I cannot download official models for inference

[SchumacherVonHeinz]

According to the guidebook, I found codes for object detection within only 10 lines, like

#inference.py in jetson-inference
import jetson.utils
import jetson.inference
input = jetson.utils.videoSource("csi://0")
output = jetson.utils.videoOutput("display://0")
net = jetson.inference.detectNet("ssd-mobilenet-v2", threshold=0.5)
while output.IsStreaming():
img = input.Capture()
detections = net.Detect(img)
output.Render(img)
output.SetStatus("Performance {:.0f}FPS".format(net.GetNetworkFPS()))`

but after i run "python inference.py", the terminal showed that

[TRT] native precisions detected for GPU: FP32, FP16, INT8
[TRT] selecting fastest native precision for GPU: FP16
[TRT] could not find engine cache .1.1.8502.GPU.FP16.engine
[TRT] cache file invalid, profiling network model on device GPU

error: model file 'networks/SSD-Mobilenet-v2/ssd_mobilenet_v2_coco.uff' was not found.
if loading a built-in model, maybe it wasn't downloaded before.

    Run the Model Downloader tool again and select it for download:

       $ cd <jetson-inference>/tools
       $ ./download-models.sh

[TRT] detectNet -- failed to initialize.
Traceback (most recent call last):
File "inference.py", line 5, in
net = jetson.inference.detectNet("ssd-mobilenet-v2", threshold=0.5)
Exception: jetson.inference -- detectNet failed to load network
(I only pasted the error part)

and I chose the imageNet using AlexNet, but still in failure(almost the same), what should I do to deal with this error? Thank u for ur attention! :)

[dusty-nv]

Here is the model mirror page: https://github.com/dusty-nv/jetson-inference/releases/tag/model-mirror-190618

…

________________________________ From: Knight Von Schumacher ***@***.***> Sent: Monday, July 1, 2024 10:30:27 AM To: dusty-nv/jetson-inference ***@***.***> Cc: Subscribed ***@***.***> Subject: [dusty-nv/jetson-inference] I cannot download official models for inference (Issue #1870) According to the guidebook, I found codes for object detection within only 10 lines, like #inference.py in jetson-inference import jetson.utils import jetson.inference input = jetson.utils.videoSource("csi://0") output = jetson.utils.videoOutput("display://0") net = jetson.inference.detectNet("ssd-mobilenet-v2", threshold=0.5) while output.IsStreaming(): img = input.Capture() detections = net.Detect(img) output.Render(img) output.SetStatus("Performance {:.0f}FPS".format(net.GetNetworkFPS()))` but after i run "python inference.py", the terminal showed that [TRT] native precisions detected for GPU: FP32, FP16, INT8 [TRT] selecting fastest native precision for GPU: FP16 [TRT] could not find engine cache .1.1.8502.GPU.FP16.engine [TRT] cache file invalid, profiling network model on device GPU error: model file 'networks/SSD-Mobilenet-v2/ssd_mobilenet_v2_coco.uff' was not found. if loading a built-in model, maybe it wasn't downloaded before. Run the Model Downloader tool again and select it for download: $ cd <jetson-inference>/tools $ ./download-models.sh [TRT] detectNet -- failed to initialize. Traceback (most recent call last): File "inference.py", line 5, in net = jetson.inference.detectNet("ssd-mobilenet-v2", threshold=0.5) Exception: jetson.inference -- detectNet failed to load network (I only pasted the error part) and I chose the imageNet using AlexNet, but still in failure(almost the same), what should I do to deal with this error? Thank u for ur attention! :) — Reply to this email directly, view it on GitHub<#1870>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/ADVEGK4ACES53T2ZMAGP3JLZKFRYHAVCNFSM6AAAAABKFWSLN6VHI2DSMVQWIX3LMV43ASLTON2WKOZSGM4DIMBRGI2TANI>. You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>

[SchumacherVonHeinz]

Here is the model mirror page: https://github.com/dusty-nv/jetson-inference/releases/tag/model-mirror-190618
…
________________________________ From: Knight Von Schumacher @.> Sent: Monday, July 1, 2024 10:30:27 AM To: dusty-nv/jetson-inference @.> Cc: Subscribed @.> Subject: [dusty-nv/jetson-inference] I cannot download official models for inference (Issue #1870) According to the guidebook, I found codes for object detection within only 10 lines, like #inference.py in jetson-inference import jetson.utils import jetson.inference input = jetson.utils.videoSource("csi://0") output = jetson.utils.videoOutput("display://0") net = jetson.inference.detectNet("ssd-mobilenet-v2", threshold=0.5) while output.IsStreaming(): img = input.Capture() detections = net.Detect(img) output.Render(img) output.SetStatus("Performance {:.0f}FPS".format(net.GetNetworkFPS()))` but after i run "python inference.py", the terminal showed that [TRT] native precisions detected for GPU: FP32, FP16, INT8 [TRT] selecting fastest native precision for GPU: FP16 [TRT] could not find engine cache .1.1.8502.GPU.FP16.engine [TRT] cache file invalid, profiling network model on device GPU error: model file 'networks/SSD-Mobilenet-v2/ssd_mobilenet_v2_coco.uff' was not found. if loading a built-in model, maybe it wasn't downloaded before. Run the Model Downloader tool again and select it for download: $ cd /tools $ ./download-models.sh [TRT] detectNet -- failed to initialize. Traceback (most recent call last): File "inference.py", line 5, in net = jetson.inference.detectNet("ssd-mobilenet-v2", threshold=0.5) Exception: jetson.inference -- detectNet failed to load network (I only pasted the error part) and I chose the imageNet using AlexNet, but still in failure(almost the same), what should I do to deal with this error? Thank u for ur attention! :) — Reply to this email directly, view it on GitHub<#1870>, or unsubscribehttps://github.com/notifications/unsubscribe-auth/ADVEGK4ACES53T2ZMAGP3JLZKFRYHAVCNFSM6AAAAABKFWSLN6VHI2DSMVQWIX3LMV43ASLTON2WKOZSGM4DIMBRGI2TANI. You are receiving this because you are subscribed to this thread.Message ID: @.>

OMG! Thank you for ur fast reply! I'll look it right now!