Closed mikel-brostrom closed 1 year ago
Knowing that TI's model is rather verbose, I optimized it independently and created a script to replace all ScatterND
with Slice
.
https://github.com/PINTO0309/PINTO_model_zoo/tree/main/363_YOLO-6D-Pose
Thank you for your quick response
I will be home with my parents today, tomorrow, and the day after, so I will not be able to provide detailed testing or assistance.
Thanks for the heads up! Testing this on my own on a detection model, not on pose. Let's see if I manage to get it working. The eval result on both models is as follows:
YOLOX nano ONNX | YOLOX-Ti nano ONNX | |
---|---|---|
mAP@0.5:0.95 | 0.256 | 0.261 |
mAP@0.5 | 0.411 | 0.418 |
Ok. As I didn't see ScatterND in the original model, I checked what the differences where. I found out that this
def meshgrid(*tensors):
if _TORCH_VER >= [1, 10]:
return torch.meshgrid(*tensors, indexing="ij")
else:
return torch.meshgrid(*tensors)
def decode_outputs(self, outputs, dtype):
grids = []
strides = []
for (hsize, wsize), stride in zip(self.hw, self.strides):
yv, xv = meshgrid([torch.arange(hsize), torch.arange(wsize)])
grid = torch.stack((xv, yv), 2).view(1, -1, 2)
grids.append(grid)
shape = grid.shape[:2]
strides.append(torch.full((*shape, 1), stride))
grids = torch.cat(grids, dim=1).type(dtype)
strides = torch.cat(strides, dim=1).type(dtype)
outputs = torch.cat([
(outputs[..., 0:2] + grids) * strides,
torch.exp(outputs[..., 2:4]) * strides,
outputs[..., 4:]
], dim=-1)
return outputs
gives:
While this:
def (self, outputs, dtype):
grids = []
strides = []
for (hsize, wsize), stride in zip(self.hw, self.strides):
yv, xv = torch.meshgrid([torch.arange(hsize), torch.arange(wsize)])
grid = torch.stack((xv, yv), 2).view(1, -1, 2)
grids.append(grid)
shape = grid.shape[:2]
strides.append(torch.full((*shape, 1), stride))
grids = torch.cat(grids, dim=1).type(dtype)
strides = torch.cat(strides, dim=1).type(dtype)
outputs[..., :2] = (outputs[..., :2] + grids) * strides
outputs[..., 2:4] = torch.exp(outputs[..., 2:4]) * strides
return outputs
gives:
This as well as some other minor fixes make it possible to get rid of ScatterND completely.
Excellent.
Perhaps the overall size of the model should be significantly smaller. 64-bit index values are almost always overly precise. However, since the computational efficiency of Gather
and Scatter
is supposed to be high to begin with, I am concerned about how much the inference performance will deteriorate after the change to Slice
.
The model performance did not decrease after the changes and for the first time I got results on one of the quantized models (dynamic_range_quant
).
Model | size | mAPval 0.5:0.95 |
mAPval 0.5 |
size |
---|---|---|---|---|
YOLOX-TI-nano ONNX (original model) | 416 | 0.261 | 0.418 | 8.7M |
YOLOX-TI-nano ONNX (no ScatterND) | 416 | 0.261 | 0.418 | 8.7M |
YOLOX-nano TFLite FP16 | 416 | 0.261 | 0.418 | 4.4M |
YOLOX-nano TFLite FP32 | 416 | 0.261 | 0.418 | 8.7M |
YOLOX-nano TFLite full_integer_quant | 416 | 0 | 0 | 2.3M |
YOLOX-nano TFLite dynamic_range_quant | 416 | 0.249 | 0.410 | 2.3M |
YOLOX-nano TFLite integer_quant | 416 | 0 | 0 | 2.3M |
But still nothing for the INT
ones though...
I can't see the structure of the model today, but I believe there were a couple of Sigmoid
at the beginning of the post-processing.
What if the model transformation is stopped just before post-processing? However, it is difficult to measure mAP.
e.g.
onnx2tf -i resnet18-v1-7.onnx \
-onimc resnetv15_stage2_conv1_fwd resnetv15_stage2_conv2_fwd
It's an interesting topic and I'd like to try it myself, but I can't easily try it right now.
