search

dusty-nv / jetson-inference

Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.
https://developer.nvidia.com/embedded/twodaystoademo
MIT License
7.85k stars 2.98k forks source link

Failed to save test images to a folder #856

Closed SAIL-LAB155 closed 1 year ago

SAIL-LAB155 commented 3 years ago

Hi. After I trained a cat-dog classification model and was going to test a folder of images using the following command:

_python3 imagenet.py --model=../training/classification/models/cat_dog/resnet18.onnx --input_blob=input_0 --output_blob=output_0 --labels=../training/classification/data/cat_dog/labels.txt ../training/classification/data/cat_dog/test/cat ../training/classification/data/cat_dog/test/test_cat_result_

An error happened:

_[cuda] registered openGL texture for interop access (500x334, GL_RGB8, 501000 bytes) [image] invalid extension format './training/classification/data/cat_dog/test/test_cat_result' saving image '../training/classification/data/cat_dog/test/test_cat_result' [image] valid extensions are: JPG/JPEG, PNG, TGA, BMP. [image] imageWriter -- failed to save '../training/classification/data/cat_dog/test/test_catresult' Traceback (most recent call last): File "/usr/local/bin/imagenet.py", line 77, in output.Render(img) Exception: jetson.utils -- videoOutput failed to render image

The paths are right because I successfully in inferring images without assigning the output folder.

dusty-nv commented 3 years ago

Can you run mkdir ../training/classification/data/cat_dog/test/test_cat_result first?

SAIL-LAB155 commented 3 years ago

Yes, I have created the folder before evaluating. But this error still occurs. The following information is shown below.

hkuit155@hkuit155-desktop:~/jetson-inference/python/examples$ mkdir ../training/classification/data/cat_dog/test/test_cat_result mkdir: cannot create directory ‘../training/classification/data/cat_dog/test/test_cat_result’: File exists hkuit155@hkuit155-desktop:~/jetson-inference/python/examples$ python3 imagenet.py --model=../training/classification/models/cat_dog/resnet18.onnx --input_blob=input_0 --output_blob=output_0 --labels=../training/classification/data/cat_dog/labels.txt ../training/classification/data/cat_dog/test/cat ../training/classification/data/cat_dog/test/test_cat_result jetson.inference -- imageNet loading network using argv command line params

imageNet -- loading classification network model from: -- prototxt (null) -- model ../training/classification/models/cat_dog/resnet18.onnx -- class_labels ../training/classification/data/cat_dog/labels.txt -- input_blob 'input_0' -- output_blob 'output_0' -- batch_size 1

[TRT] TensorRT version 7.1.3 [TRT] loading NVIDIA plugins... [TRT] Registered plugin creator - ::GridAnchor_TRT version 1 [TRT] Registered plugin creator - ::NMS_TRT version 1 [TRT] Registered plugin creator - ::Reorg_TRT version 1 [TRT] Registered plugin creator - ::Region_TRT version 1 [TRT] Registered plugin creator - ::Clip_TRT version 1 [TRT] Registered plugin creator - ::LReLU_TRT version 1 [TRT] Registered plugin creator - ::PriorBox_TRT version 1 [TRT] Registered plugin creator - ::Normalize_TRT version 1 [TRT] Registered plugin creator - ::RPROI_TRT version 1 [TRT] Registered plugin creator - ::BatchedNMS_TRT version 1 [TRT] Could not register plugin creator - ::FlattenConcat_TRT version 1 [TRT] Registered plugin creator - ::CropAndResize version 1 [TRT] Registered plugin creator - ::DetectionLayer_TRT version 1 [TRT] Registered plugin creator - ::Proposal version 1 [TRT] Registered plugin creator - ::ProposalLayer_TRT version 1 [TRT] Registered plugin creator - ::PyramidROIAlign_TRT version 1 [TRT] Registered plugin creator - ::ResizeNearest_TRT version 1 [TRT] Registered plugin creator - ::Split version 1 [TRT] Registered plugin creator - ::SpecialSlice_TRT version 1 [TRT] Registered plugin creator - ::InstanceNormalization_TRT version 1 [TRT] detected model format - ONNX (extension '.onnx') [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 ../training/classification/models/cat_dog/resnet18.onnx.1.1.7103.GPU.FP16.engine [TRT] loading network plan from engine cache... ../training/classification/models/cat_dog/resnet18.onnx.1.1.7103.GPU.FP16.engine [TRT] device GPU, loaded ../training/classification/models/cat_dog/resnet18.onnx [TRT] Using an engine plan file across different models of devices is not recommended and is likely to affect performance or even cause errors. [TRT] Deserialize required 35057804 microseconds. [TRT]
[TRT] CUDA engine context initialized on device GPU: [TRT] -- layers 29 [TRT] -- maxBatchSize 1 [TRT] -- workspace 0 [TRT] -- deviceMemory 29827072 [TRT] -- bindings 2 [TRT] binding 0 -- index 0 -- name 'input_0' -- type FP32 -- in/out INPUT -- # dims 4 -- dim #0 1 (SPATIAL) -- dim #1 3 (SPATIAL) -- dim #2 224 (SPATIAL) -- dim #3 224 (SPATIAL) [TRT] binding 1 -- index 1 -- name 'output_0' -- type FP32 -- in/out OUTPUT -- # dims 2 -- dim #0 1 (SPATIAL) -- dim #1 2 (SPATIAL) [TRT]
[TRT] binding to input 0 input_0 binding index: 0 [TRT] binding to input 0 input_0 dims (b=1 c=3 h=224 w=224) size=602112 [TRT] binding to output 0 output_0 binding index: 1 [TRT] binding to output 0 output_0 dims (b=1 c=2 h=1 w=1) size=8 [TRT]
[TRT] device GPU, ../training/classification/models/cat_dog/resnet18.onnx initialized. [TRT] imageNet -- loaded 2 class info entries [TRT] imageNet -- ../training/classification/models/cat_dog/resnet18.onnx initialized. [video] created imageLoader from file:///home/hkuit155/jetson-inference/python/examples/../training/classification/data/cat_dog/test/cat

imageLoader video options:

-- URI: file:///home/hkuit155/jetson-inference/python/examples/../training/classification/data/cat_dog/test/cat