I am converting my custom model from the onnx format to the hef format. I take the standard code and modify it for my model from https://hailo.ai/developer-zone/documentation/v3-28-0/? sp_referrer=tutorials/tutorials.html
I have an error at the optimization stage
(hailo_env) sensorama@sensorama-ubuntu-pc:~/convert_to_hef$ python optimize_hef.py
2024-10-04 17:13:20.324385: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2024-10-04 17:13:20.808621: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
2024-10-04 17:13:23.547417: I tensorflow/compiler/xla/stream_executor/cuda/cuda_gpu_executor.cc:996] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at linux/Documentation/ABI/testing/sysfs-bus-pci at v6.0 · torvalds/linux · GitHub
2024-10-04 17:13:23.572810: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1956] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at Install TensorFlow with pip for how to download and setup the required libraries for your platform.
Skipping registering GPU devices…
[info] Loading model script commands to best from string
[info] Starting Model Optimization
[warning] Reducing optimization level to 0 (the accuracy won’t be optimized and compression won’t be used) because there’s no available GPU
[warning] Running model optimization with zero level of optimization is not recommended for production use and might lead to suboptimal accuracy results
[info] Model received quantization params from the hn
[info] Starting Mixed Precision
[info] Mixed Precision is done (completion time is 00:00:00.46)
[info] Layer Norm Decomposition skipped
[info] Starting Stats Collector
[info] Using dataset with 64 entries for calibration
Calibration: 0%| | 0/64 [00:00<?, ?entries/s]2024-10-04 17:14:07.933015: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype int32
[[{{node Placeholder/_0}}]]
2024-10-04 17:14:07.957599: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 2%|▉ | 1/64 [00:16<17:16, 16.44s/entries]2024-10-04 17:14:20.594001: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 3%|█▊ | 2/64 [00:16<07:07, 6.89s/entries]2024-10-04 17:14:20.791885: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 5%|██▋ | 3/64 [00:16<03:53, 3.83s/entries]2024-10-04 17:14:20.987680: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 6%|███▋ | 4/64 [00:17<02:23, 2.40s/entries]2024-10-04 17:14:21.180414: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 8%|████▌ | 5/64 [00:17<01:34, 1.60s/entries]2024-10-04 17:14:21.371342: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 9%|█████▍ | 6/64 [00:17<01:05, 1.12s/entries]2024-10-04 17:14:21.562485: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 11%|██████▎ | 7/64 [00:17<00:46, 1.22entries/s]2024-10-04 17:14:21.753194: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 12%|███████▎ | 8/64 [00:17<00:34, 1.61entries/s]2024-10-04 17:14:21.951188: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 14%|████████▏ | 9/64 [00:17<00:26, 2.06entries/s]2024-10-04 17:14:22.142739: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 28%|████████████████ | 18/64 [00:19<00:09, 4.85entries/s]2024-10-04 17:14:24.007097: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 30%|████████████████▉ | 19/64 [00:20<00:09, 4.95entries/s]2024-10-04 17:14:24.199747: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 31%|█████████████████▊ | 20/64 [00:20<00:08, 5.00entries/s]2024-10-04 17:14:24.394780: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 33%|██████████████████▋ | 21/64 [00:20<00:08, 5.01entries/s]2024-10-04 17:14:24.593410: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 34%|███████████████████▌ | 22/64 [00:20<00:08, 5.07entries/s]2024-10-04 17:14:24.785675: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 36%|████████████████████▍ | 23/64 [00:20<00:08, 5.07entries/s]2024-10-04 17:14:24.982576: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 38%|█████████████████████▍ | 24/64 [00:21<00:07, 5.11entries/s]2024-10-04 17:14:25.174911: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 39%|██████████████████████▎ | 25/64 [00:21<00:07, 5.12entries/s]2024-10-04 17:14:25.369701: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 41%|███████████████████████▏ | 26/64 [00:21<00:07, 5.13entries/s]2024-10-04 17:14:25.563129: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 42%|████████████████████████ | 27/64 [00:21<00:07, 5.14entries/s]2024-10-04 