You are right @PINTO0309 . I missed this:
output = torch.cat(
[reg_output, obj_output.sigmoid(), cls_output.sigmoid()], 1
)
which in the ONNX model is represented as:
then in the TFLite models these Sigmoid
converts into Logistic
:
But why is the dynamic range quantized model working and not the rest of the quantized models?
If I remember correctly, dynamic range is less prone to accuracy degradation because it recalculates the quantization range each time; compared to INT8 full quantization, the inference speed would have been very slow in exchange for maintaining accuracy.
I may be wrong because I do not have an accurate grasp of recent quantization specifications.
By the way,
Sigmoid
= Logistic
Maybe a bit out of topic. Anyways, I am using the official TFLite benchmark tool for the exported models and on the specific android device i I am running this on I get that the Float32 models is much faster that the dynamically quantized one.
People are getting the same quantization problems with YOLOv8 https://github.com/ultralytics/ultralytics/pull/1447:
full_integer_quant
and integer_quant
does not work. dynamic_range_quant
works but it is very slow
But then I guess that the only option we have is to perform the sigmoid
operation outside the model...
@mikel-brostrom As for the accuracy degradation of YOLOX integer quantization, I think it may be due to the distribution mismatch of xywh and score values.
Just before the last Concat, xywh seems to have a distribution of (min, max)~(0.0, 416.0). On the other hand, scores have a much narrower distribution of (min, max) = (0.0, 1.0) because of sigmoid.
In TFLite quantization, activation is quantized in per-tensor manner. That is, the OR distribution of xywh and scores, (min, max) = (0.0, 416.0), is mapped to integer values of (min, max) = (0, 255) after the Concat. As a result, even if the score is 1.0, after quantization it is mapped to: int(1.0 / 416 * 255) = int(0.61) = 0, resulting in all scores being zero!
A possible solution is to divide xywh tensors by the image size (416) to keep it in the range (min, max) ~ (0.0, 1.0) and then concat with the score tensor so that scores are not "collapsed" due to the per-tensor quantization.
The same workaround is done in YOLOv5: https://github.com/ultralytics/yolov5/blob/b96f35ce75effc96f1a20efddd836fa17501b4f5/models/tf.py#L307-L310
This was super helpful @motokimura! Will try this out
I hope this helps.. When you try this workaround, do not forget to multiply xywh tensors by 416 in the prediction phase!
Get it!
No change on the INT8 models @motokimura after implementing what you suggested... Still the same results for all the TFLite models, so the problem may primarily be in an operation or set of operations
hmm.. As PINTO pointed out, it may be better to compare int8 and float model activations before the decoder part.
https://github.com/PINTO0309/onnx2tf/issues/269#issuecomment-1482738822
It may be helpful to export onnx without '--export-det' option and compare the int8 and float outputs.
Anyways, I am using the official TFLite benchmark tool for the exported models and on the specific android device i I am running this on I get that the Float32 models is much faster that the dynamically quantized one.
First, let me tell you that your results will vary greatly depending on the architecture of the CPU you are using for your verification. If you are using an Intel x64(x86) or AMD x64(x86) architecture CPU, the Float32 model should be able to reason about 10 times faster than the INT8 model. INT8 models are very slow on the x64 architecture. Perhaps the RaspberryPi's ARM64 CPU 4 threads would be 10 times faster. The keyword XNNPACK is a good way to search for information. In the case of Intel's x64 architecture, CPUs of the 10th generation or later differ from CPUs of the 9th generation or earlier in the presence or absence of an optimization mechanism for processing Integer. If you are using a 10th generation or later CPU, it should run about 20% faster.
Therefore, when benchmarking using benchmarking tools, it is recommended to try to do so on ARM64 devices.
The benchmarking in the discussion on the ultralytics thread is not appropriate.
Next, let's look at dynamic range quantization.
My tool does per-channel
quantization by default. This is due to the TFLiteConverter specification. per-channel
quantization calculates the quantization range for each element of the tensor, which reduces the accuracy degradation and, at the same time, increases the cost of calculating the quantization range, which slows down the inference a little. Also, most of the current edge devices in the world are not optimized for per-channel
quantization. For example, EdgeTPU only supports per-tensor
quantization. Therefore, if quantization is to be performed with the assumption that the model will be put to practical use in the future, it is recommended that per-tensor
quantization be performed during the transformation as follows.
onnx2tf -i xxxx.onnx -oiqt -qt per-tensor
per-channel
quant
per-tensor
quant
Next, we discuss post-quantization accuracy degradation. I think motoki's point is mostly correct. I think you should first try to split the model at the red line and see how the accuracy changes.
