PyMNNInterpreter_getSessionOutput: Get output failed - Solved

[Tarsyer]

When

score_out_name = [ "cls_pred_stride_8", "cls_pred_stride_16", "cls_pred_stride_32"]

boxes_out_name = [ "dis_pred_stride_8", "dis_pred_stride_16", "dis_pred_stride_32"]

Then below error was occuring

Using MNN as inference backend
Using weight: ../../../nanodet-320.mnn
find 2 images
0%| | 0/2 [00:00<?, ?it/s]Error: can't find output: cls_pred_stride_8
0%| | 0/2 [00:00<?, ?it/s]
Traceback (most recent call last):
File "demo_mnn.py", line 811, in
main()
File "demo_mnn.py", line 797, in main
detector.detect_folder(args.img_fold, args.result_fold)
File "demo_mnn.py", line 655, in detect_folder
bbox, label, score = self.detect(img)
File "demo_mnn.py", line 620, in detect
scores, raw_boxes = self.infer_image(img_input)
File "demo_mnn.py", line 689, in infer_image
scores = [
File "demo_mnn.py", line 690, in
self.interpreter.getSessionOutput(self.session, x).getData()
Exception: PyMNNInterpreter_getSessionOutput: Get output failed

The solution was to give the string number

[meng8407]

When

score_out_name = [ "cls_pred_stride_8", "cls_pred_stride_16", "cls_pred_stride_32"]

boxes_out_name = [ "dis_pred_stride_8", "dis_pred_stride_16", "dis_pred_stride_32"]

Then below error was occuring

Using MNN as inference backend Using weight: ../../../nanodet-320.mnn find 2 images 0%| | 0/2 [00:00<?, ?it/s]Error: can't find output: cls_pred_stride_8 0%| | 0/2 [00:00<?, ?it/s] Traceback (most recent call last): File "demo_mnn.py", line 811, in main() File "demo_mnn.py", line 797, in main detector.detect_folder(args.img_fold, args.result_fold) File "demo_mnn.py", line 655, in detect_folder bbox, label, score = self.detect(img) File "demo_mnn.py", line 620, in detect scores, raw_boxes = self.infer_image(img_input) File "demo_mnn.py", line 689, in infer_image scores = [ File "demo_mnn.py", line 690, in self.interpreter.getSessionOutput(self.session, x).getData() Exception: PyMNNInterpreter_getSessionOutput: Get output failed

The solution was to give the string number

I have the same problem. Has your problem been solved?