- 
- 
-
-
-Note
-Click here -to download the full example code
-
-
-
-
- PyTorch FX Numeric Suite Core APIs Tutorial¶
-
-
-Introduction¶
-Quantization is good when it works, but it is difficult to know what is wrong -when it does not satisfy the accuracy we expect. Debugging the accuracy issue -of quantization is not easy and time-consuming.
-One important step of debugging is to measure the statistics of the float model -and its corresponding quantized model to know where they differ most. -We built a suite of numeric tools called PyTorch FX Numeric Suite Core APIs in -PyTorch quantization to enable the measurement of the statistics between -quantized module and float module to support quantization debugging efforts. -Even for the quantized model with good accuracy, PyTorch FX Numeric Suite Core -APIs can still be used as the profiling tool to better understand the -quantization error within the model and provide the guidance for further -optimization.
-PyTorch FX Numeric Suite Core APIs currently supports models quantized through -both static quantization and dynamic quantization with unified APIs.
-In this tutorial we will use MobileNetV2 as an example to show how to use -PyTorch FX Numeric Suite Core APIs to measure the statistics between static -quantized model and float model.
-
-
-
-
-
-
-
-
-
-
-Setup¶
-We’ll start by doing the necessary imports:
-# Imports and util functions
-
-import copy
-import torch
-import torchvision
-import torch.quantization
-import torch.ao.ns._numeric_suite_fx as ns
-import torch.quantization.quantize_fx as quantize_fx
-
-import matplotlib.pyplot as plt
-from tabulate import tabulate
-
-torch.manual_seed(0)
-plt.style.use('seaborn-whitegrid')
-
-
-# a simple line graph
-def plot(xdata, ydata, xlabel, ylabel, title):
- _ = plt.figure(figsize=(10, 5), dpi=100)
- plt.xlabel(xlabel)
- plt.ylabel(ylabel)
- plt.title(title)
- ax = plt.axes()
- ax.plot(xdata, ydata)
- plt.show()
-/var/lib/jenkins/workspace/prototype_source/fx_numeric_suite_tutorial.py:50: MatplotlibDeprecationWarning:
-
-The seaborn styles shipped by Matplotlib are deprecated since 3.6, as they no longer correspond to the styles shipped by seaborn. However, they will remain available as 'seaborn-v0_8-<style>'. Alternatively, directly use the seaborn API instead.
-Then we load the pretrained float MobileNetV2 model, and quantize it.
-# create float model
-mobilenetv2_float = torchvision.models.quantization.mobilenet_v2(
- pretrained=True, quantize=False).eval()
-
-# create quantized model
-qconfig_dict = {
- '': torch.quantization.get_default_qconfig('x86'), # The old 'fbgemm' is still available but 'x86' is the recommended default.
- # adjust the qconfig to make the results more interesting to explore
- 'module_name': [
- # turn off quantization for the first couple of layers
- ('features.0', None),
- ('features.1', None),
- # use MinMaxObserver for `features.17`, this should lead to worse
- # weight SQNR
- ('features.17', torch.quantization.default_qconfig),
- ]
-}
-# Note: quantization APIs are inplace, so we save a copy of the float model for
-# later comparison to the quantized model. This is done throughout the
-# tutorial.
-datum = torch.randn(1, 3, 224, 224)
-mobilenetv2_prepared = quantize_fx.prepare_fx(
- copy.deepcopy(mobilenetv2_float), qconfig_dict, (datum,))
-mobilenetv2_prepared(datum)
-# Note: there is a long standing issue that we cannot copy.deepcopy a
-# quantized model. Since quantization APIs are inplace and we need to use
-# different copies of the quantized model throughout this tutorial, we call
-# `convert_fx` on a copy, so we have access to the original `prepared_model`
-# later. This is done throughout the tutorial.
-mobilenetv2_quantized = quantize_fx.convert_fx(
- copy.deepcopy(mobilenetv2_prepared))
-/opt/conda/lib/python3.10/site-packages/torchvision/models/_utils.py:208: UserWarning:
-
-The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
-
-/opt/conda/lib/python3.10/site-packages/torchvision/models/_utils.py:223: UserWarning:
-
-Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=MobileNet_V2_Weights.IMAGENET1K_V1`. You can also use `weights=MobileNet_V2_Weights.DEFAULT` to get the most up-to-date weights.