If the Sigmoid
in this position does not affect the accuracy, it should work. It is better to think about complex problems by breaking them down into smaller problems without being too hasty.
I just cut the model at the point you suggested by:
onnx2tf -i /datadrive/mikel/yolox_tflite_export/yolox_nano.onnx -b 1 -cotof -cotoa 1e-1 -onimc /head/Concat_6_output_0
But I get the following error:
File "/datadrive/mikel/yolox_tflite_export/env/lib/python3.8/site-packages/onnx2tf/utils/common_functions.py", line 3071, in onnx_tf_tensor_validation
onnx_tensor_shape = onnx_tensor.shape
AttributeError: 'NoneType' object has no attribute 'shape'
I couldn't find a similar issue and I had the same problem when I tried to cut YOLOX in our previous discussion. I probably misinterpreted how the tool is supposed to be used...
First, let me tell you that your results will vary greatly depending on the architecture of the CPU you are using for your verification. If you are using an Intel x64(x86) or AMD x64(x86) architecture CPU, the Float32 model should be able to reason about 10 times faster than the INT8 model. INT8 models are very slow on the x64 architecture. Perhaps the RaspberryPi's ARM64 CPU 4 threads would be 10 times faster. The keyword XNNPACK is a good way to search for information. In the case of Intel's x64 architecture, CPUs of the 10th generation or later differ from CPUs of the 9th generation or earlier in the presence or absence of an optimization mechanism for processing Integer. If you are using a 10th generation or later CPU, it should run about 20% faster.
Therefore, when benchmarking using benchmarking tools, it is recommended to try to do so on ARM64 devices.
I compiled the benchmark binary for android_arm64. The device has a Exynos9810 which is arm 64-bit. It contains a Mali-G72MP18 GPU. However, I am running the model without GPU accelerators, so the INT8 model must be running on CPU. The CPU got released 2018 so that may explain why the quantized model is that slow...
But I get the following error:
I came home and tried the same conversion as you.
The following command did not generate an error. It is a little strange that the situation is different in your environment and mine. Since scatternd
requires a very complex modification at the moment, would the same error occur in ONNX with scatternd
replaced with slice
?
onnx2tf -i yolox_nano_no_scatternd.onnx -cotof -cotoa 1e-4 -onimc /head/Concat_6_output_0
INFO: onnx_output_name: /head/stems.2/act/Relu_output_0 tf_output_name: tf.nn.relu_70/Relu:0 shape: (1, 64, 13, 13) dtype: float32 validate_result: Matches
INFO: onnx_output_name: /head/cls_convs.2/cls_convs.2.0/conv/Conv_output_0 tf_output_name: tf.math.add_84/Add:0 shape: (1, 64, 13, 13) dtype: float32 validate_result: Matches
INFO: onnx_output_name: /head/reg_convs.2/reg_convs.2.0/conv/Conv_output_0 tf_output_name: tf.math.add_85/Add:0 shape: (1, 64, 13, 13) dtype: float32 validate_result: Matches
INFO: onnx_output_name: /head/cls_convs.2/cls_convs.2.0/act/Relu_output_0 tf_output_name: tf.nn.relu_71/Relu:0 shape: (1, 64, 13, 13) dtype: float32 validate_result: Matches
INFO: onnx_output_name: /head/reg_convs.2/reg_convs.2.0/act/Relu_output_0 tf_output_name: tf.nn.relu_72/Relu:0 shape: (1, 64, 13, 13) dtype: float32 validate_result: Matches
INFO: onnx_output_name: /head/cls_convs.2/cls_convs.2.1/conv/Conv_output_0 tf_output_name: tf.math.add_86/Add:0 shape: (1, 64, 13, 13) dtype: float32 validate_result: Matches
INFO: onnx_output_name: /head/reg_convs.2/reg_convs.2.1/conv/Conv_output_0 tf_output_name: tf.math.add_87/Add:0 shape: (1, 64, 13, 13) dtype: float32 validate_result: Matches
INFO: onnx_output_name: /head/cls_convs.2/cls_convs.2.1/act/Relu_output_0 tf_output_name: tf.nn.relu_73/Relu:0 shape: (1, 64, 13, 13) dtype: float32 validate_result: Matches
