ValueError: cannot reshape array of size 324670 into shape (512,256,3,3)

[chrisTopp84]

Hi,
when I'm running python load_weights.py --weights ./weights/yolov3-tiny.weights --output ./weights/yolov3-tiny.tf --tiny
on my Jetson Nano (Jetpack 4.3, tensorflow 2.1.0) an error occurs.

Error:

ValueError: cannot reshape array of size 324670 into shape (512,256,3,3)

Can somebody help me with that?
Best regards an thanks in advance.

Below you will find the complete output after running the python file:

(aiguyyolotest1) christopher@ccz:~/aiguyyolotest1/Object-Detection-API$ python load_weights.py --weights ./weights/yolov3-tiny.weights --output ./weights/yolov3-tiny.tf --tiny
2020-09-18 08:33:58.451661: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.0
2020-09-18 08:34:03.677829: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libnvinfer.so.6
2020-09-18 08:34:03.724180: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libnvinfer_plugin.so.6
2020-09-18 08:34:18.304032: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1
2020-09-18 08:34:18.352799: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:948] ARM64 does not support NUMA - returning NUMA node zero
2020-09-18 08:34:18.353007: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1555] Found device 0 with properties:
pciBusID: 0000:00:00.0 name: NVIDIA Tegra X1 computeCapability: 5.3
coreClock: 0.9216GHz coreCount: 1 deviceMemorySize: 3.87GiB deviceMemoryBandwidth: 23.84GiB/s
2020-09-18 08:34:18.353174: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.0
2020-09-18 08:34:18.353300: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10.0
2020-09-18 08:34:18.435096: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10.0
2020-09-18 08:34:18.543380: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10.0
2020-09-18 08:34:18.661994: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10.0
2020-09-18 08:34:18.731548: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10.0
2020-09-18 08:34:18.732000: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7
2020-09-18 08:34:18.733151: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:948] ARM64 does not support NUMA - returning NUMA node zero
2020-09-18 08:34:18.733627: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:948] ARM64 does not support NUMA - returning NUMA node zero
2020-09-18 08:34:18.733735: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1697] Adding visible gpu devices: 0
2020-09-18 08:34:18.843884: W tensorflow/core/platform/profile_utils/cpu_utils.cc:98] Failed to find bogomips in /proc/cpuinfo; cannot determine CPU frequency
2020-09-18 08:34:18.844908: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x3ce9c5e0 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2020-09-18 08:34:18.844972: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version
2020-09-18 08:34:18.945611: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:948] ARM64 does not support NUMA - returning NUMA node zero
2020-09-18 08:34:18.945924: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x3ce01a20 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
2020-09-18 08:34:18.945975: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA Tegra X1, Compute Capability 5.3
2020-09-18 08:34:18.946674: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:948] ARM64 does not support NUMA - returning NUMA node zero
2020-09-18 08:34:18.946802: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1555] Found device 0 with properties:
pciBusID: 0000:00:00.0 name: NVIDIA Tegra X1 computeCapability: 5.3
coreClock: 0.9216GHz coreCount: 1 deviceMemorySize: 3.87GiB deviceMemoryBandwidth: 23.84GiB/s
2020-09-18 08:34:18.946871: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.0
2020-09-18 08:34:18.946920: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10.0
2020-09-18 08:34:18.947109: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10.0
2020-09-18 08:34:18.947211: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10.0
2020-09-18 08:34:18.947296: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10.0
2020-09-18 08:34:18.947378: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10.0
2020-09-18 08:34:18.947418: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7
2020-09-18 08:34:18.947742: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:948] ARM64 does not support NUMA - returning NUMA node zero
2020-09-18 08:34:18.948078: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:948] ARM64 does not support NUMA - returning NUMA node zero
2020-09-18 08:34:18.948156: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1697] Adding visible gpu devices: 0
2020-09-18 08:34:18.948256: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.0
2020-09-18 08:34:31.465761: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1096] Device interconnect StreamExecutor with strength 1 edge matrix:
2020-09-18 08:34:31.465973: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] 0
2020-09-18 08:34:31.466015: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] 0: N
2020-09-18 08:34:31.482722: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:948] ARM64 does not support NUMA - returning NUMA node zero
2020-09-18 08:34:31.483740: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:948] ARM64 does not support NUMA - returning NUMA node zero
2020-09-18 08:34:31.489128: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1241] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 279 MB memory) -> physical GPU (device: 0, name: NVIDIA Tegra X1, pci bus id: 0000:00:00.0, compute capability: 5.3)
Model: "yolov3_tiny"

---

Layer (type) Output Shape Param # Connected to

input (InputLayer) [(None, None, None, 0

---

yolo_darknet (Model) ((None, None, None, 6298480 input[0][0]

---

yolo_conv_0 (Model) (None, None, None, 2 263168 yolo_darknet[1][1]

---

yolo_conv_1 (Model) (None, None, None, 3 33280 yolo_conv_0[1][0]
yolo_darknet[1][0]

---

yolo_output_0 (Model) (None, None, None, 3 1312511 yolo_conv_0[1][0]

---

yolo_output_1 (Model) (None, None, None, 3 951295 yolo_conv_1[1][0]

---

yolo_boxes_0 (Lambda) ((None, None, None, 0 yolo_output_0[1][0]

---

yolo_boxes_1 (Lambda) ((None, None, None, 0 yolo_output_1[1][0]

---

yolo_nms (Lambda) ((None, 100, 4), (No 0 yolo_boxes_0[0][0]
yolo_boxes_0[0][1]
yolo_boxes_0[0][2]
yolo_boxes_1[0][0]
yolo_boxes_1[0][1]
yolo_boxes_1[0][2]

Total params: 8,858,734
Trainable params: 8,852,366
Non-trainable params: 6,368

---

I0918 08:34:40.257712 547578310672 load_weights.py:19] model created
I0918 08:34:40.266925 547578310672 utils.py:47] yolo_darknet/conv2d bn
I0918 08:34:40.282309 547578310672 utils.py:47] yolo_darknet/conv2d_1 bn
I0918 08:34:40.295813 547578310672 utils.py:47] yolo_darknet/conv2d_2 bn
I0918 08:34:40.312008 547578310672 utils.py:47] yolo_darknet/conv2d_3 bn
I0918 08:34:40.321672 547578310672 utils.py:47] yolo_darknet/conv2d_4 bn
I0918 08:34:40.345241 547578310672 utils.py:47] yolo_darknet/conv2d_5 bn
Traceback (most recent call last):
File "load_weights.py", line 34, in
app.run(main)
File "/usr/local/lib/python3.6/dist-packages/absl/app.py", line 299, in run
_run_main(main, args)
File "/usr/local/lib/python3.6/dist-packages/absl/app.py", line 250, in _run_main
sys.exit(main(argv))
File "load_weights.py", line 21, in main
load_darknet_weights(yolo, FLAGS.weights, FLAGS.tiny)
File "/home/christopher/aiguyyolotest1/Object-Detection-API/yolov3_tf2/utils.py", line 68, in load_darknet_weights
conv_shape).transpose([2, 3, 1, 0])
ValueError: cannot reshape array of size 324670 into shape (512,256,3,3)

[MhdMartini]

Try specifying the number of classes, e.g.:
python load_weights.py --num_classes 4