-
-Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /var/lib/jenkins/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
- 0%| | 0.00/13.6M [00:00<?, ?B/s]
- 4%|4 | 600k/13.6M [00:00<00:02, 6.11MB/s]
- 46%|####5 | 6.19M/13.6M [00:00<00:00, 37.0MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 54.9MB/s]
-/opt/conda/lib/python3.10/site-packages/torch/ao/quantization/fx/prepare.py:1536: UserWarning:
-
-Passing a QConfig dictionary to prepare is deprecated and will not be supported in a future version. Please pass in a QConfigMapping instead.
-
-/opt/conda/lib/python3.10/site-packages/torch/ao/quantization/observer.py:214: UserWarning:
-
-Please use quant_min and quant_max to specify the range for observers. reduce_range will be deprecated in a future release of PyTorch.
-
-
-
-
-
-
-
-
-1. Compare the weights of float and quantized models¶
-The first analysis we can do is comparing the weights of the fp32 model and -the int8 model by calculating the SQNR between each pair of weights.
-The extract_weights API can be used to extract weights from linear, -convolution and LSTM layers. It works for dynamic quantization as well as -PTQ/QAT.
-# Note: when comparing weights in models with Conv-BN for PTQ, we need to
-# compare weights after Conv-BN fusion for a proper comparison. Because of
-# this, we use `prepared_model` instead of `float_model` when comparing
-# weights.
-
-# Extract conv and linear weights from corresponding parts of two models, and
-# save them in `wt_compare_dict`.
-mobilenetv2_wt_compare_dict = ns.extract_weights(
- 'fp32', # string name for model A
- mobilenetv2_prepared, # model A
- 'int8', # string name for model B
- mobilenetv2_quantized, # model B
-)
-
-# calculate SQNR between each pair of weights
-ns.extend_logger_results_with_comparison(
- mobilenetv2_wt_compare_dict, # results object to modify inplace
- 'fp32', # string name of model A (from previous step)
- 'int8', # string name of model B (from previous step)
- torch.ao.ns.fx.utils.compute_sqnr, # tensor comparison function
- 'sqnr', # the name to use to store the results under
-)
-
-# massage the data into a format easy to graph and print
-mobilenetv2_wt_to_print = []
-for idx, (layer_name, v) in enumerate(mobilenetv2_wt_compare_dict.items()):
- mobilenetv2_wt_to_print.append([
- idx,
- layer_name,
- v['weight']['int8'][0]['prev_node_target_type'],
- v['weight']['int8'][0]['values'][0].shape,
- v['weight']['int8'][0]['sqnr'][0],
- ])
-
-# plot the SQNR between fp32 and int8 weights for each layer
-plot(
- [x[0] for x in mobilenetv2_wt_to_print],
- [x[4] for x in mobilenetv2_wt_to_print],
- 'idx',
- 'sqnr',
- 'weights, idx to sqnr'
-)
-Also print out the SQNR, so we can inspect the layer name and type:
-print(tabulate(
- mobilenetv2_wt_to_print,
- headers=['idx', 'layer_name', 'type', 'shape', 'sqnr']
-))
- idx layer_name type shape sqnr
------ -------------------- ------------------------------------------------------------ ----------------------------- --------
- 0 features_0_0 torch.ao.nn.intrinsic.modules.fused.ConvReLU2d torch.Size([32, 3, 3, 3]) inf
- 1 features_1_conv_0_0 torch.ao.nn.intrinsic.modules.fused.ConvReLU2d torch.Size([32, 1, 3, 3]) inf
- 2 features_1_conv_1 torch.nn.modules.conv.Conv2d torch.Size([16, 32, 1, 1]) inf
- 3 features_2_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([96, 16, 1, 1]) 45.3583
- 4 features_2_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([96, 1, 3, 3]) 46.3591
- 5 features_2_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([24, 96, 1, 1]) 43.1405
- 6 features_3_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([144, 24, 1, 1]) 45.1226
- 7 features_3_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([144, 1, 3, 3]) 44.8846
- 8 features_3_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([24, 144, 1, 1]) 42.2562
- 9 features_4_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([144, 24, 1, 1]) 44.7671
- 10 features_4_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([144, 1, 3, 3]) 47.5017
- 11 features_4_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([32, 144, 1, 1]) 42.4501
- 12 features_5_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([192, 32, 1, 1]) 44.8431
- 13 features_5_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([192, 1, 3, 3]) 44.955