INFO: onnx_output_name: /head/reg_convs.2/reg_convs.2.1/act/Relu_output_0 tf_output_name: tf.nn.relu_74/Relu:0 shape: (1, 64, 13, 13) dtype: float32 validate_result: Matches
INFO: onnx_output_name: /head/cls_preds.2/Conv_output_0 tf_output_name: tf.math.add_88/Add:0 shape: (1, 80, 13, 13) dtype: float32 validate_result: Matches
INFO: onnx_output_name: /head/reg_preds.2/Conv_output_0 tf_output_name: tf.math.add_89/Add:0 shape: (1, 4, 13, 13) dtype: float32 validate_result: Matches
INFO: onnx_output_name: /head/obj_preds.2/Conv_output_0 tf_output_name: tf.math.add_90/Add:0 shape: (1, 1, 13, 13) dtype: float32 validate_result: Matches
INFO: onnx_output_name: /head/Sigmoid_4_output_0 tf_output_name: tf.math.sigmoid_4/Sigmoid:0 shape: (1, 1, 13, 13) dtype: float32 validate_result: Matches
INFO: onnx_output_name: /head/Sigmoid_5_output_0 tf_output_name: tf.math.sigmoid_5/Sigmoid:0 shape: (1, 80, 13, 13) dtype: float32 validate_result: Matches
INFO: onnx_output_name: /head/Concat_2_output_0 tf_output_name: tf.concat_15/concat:0 shape: (1, 85, 13, 13) dtype: float32 validate_result: Matches
INFO: onnx_output_name: /head/Reshape_2_output_0 tf_output_name: tf.reshape_2/Reshape:0 shape: (1, 85, 169) dtype: float32 validate_result: Matches
INFO: onnx_output_name: /head/Concat_6_output_0 tf_output_name: tf.concat_16/concat:0 shape: (1, 85, 3549) dtype: float32 validate_result: Matches
onnx2tf -i yolox_nano_no_scatternd.onnx -oiqt -cotof -cotoa 1e-4 -onimc /head/Concat_6_output_0
I compiled the benchmark binary for android_arm64. The device has a Exynos9810 which is arm 64-bit. It contains a Mali-G72MP18 GPU. However, I am running the model without GPU accelerators, so the INT8 model must be running on CPU. The CPU got released 2018 so that may explain why the quantized model is that slow...
Cortex-A55 may be a bit old architecture. I am not very familiar with the details of the CPU architecture, but I think Coretex-A7x may have faster inference because of the implementation of faster operations with Neon instructions. Performance seems to vary considerably depending on whether Arm NN can be called from TFLite.
Here is a video of me running an INT8 quantized SSD on a RaspberryPi4 CPU (Debian 64bit) alone in 2020. https://www.youtube.com/watch?v=bd3lTBAYIq4
RaspberryPi4 (CPU only) + Python3.7 + Tensorflow Lite + MobileNetV2-SSDLite + Sync + MP4 640x360
15FPS (about 66ms/pred)
Sorry, I have no idea what I did wrong last time, when I run:
onnx2tf -i yolox_nano_no_scatternd.onnx -cotof -cotoa 1e-4 -onimc /head/Concat_6_output_0
But you are right @PINTO0309, everything looks alright up to that operation:
ONNX and TF output value validation started =========================================
...
INFO: onnx_output_name: /head/Sigmoid_4_output_0 tf_output_name: tf.math.sigmoid_4/Sigmoid:0 shape: (1, 1, 13, 13) dtype: float32 validate_result: Matches
INFO: onnx_output_name: /head/Sigmoid_5_output_0 tf_output_name: tf.math.sigmoid_5/Sigmoid:0 shape: (1, 80, 13, 13) dtype: float32 validate_result: Matches
INFO: onnx_output_name: /head/Concat_2_output_0 tf_output_name: tf.concat_15/concat:0 shape: (1, 85, 13, 13) dtype: float32 validate_result: Matches
INFO: onnx_output_name: /head/Reshape_2_output_0 tf_output_name: tf.reshape_2/Reshape:0 shape: (1, 85, 169) dtype: float32 validate_result: Matches
INFO: onnx_output_name: /head/Concat_6_output_0 tf_output_name: tf.concat_16/concat:0 shape: (1, 85, 3549) dtype: float32 validate_result: Matches
What seems to differ are the output of the Multiply head operations for some reason. Not sure if these error are large enough for breaking the model completely? But given that I tried @motokimura's suggestion and it didn't work, I guess so...
