tactic: 0 time 0.643593
[TRT] Fastest Tactic: 0 Time: 0.643593
[TRT] --------------- Timing Runner: <reformat> (Reformat)
[TRT] Tactic: 1002 time 2.21883
[TRT] Tactic: 0 time 0.597579
[TRT] Fastest Tactic: 0 Time: 0.597579
[TRT] --------------- Timing Runner: <reformat> (Reformat)
[TRT] Tactic: 1002 time 2.2151
[TRT] Tactic: 0 time 0.587552
[TRT] Fastest Tactic: 0 Time: 0.587552
[TRT] *************** Autotuning format combination: Float(1,112,12544,802816) -> Float(1,56,3136,200704) ***************
[TRT] --------------- Timing Runner: pool1/3x3_s2 (Pooling)
[TRT] Tactic: -1 time 0.624636
[TRT] Fastest Tactic: -1 Time: 0.624636
...