- 14 features_5_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([32, 192, 1, 1]) 43.0342
- 15 features_6_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([192, 32, 1, 1]) 44.7193
- 16 features_6_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([192, 1, 3, 3]) 45.2428
- 17 features_6_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([32, 192, 1, 1]) 42.7734
- 18 features_7_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([192, 32, 1, 1]) 44.5686
- 19 features_7_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([192, 1, 3, 3]) 47.4552
- 20 features_7_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([64, 192, 1, 1]) 42.6587
- 21 features_8_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([384, 64, 1, 1]) 44.091
- 22 features_8_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([384, 1, 3, 3]) 45.0733
- 23 features_8_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([64, 384, 1, 1]) 42.3311
- 24 features_9_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([384, 64, 1, 1]) 44.2334
- 25 features_9_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([384, 1, 3, 3]) 45.5776
- 26 features_9_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([64, 384, 1, 1]) 42.0875
- 27 features_10_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([384, 64, 1, 1]) 44.2595
- 28 features_10_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([384, 1, 3, 3]) 45.3682
- 29 features_10_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([64, 384, 1, 1]) 41.3764
- 30 features_11_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([384, 64, 1, 1]) 43.9487
- 31 features_11_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([384, 1, 3, 3]) 43.7704
- 32 features_11_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([96, 384, 1, 1]) 41.963
- 33 features_12_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([576, 96, 1, 1]) 43.8682
- 34 features_12_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([576, 1, 3, 3]) 45.3413
- 35 features_12_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([96, 576, 1, 1]) 41.8074
- 36 features_13_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([576, 96, 1, 1]) 43.9367
- 37 features_13_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([576, 1, 3, 3]) 45.3374
- 38 features_13_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([96, 576, 1, 1]) 40.3783
- 39 features_14_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([576, 96, 1, 1]) 43.3986
- 40 features_14_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([576, 1, 3, 3]) 47.4357
- 41 features_14_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([160, 576, 1, 1]) 41.8716
- 42 features_15_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([960, 160, 1, 1]) 43.4877
- 43 features_15_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([960, 1, 3, 3]) 46.1367
- 44 features_15_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([160, 960, 1, 1]) 41.2812
- 45 features_16_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([960, 160, 1, 1]) 43.5446
- 46 features_16_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([960, 1, 3, 3]) 45.7084
- 47 features_16_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([160, 960, 1, 1]) 41.2971
- 48 features_17_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([960, 160, 1, 1]) 33.8474
- 49 features_17_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([960, 1, 3, 3]) 34.8042
- 50 features_17_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([320, 960, 1, 1]) 38.6114
- 51 features_18_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1280, 320, 1, 1]) 42.8171
- 52 classifier_1 torch.ao.nn.quantized.modules.linear.Linear torch.Size([1000, 1280]) 42.5315
-
-
-
-
-
-
-
-
-
-
-2. Compare activations API¶
-The second tool allows for comparison of activations between float and -quantized models at corresponding locations for the same input.
-
-
-
-
-The add_loggers/extract_logger_info API can be used to to extract -activations from any layer with a torch.Tensor return type. It works for -dynamic quantization as well as PTQ/QAT.
-# Compare unshadowed activations
-
-# Create a new copy of the quantized model, because we cannot `copy.deepcopy`
-# a quantized model.