INFO: onnx_output_name: /head/Mul_output_0 tf_output_name: tf.math.multiply_9/Mul:0 shape: (1, 3549, 2) dtype: float32 validate_result: Unmatched max_abs_error: 0.000156402587890625
INFO: onnx_output_name: /head/Mul_1_output_0 tf_output_name: tf.math.multiply_11/Mul:0 shape: (1, 3549, 2) dtype: float32 validate_result: Unmatched max_abs_error: 0.000579833984375
INFO: onnx_output_name: /head/Div_output_0 tf_output_name: tf.math.divide/truediv:0 shape: (1, 3549, 2) dtype: float32 validate_result: Matches
INFO: onnx_output_name: /head/Div_1_output_0 tf_output_name: tf.math.divide_1/truediv:0 shape: (1, 3549, 2) dtype: float32 validate_result: Matches
INFO: onnx_output_name: output tf_output_name: tf.concat_17/concat:0 shape: (1, 3549, 85) dtype: float32 validate_result: Matches
I compiled the benchmark binary for android_arm64. The device has a Exynos9810 which is arm 64-bit. It contains a Mali-G72MP18 GPU. However, I am running the model without GPU accelerators, so the INT8 model must be running on CPU. The CPU got released 2018 so that may explain why the quantized model is that slow...
Cortex-A55 may be a bit old architecture. I am not very familiar with the details of the CPU architecture, but I think Coretex-A7x may have faster inference because of the implementation of faster operations with Neon instructions. Performance seems to vary considerably depending on whether Arm NN can be called from TFLite.
Apparently the benchmark binary can be run with nnapi delegate by --use_nnapi=true
and with GPU delegate by --use_gpu=true
(source). This will give a better understanding of how this model actually performs with hardware accelerators. If anybody is interested I can upload those results as well :smile:
I am very interested. Probably other engineers besides myself as well.
Today and tomorrow will involve travel to distant places for work, which will slow down research and work.
Incidentally, Motoki seems to have succeeded in maintaining accuracy with INT8 quantization.
I'm going to share how I quantized the nano model tonight. I’ve not yet done qualitative evaluation of the quantized model, but the detection result looks OK.
@mikel-brostrom This repository explains how I quantized the nano model. I hope you find this helpful! https://github.com/motokimura/yolox-ti-lite_tflite
Note that my model doesn’t include post-process (ONNX model was exported without --export-det
).
I compared the inference results from yolox_nano_ti_lite_integer_quant.tflite
and ONNX models for some sample images, and confirmed the errors are acceptably small.
@mikel-brostrom As for the accuracy degradation of your static quantized int8 model, I'm concerned your calibration setting might not be correct.
In calibration, representative images called calibration data is input to the model in order to observe the activation value range of each layer. Based on the observed activation range, the quantization parameters (scale and offset) which are used to map fp32 activations into int8 are computed for each layer (all of these were done in onnx2tf). So, if the calibration data is not correct, these quantization parameters are not computed properly, resulting catastrophic accuracy degradation of the quantized model.
Since YOLOX models expects unnormalized pixel values from 0 to 255 as the input, I generated calibration data from COCO train images without normalization [code link]. Then, I passed it to onnx2tf with -qcind
option without normalization as written in README:
onnx2tf -i yolox_nano_ti_lite.onnx -oiqt -qcind images calib_data_416x416_n200.npy "[[[[0,0,0]]]]" "[[[[1,1,1]]]]"
Did you pass calibration data to onnx2tf like I did?
If -qcind
is not specified, onnx2tf seems to use sample calibration data as described here. This sample calibration data seems to be normalized so that the pixel values are from 0 to 1 as written here and to be further normalized ImageNet mean and std. As YOLOX models do not expect such normalized pixel values, this causes the problem in the calibration.
Btw, the reason why dynamic int8 calibration worked is because the dynamic quantization does not use any calibration data; the quantization parameters are adjusted for each input dynamically (so it’s called dynamic quantization in contrast to static quantization) as PINTO explained above:
If I remember correctly, dynamic range is less prone to accuracy degradation because it recalculates the quantization range each time; compared to INT8 full quantization, the inference speed would have been very slow in exchange for maintaining accuracy.
Sorry for my late reply. I spent most of the day creating the benchmark result plot for yolox on the specific hardware I am using. I added delegate results as well. hexagon
is skipped as the target device has no qualcomm chip. INT8 models don't get a boost on this chip due to the lack of an INT8 ISA. GPU boosts make sense as the EXYNOS9810 contains a Mali-G72MP18 GPU, but inference speed is quite similar to using XNNPACK with 4 threads.