17:14:25.758631: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 44%|████████████████████████▉ | 28/64 [00:21<00:07, 5.14entries/s]2024-10-04 17:14:25.952349: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 45%|█████████████████████████▊ | 29/64 [00:21<00:06, 5.14entries/s]2024-10-04 17:14:26.146993: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 47%|██████████████████████████▋ | 30/64 [00:22<00:06, 5.14entries/s]2024-10-04 17:14:26.340307: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 48%|███████████████████████████▌ | 31/64 [00:22<00:06, 5.14entries/s]2024-10-04 17:14:26.534795: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 50%|████████████████████████████▌ | 32/64 [00:22<00:06, 5.12entries/s]2024-10-04 17:14:26.733216: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 52%|█████████████████████████████▍ | 33/64 [00:22<00:06, 5.13entries/s]2024-10-04 17:14:26.928250: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 53%|██████████████████████████████▎ | 34/64 [00:22<00:05, 5.14entries/s]2024-10-04 17:14:27.120400: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 55%|███████████████████████████████▏ | 35/64 [00:23<00:05, 5.14entries/s]2024-10-04 17:14:27.315296: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 56%|████████████████████████████████ | 36/64 [00:23<00:05, 5.15entries/s]2024-10-04 17:14:27.507418: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 58%|████████████████████████████████▉ | 37/64 [00:23<00:05, 5.14entries/s]2024-10-04 17:14:27.703821: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 59%|█████████████████████████████████▊ | 38/64 [00:23<00:05, 5.14entries/s]2024-10-04 17:14:27.897470: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 61%|██████████████████████████████████▋ | 39/64 [00:23<00:04, 5.14entries/s]2024-10-04 17:14:28.092880: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 62%|███████████████████████████████████▋ | 40/64 [00:24<00:04, 5.15entries/s]2024-10-04 17:14:28.285805: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 64%|████████████████████████████████████▌ | 41/64 [00:24<00:04, 5.15entries/s]2024-10-04 17:14:28.480739: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 66%|█████████████████████████████████████▍ | 42/64 [00:24<00:04, 5.16entries/s]2024-10-04 17:14:28.673279: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 67%|██████████████████████████████████████▎ | 43/64 [00:24<00:04, 5.16entries/s]2024-10-04 17:14:28.867445: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 69%|███████████████████████████████████████▏ | 44/64 [00:25<00:04, 4.33entries/s]2024-10-04 17:14:29.184579: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 70%|████████████████████████████████████████ | 45/64 [00:25<00:04, 3.90entries/s]2024-10-04 17:14:29.499700: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 72%|████████████████████████████████████████▉ | 46/64 [00:25<00:04, 4.21entries/s]2024-10-04 17:14:29.694108: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 73%|█████████████████████████████████████████▊ | 47/64 [00:25<00:03, 4.47entries/s]2024-10-04 17:14:29.885868: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 75%|██████████████████████████████████████████▊ | 48/64 [00:25<00:03, 4.65entries/s]2024-10-04 17:14:30.080285: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 77%|███████████████████████████████████████████▋ | 49/64 [00:26<00:03, 4.80entries/s]2024-10-04 17:14:30.273154: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 78%|████████████████████████████████████████████▌ | 50/64 [00:26<00:02, 4.91entries/s]2024-10-04 17:14:30.465107: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 80%|█████████████████████████████████████████████▍ | 51/64 [00:26<00:02, 4.99entries/s]2024-10-04 17:14:30.658670: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 81%|██████████████████████████████████████████████▎ | 52/64 [00:26<00:02, 4.26entries/s]2024-10-04 17:14:30.973127: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 83%|███████████████████████████████████████████████▏ | 53/64 [00:27<00:02, 4.52entries/s]2024-10-04 17:14:31.162487: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 84%|████████████████████████████████████████████████ | 54/64 [00:27<00:02, 4.71entries/s]2024-10-04 17:14:31.354724: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 86%|████████████████████████████████████████████████▉ | 55/64 [00:27<00:01, 4.82entries/s]2024-10-04 17:14:31.552346: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 88%|█████████████████████████████████████████████████▉ | 56/64 [00:27<00:01, 4.86entries/s]2024-10-04 17:14:31.753005: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 89%|██████████████████████████████████████████████████▊ | 57/64 [00:27<00:01, 4.20entries/s]2024-10-04 17:14:32.068157: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 91%|███████████████████████████████████████████████████▋ | 58/64 [00:28<00:01, 4.42entries/s]2024-10-04 17:14:32.267160: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 92%|████████████████████████████████████████████████████▌ | 59/64 [00:28<00:01, 4.61entries/s]2024-10-04 17:14:32.461151: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 94%|█████████████████████████████████████████████████████▍ | 60/64 [00:28<00:00, 4.75entries/s]2024-10-04 17:14:32.656302: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 95%|██████████████████████████████████████████████████████▎ | 61/64 [00:28<00:00, 4.88entries/s]2024-10-04 17:14:32.848457: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 97%|███████████████████████████████████████████████████████▏ | 62/64 [00:28<00:00, 4.97entries/s]2024-10-04 17:14:33.040694: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 98%|████████████████████████████████████████████████████████ | 63/64 [00:29<00:00, 5.05entries/s]2024-10-04 17:14:33.231540: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor ‘Placeholder/_0’ with dtype float and shape [1,640,640,3]
[[{{node Placeholder/_0}}]]
Calibration: 100%|█████████████████████████████████████████████████████████| 64/64 [00:29<00:00, 2.19entries/s]
[info] Stats Collector is done (completion time is 00:00:30.69)
[info] Starting Fix zp_comp Encoding
[info] Fix zp_comp Encoding is done (completion time is 00:00:00.00)
[info] matmul_equalization skipped
[info] Finetune encoding skipped
[info] Bias Correction skipped
[info] Adaround skipped
[info] Fine Tune skipped
[info] Layer Noise Analysis skipped
Traceback (most recent call last):
File “optimize_hef.py”, line 58, in
runner.optimize(calib_dataset)
File “/home/sensorama/hailo_env/lib/python3.8/site-packages/hailo_sdk_common/states/states.py”, line 16, in wrapped_func
return func(self, *args, **kwargs)
File “/home/sensorama/hailo_env/lib/python3.8/site-packages/hailo_sdk_client/runner/client_runner.py”, line 2093, in optimize
self._optimize(calib_data, data_type=data_type, work_dir=work_dir)
File “/home/sensorama/hailo_env/lib/python3.8/site-packages/hailo_sdk_common/states/states.py”, line 16, in wrapped_func
return func(self, *args, **kwargs)
File “/home/sensorama/hailo_env/lib/python3.8/site-packages/hailo_sdk_client/runner/client_runner.py”, line 1935, in _optimize
self._sdk_backend.full_quantization(calib_data, data_type=data_type, work_dir=work_dir)
File “/home/sensorama/hailo_env/lib/python3.8/site-packages/hailo_sdk_client/sdk_backend/sdk_backend.py”, line 1045, in full_quantization
self._full_acceleras_run(self.calibration_data, data_type)
File “/home/sensorama/hailo_env/lib/python3.8/site-packages/hailo_sdk_client/sdk_backend/sdk_backend.py”, line 1239, in _full_acceleras_run
self._model = HailoNN.from_hn(json.dumps(hn))
File “/home/sensorama/hailo_env/lib/python3.8/site-packages/hailo_sdk_common/hailo_nn/hailo_nn.py”, line 1594, in from_hn
return HNImporter().from_hn(hn_json)
File “/home/sensorama/hailo_env/lib/python3.8/site-packages/hailo_sdk_common/hailo_nn/hailo_nn.py”, line 1847, in from_hn
return self.from_parsed_hn(json.loads(ensure_str(hn_json)))
File “/home/sensorama/hailo_env/lib/python3.8/site-packages/hailo_sdk_common/hailo_nn/hailo_nn.py”, line 1835, in from_parsed_hn
self._hailo_nn.calculate_shapes()
File “/home/sensorama/hailo_env/lib/python3.8/site-packages/hailo_sdk_common/hailo_nn/hailo_nn.py”, line 755, in calculate_shapes
layer.update_output_shapes(hn_stage=self.net_params.stage, validate_shapes=validate_shapes)
File “/home/sensorama/hailo_env/lib/python3.8/site-packages/hailo_sdk_common/hailo_nn/hn_layers/feature_splitter.py”, line 117, in update_output_shapes
raise UnsupportedModelError(
hailo_sdk_common.hailo_nn.exceptions.UnsupportedModelError: Unexpected split shapes at feature splitter layer best/feature_splitter9 (translated from /model.22/Split), output_shapes=[[-1, 1, 8400, 64]], input_shapes=[[-1, 1, 8400, 66]])