-mobilenetv2_quantized = quantize_fx.convert_fx(
- copy.deepcopy(mobilenetv2_prepared))
-mobilenetv2_float_ns, mobilenetv2_quantized_ns = ns.add_loggers(
- 'fp32', # string name for model A
- copy.deepcopy(mobilenetv2_prepared), # model A
- 'int8', # string name for model B
- mobilenetv2_quantized, # model B
- ns.OutputLogger, # logger class to use
-)
-
-# feed data through network to capture intermediate activations
-mobilenetv2_float_ns(datum)
-mobilenetv2_quantized_ns(datum)
-
-# extract intermediate activations
-mobilenetv2_act_compare_dict = ns.extract_logger_info(
- mobilenetv2_float_ns, # model A, with loggers (from previous step)
- mobilenetv2_quantized_ns, # model B, with loggers (from previous step)
- ns.OutputLogger, # logger class to extract data from
- 'int8', # string name of model to use for layer names for the output
-)
-
-# add SQNR comparison
-ns.extend_logger_results_with_comparison(
- mobilenetv2_act_compare_dict, # results object to modify inplace
- 'fp32', # string name of model A (from previous step)
- 'int8', # string name of model B (from previous step)
- torch.ao.ns.fx.utils.compute_sqnr, # tensor comparison function
- 'sqnr', # the name to use to store the results under
-)
-
-# massage the data into a format easy to graph and print
-mobilenet_v2_act_to_print = []
-for idx, (layer_name, v) in enumerate(mobilenetv2_act_compare_dict.items()):
- mobilenet_v2_act_to_print.append([
- idx,
- layer_name,
- v['node_output']['int8'][0]['prev_node_target_type'],
- v['node_output']['int8'][0]['values'][0].shape,
- v['node_output']['int8'][0]['sqnr'][0]])
-
-# plot the SQNR between fp32 and int8 activations for each layer
-plot(
- [x[0] for x in mobilenet_v2_act_to_print],
- [x[4] for x in mobilenet_v2_act_to_print],
- 'idx',
- 'sqnr',
- 'unshadowed activations, idx to sqnr',
-)
-/opt/conda/lib/python3.10/site-packages/torch/ao/quantization/observer.py:214: UserWarning:
-
-Please use quant_min and quant_max to specify the range for observers. reduce_range will be deprecated in a future release of PyTorch.
-Also print out the SQNR, so we can inspect the layer name and type:
-print(tabulate(
- mobilenet_v2_act_to_print,
- headers=['idx', 'layer_name', 'type', 'shape', 'sqnr']
-))
- idx layer_name type shape sqnr
------ -------------------- ------------------------------------------------------------ ----------------------------- --------
- 0 features_0_0 torch.ao.nn.intrinsic.modules.fused.ConvReLU2d torch.Size([1, 32, 112, 112]) inf
- 1 features_1_conv_0_0 torch.ao.nn.intrinsic.modules.fused.ConvReLU2d torch.Size([1, 32, 112, 112]) inf
- 2 features_1_conv_1 torch.nn.modules.conv.Conv2d torch.Size([1, 16, 112, 112]) inf
- 3 features_2_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 96, 112, 112]) 29.0991
- 4 features_2_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 96, 56, 56]) 25.2115
- 5 features_2_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([1, 24, 56, 56]) 24.5646
- 6 features_3_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 144, 56, 56]) 27.2
- 7 features_3_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 144, 56, 56]) 22.0608
- 8 features_3_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([1, 24, 56, 56]) 20.7146
- 9 add torch._ops.quantized.PyCapsule.add torch.Size([1, 24, 56, 56]) 19.8953
- 10 features_4_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 144, 56, 56]) 21.3246
- 11 features_4_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 144, 28, 28]) 22.9555
- 12 features_4_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([1, 32, 28, 28]) 21.5757
- 13 features_5_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 192, 28, 28]) 26.2408
- 14 features_5_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 192, 28, 28]) 19.2934
- 15 features_5_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([1, 32, 28, 28]) 16.944
- 16 add_1 torch._ops.quantized.PyCapsule.add torch.Size([1, 32, 28, 28]) 19.0961
- 17 features_6_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 192, 28, 28]) 22.585
- 18 features_6_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 192, 28, 28]) 18.3034
- 19 features_6_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([1, 32, 28, 28]) 15.034