Any idea why the memory footprint for the GPU delegate is so big compared to the others? Specially for the quantized one?
Exynos 9810 (ARM Mali-G72MP18 GPU). Released: March 01, 2018
Exynos 7870 (ARM Mali-T830 MP2 GPU). Released: February 17, 2016
@mikel-brostrom As for the accuracy degradation of your static quantized int8 model, I'm concerned your calibration setting might not be correct.
In calibration, representative images called calibration data is input to the model in order to observe the activation value range of each layer. Based on the observed activation range, the quantization parameters (scale and offset) which are used to map fp32 activations into int8 are computed for each layer (all of these were done in onnx2tf). So, if the calibration data is not correct, these quantization parameters are not computed properly, resulting catastrophic accuracy degradation of the quantized model.
Since YOLOX models expects unnormalized pixel values from 0 to 255 as the input, I generated calibration data from COCO train images without normalization [code link]. Then, I passed it to onnx2tf with
-qcind
option without normalization as written in README:onnx2tf -i yolox_nano_ti_lite.onnx -oiqt -qcind images calib_data_416x416_n200.npy "[[[[0,0,0]]]]" "[[[[1,1,1]]]]"
Did you pass calibration data to onnx2tf like I did? If
-qcind
is not specified, onnx2tf seems to use sample calibration data as described here. This sample calibration data seems to be normalized so that the pixel values are from 0 to 1 as written here and to be further normalized ImageNet mean and std. As YOLOX models do not expect such normalized pixel values, this causes the problem in the calibration.
I won't have time to check this out today @motokimura. But will report back tomorrow with my findings :smile:. Thanks again for your time and guidance
I tried a complete model export (including --export-det
) following @motokimura's instructions. I am aware of the fact that the post-processing step induces large errors on INT quantized models as showed here: https://github.com/PINTO0309/onnx2tf/issues/269#issuecomment-1484182307. Despite of all this I decided to proceed to check what performance I would get, as I want to do as little post-processing outside of the model as possible. These are my results:
Model | size | mAPval 0.5:0.95 |
mAPval 0.5 |
size | xywh output | calibration images |
---|---|---|---|---|---|---|
YOLOX-TI-nano ONNX (original model) | 416 | 0.261 | 0.418 | 8.7M | [0, 416] | N/A |
YOLOX-TI-nano ONNX (no ScatterND) | 416 | 0.261 | 0.418 | 8.7M | [0, 416] | N/A |
YOLOX-nano TFLite FP32 | 416 | 0.261 | 0.418 | 8.7M | [0, 416] | N/A |
YOLOX-nano TFLite FP16 | 416 | 0.261 | 0.418 | 4.4M | [0, 416] | N/A |
YOLOX-nano TFLite full_integer_quant | 416 | 0 | 0 | 2.4M | [0, 1] | 0 |
YOLOX-nano TFLite full_integer_quant | 416 | 0.039 | 0.115 | 2.4M | [0, 1] | 200 |
YOLOX-nano TFLite full_integer_quant | 416 | 0.033 | 0.098 | 2.4M | [0, 1] | 600 |
YOLOX-nano TFLite dynamic_range_quant | 416 | 0.259 | 0.416 | 2.4M | [0, 1] | 200 |
YOLOX-nano TFLite dynamic_range_quant | 416 | 0.259 | 0.416 | 2.4M | [0, 1] | 600 |
YOLOX-nano TFLite integer_quant | 416 | 0.039 | 0.115 | 2.4M | [0, 1] | 200 |
YOLOX-nano TFLite integer_quant | 416 | 0.033 | 0.098 | 2.4M | [0, 1] | 600 |
YOLOX-nano TFLite integer_quant | 416 | 0 | 0 | 2.4M | [0, 416] | 200 |
Sorry for all the experiment results I am dropping here. I hope they can help somebody going through a similar kind of processes. Without the --export-det
I get the same results as @motokimura :smile:
Why would a multiplication operation be problematic when INT quantizing? https://github.com/PINTO0309/onnx2tf/issues/269#issuecomment-1484182307
Errors of less than 1e-3 hardly make any difference to the accuracy of the model. Errors introduced by Mul can be caused by slight differences in fraction handling between ONNX and TensorFlow. Ignoring it will only cause a difference that is not noticeable to the human eye.
Then something else must be wrong in what I am doing... Will double check tomorrow
I explained it in a very simplified manner because it would be very complicated to explain in detail. You need to understand how onnx2tf checks the final and intermediate outputs.
Once you understand the principles of the accuracy checker, you will realize that minor errors can always occur, even if the model transformation is perfectly normal.
Matches
.
INFO: onnx_output_name: output tf_output_name: tf.concat_17/concat:0 shape: (1, 3549, 85) dtype: float32 validate_result: Matches
Unmached
appears is the result of the precision check in Float32, regardless of whether it was quantized to INT8 or not.However, I am very concerned about the zero mAP in the last benchmark result. :eyes:
Errors below 1e-4 can occur in almost any model due to differences in rounding, truncation, and rounding up criteria between ONNX's internal processing and TensorFlow's internal processing.
Get it!
Also, this tool does not have the ability to check INT8 accuracy, only Float32 accuracy. Therefore, it should be noted that whether or not Unmached appears is the result of the precision check in Float32, regardless of whether it was quantized to INT8 or not.
Good to know :smile:
However, I am very concerned about the zero mAP in the last benchmark result. eyes
Will double check everything tomorrow just to make sure there are no errors on my side
A workaround has been implemented to avoid ScatterND
shape mismatch errors as much as possible. In v1.8.3, the conversion succeeds as is even if ScatterND
is included, and the accuracy check has been improved to no problem.
However, since NMS is included in the post-processing, accuracy verification with random data does not display very good results. For an accurate accuracy check, it is better to use a still image of the assumption used in the inference. This is because accuracy checks using random data may result in zero final output data counts.
https://github.com/PINTO0309/onnx2tf/releases/tag/1.8.3
onnx2tf -i xxx.onnx
In any case, ScatterND
converts to a very verbose OP, so it is still better to create a model that replaces it with Slice
as much as possible.
In any case, ScatterND converts to a very verbose OP, so it is still better to create a model that replaces it with Slice as much as possible.
I may try this out later today :smile:
Also, this tool does not have the ability to check INT8 accuracy, only Float32 accuracy. Therefore, it should be noted that whether or not Unmached appears is the result of the precision check in Float32, regardless of whether it was quantized to INT8 or not.
I guess I have no option more than to wait for https://github.com/PINTO0309/onnx2tf/issues/258 to get a better understanding if in the INT8 model is the problem at all. The only difference between @motokimura's INT8 model and mine is:
In the model, just before the output, I do:
if self.int8:
xy = torch.div(xy, 416)
wh = torch.div(wh, 416)
outputs = torch.cat([xy, wh, outputs[..., 4:]], dim=-1)
My inference look like this:
im_batch = im_batch.cpu().numpy()
input = self.input_details[0]
int8 = (input['dtype'] == np.int8 or input['dtype'] == np.uint8) # is TFLite quantized uint8 model
if int8:
print('True')
scale, zero_point = input['quantization']
im_batch = (im_batch / scale + zero_point).astype(np.int8) # de-scale
self.interpreter.set_tensor(input['index'], im_batch)
self.interpreter.invoke()
y = []
for output in self.output_details:
x = self.interpreter.get_tensor(output['index'])
if int8:
scale, zero_point = output['quantization']
x = ((x.astype(np.float32) - zero_point) * scale) # re-scale
x[0:4] = x[0:4] * 416 # notice xywh in the model is divided by 416
y.append(x) # de-normalize output
Some eval results on first 8 COCO images, just to speed up the comparison process
Model | size | mAPval 0.5:0.95 |
mAPval 0.5 |
size | xywh model output | calibration images |
---|---|---|---|---|---|---|
YOLOX-TI-nano TFLite FP32 | 416 | 0.390 | 0.653 | 8.7M | [0, 1] | N/A |
YOLOX-TI-nano TFLite FP16 | 416 | 0.390 | 0.653 | 4.4M | [0, 1] | N/A |
YOLOX-TI-nano TFLite full_integer_quant | 416 | 0.135 | 0.356 | 2.4M | [0, 1] | 200 |
YOLOX-TI-nano TFLite full_integer_quant_with_int16_act | 416 | 0 | 0 | 2.4M | [0, 1] | 200 |
YOLOX-TI-nano TFLite dynamic_range_quant | 416 | 0.389 | 0.652 | 2.4M | [0, 1] | 200 |
YOLOX-TI-nano TFLite integer_quant | 416 | 0.135 | 0.356 | 2.4M | [0, 1] | 200 |
YOLOX-TI-nano TFLite integer_quant_with_int16_act | 416 | 0.389 | 0.672 | 2.4M | [0, 1] | 200 |
full_integer_quant_with_int16_act
gives me ValueError: Cannot set tensor: Got value of type FLOAT32 but expected type INT16 for input 0, name: serving_default_images:0
. This is not the case for integer_quant_with_int16_act
. Taking the input and .astype(np.int16)
-ing it gives 0
@mikel-brostrom Thanks for sharing your results! https://github.com/PINTO0309/onnx2tf/issues/269#issuecomment-1486969872 The accuracy degradation because of the decoder is interesting..