- 20 add_2 torch._ops.quantized.PyCapsule.add torch.Size([1, 32, 28, 28]) 18.3704
- 21 features_7_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 192, 28, 28]) 20.4532
- 22 features_7_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 192, 14, 14]) 25.3305
- 23 features_7_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([1, 64, 14, 14]) 21.1715
- 24 features_8_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 384, 14, 14]) 27.0235
- 25 features_8_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 384, 14, 14]) 20.7113
- 26 features_8_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([1, 64, 14, 14]) 22.4801
- 27 add_3 torch._ops.quantized.PyCapsule.add torch.Size([1, 64, 14, 14]) 20.6856
- 28 features_9_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 384, 14, 14]) 24.7087
- 29 features_9_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 384, 14, 14]) 21.0379
- 30 features_9_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([1, 64, 14, 14]) 19.4405
- 31 add_4 torch._ops.quantized.PyCapsule.add torch.Size([1, 64, 14, 14]) 18.3986
- 32 features_10_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 384, 14, 14]) 21.9657
- 33 features_10_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 384, 14, 14]) 20.4307
- 34 features_10_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([1, 64, 14, 14]) 18.2502
- 35 add_5 torch._ops.quantized.PyCapsule.add torch.Size([1, 64, 14, 14]) 17.2593
- 36 features_11_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 384, 14, 14]) 20.6413
- 37 features_11_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 384, 14, 14]) 21.4936
- 38 features_11_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([1, 96, 14, 14]) 16.453
- 39 features_12_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 576, 14, 14]) 20.3278
- 40 features_12_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 576, 14, 14]) 20.0808
- 41 features_12_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([1, 96, 14, 14]) 14.4468
- 42 add_6 torch._ops.quantized.PyCapsule.add torch.Size([1, 96, 14, 14]) 15.5235
- 43 features_13_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 576, 14, 14]) 19.66
- 44 features_13_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 576, 14, 14]) 20.665
- 45 features_13_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([1, 96, 14, 14]) 14.5214
- 46 add_7 torch._ops.quantized.PyCapsule.add torch.Size([1, 96, 14, 14]) 15.2789
- 47 features_14_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 576, 14, 14]) 18.8154
- 48 features_14_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 576, 7, 7]) 24.1442
- 49 features_14_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([1, 160, 7, 7]) 17.8406
- 50 features_15_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 960, 7, 7]) 20.9833
- 51 features_15_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 960, 7, 7]) 20.9399
- 52 features_15_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([1, 160, 7, 7]) 16.5824
- 53 add_8 torch._ops.quantized.PyCapsule.add torch.Size([1, 160, 7, 7]) 16.9591
- 54 features_16_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 960, 7, 7]) 20.2238
- 55 features_16_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 960, 7, 7]) 20.3089
- 56 features_16_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([1, 160, 7, 7]) 15.7145
- 57 add_9 torch._ops.quantized.PyCapsule.add torch.Size([1, 160, 7, 7]) 16.014
- 58 features_17_conv_0_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 960, 7, 7]) 17.3424
- 59 features_17_conv_1_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 960, 7, 7]) 27.073
- 60 features_17_conv_2 torch.ao.nn.quantized.modules.conv.Conv2d torch.Size([1, 320, 7, 7]) 15.3544
- 61 features_18_0 torch.ao.nn.intrinsic.quantized.modules.conv_relu.ConvReLU2d torch.Size([1, 1280, 7, 7]) 15.3328
- 62 adaptive_avg_pool2d torch.nn.functional.adaptive_avg_pool2d torch.Size([1, 1280, 1, 1]) 18.7136
- 63 flatten torch._VariableFunctionsClass.flatten torch.Size([1, 1280]) 18.7136
- 64 classifier_0 torch.ao.nn.quantized.modules.dropout.Dropout torch.Size([1, 1280]) 18.7136
- 65 classifier_1 torch.ao.nn.quantized.modules.linear.Linear torch.Size([1, 1000]) 20.0098
-Total running time of the script: ( 0 minutes 6.825 seconds)
- - -
-