You may find something if you compare the fp32/int8 TFLite final outputs. Even without onnx2tf's new feature, you can do it by saving output arrays into npy files and then compare them.
The figure below is the one when I quantized YOLOv3.
Left shows the distribution of x
channel, and right shows the distribution of w
channel.
Orange is float, and blue is quantized.
In YOLOv3 case above, w
channel has large quantization error.
If you can visualize the output distribution like this, we may find which channel (x
, y
, w
, h
, and/or, class
) causes this accuracy deguradation.
Just a hunch on my part, but if you do not Concat
at the end, maybe there will be no accuracy degradation. I will have to try it out to find out. In the first place, I feel that the difference in value ranges is too large. Then Concat
may not be relevant.
Ref: https://github.com/PINTO0309/onnx2tf/issues/269#issuecomment-1483090981
By the way, _int16_act
seems to be an experimental implementation of TFLite, so there are still many bugs or unsupported OPs.
https://www.tensorflow.org/lite/performance/post_training_integer_quant_16x8
TensorFlow Lite now supports converting activations to 16-bit integer values
and weights to 8-bit integer values during model conversion from TensorFlow
to TensorFlow Lite's flat buffer format. We refer to this mode as the "16x8 quantization mode".
This mode can improve accuracy of the quantized model significantly,
when activations are sensitive to the quantization, while still achieving almost 3-4x reduction
in model size. Moreover, this fully quantized model can be consumed by integer-only hardware accelerators.
Just a hunch on my part, but if you do not Concat at the end, maybe there will be no accuracy degradation.
Trying this out right away
@PINTO0309 :rocket: ! I just implemented what you explained here: https://github.com/PINTO0309/onnx2tf/issues/269#issuecomment-1488349530. What is the rationale behind this?
Model | size | mAPval 0.5:0.95 |
mAPval 0.5 |
size | xywh model output | calibration images |
---|---|---|---|---|---|---|
YOLOX-TI-nano TFLite FP32 | 416 | 0.390 | 0.653 | 8.7M | [0, 1] | N/A |
YOLOX-TI-nano TFLite FP16 | 416 | 0.390 | 0.653 | 4.4M | [0, 1] | N/A |
YOLOX-TI-nano TFLite full_integer_quant | 416 | 0.362 | 0.641 | 2.4M | [0, 1] | 200 |
YOLOX-TI-nano TFLite full_integer_quant_with_int16_act | 416 | 0 | 0 | 2.4M | [0, 1] | 200 |
YOLOX-TI-nano TFLite dynamic_range_quant | 416 | 0.389 | 0.652 | 2.4M | [0, 1] | 200 |
YOLOX-TI-nano TFLite integer_quant | 416 | 0.362 | 0.641 | 2.4M | [0, 1] | 200 |
YOLOX-TI-nano TFLite integer_quant_with_int16_act | 416 | 0.389 | 0.672 | 2.4M | [0, 1] | 200 |
Issue Type
Others
onnx2tf version number
1.8.1
onnx version number
1.13.1
tensorflow version number
2.12.0
Download URL for ONNX
yolox_nano_ti_lite_26p1_41p8.zip
Parameter Replacement JSON
Description
Hi @PINTO0309. After our lengthy discussion regarding INT8 YOLOX export I decided to try out Ti's version of these models (https://github.com/TexasInstruments/edgeai-yolox/tree/main/pretrained_models). It looked to me that you manged to INT8-export those so maybe you could provide some hints :smile:. I just downloaded the ONNX version of YOLOX-nano. For this model, the following fails:
The error I get: