o ॵik,@sdZddlZddlZejdkrddlZnddlmZejdkr#ejj ZGddde dgdZ ddd Z dd d Z ej  dd dZ    dddZdS)a Contains building blocks for various versions of Residual Networks. Residual networks (ResNets) were proposed in: Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun Deep Residual Learning for Image Recognition. arXiv:1512.03385, 2015 More variants were introduced in: Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun Identity Mappings in Deep Residual Networks. arXiv: 1603.05027, 2016 We can obtain different ResNet variants by changing the network depth, width, and form of residual unit. This module implements the infrastructure for building them. Concrete ResNet units and full ResNet networks are implemented in the accompanying resnet_v1.py and resnet_v2.py modules. Compared to https://github.com/KaimingHe/deep-residual-networks, in the current implementation we subsample the output activations in the last residual unit of each block, instead of subsampling the input activations in the first residual unit of each block. The two implementations give identical results but our implementation is more memory efficient. Nz2.0)slimc@seZdZdZdS)BlockaA named tuple describing a ResNet block. Its parts are: scope: The scope of the `Block`. unit_fn: The ResNet unit function which takes as input a `Tensor` and returns another `Tensor` with the output of the ResNet unit. args: A list of length equal to the number of units in the `Block`. The list contains one (depth, depth_bottleneck, stride) tuple for each unit in the block to serve as argument to unit_fn. N)__name__ __module__ __qualname____doc__rrb/home/ubuntu/.local/lib/python3.10/site-packages/modelscope/pipelines/cv/ocr_utils/resnet_utils.pyr.sr)scopeunit_fnargscCs"|dkr|Stj|ddg||dS)aSubsamples the input along the spatial dimensions. Args: inputs: A `Tensor` of size [batch, height_in, width_in, channels]. factor: The subsampling factor. scope: Optional variable_scope. Returns: output: A `Tensor` of size [batch, height_out, width_out, channels] with the input, either intact (if factor == 1) or subsampled (if factor > 1). )strider )r max_pool2d)inputsfactorr rrr subsample:s rr c Cs|dkrtj|||d|d|dS||d|d}|d}|d}||} t|ddg|| g|| gddgg}tj|||||d|dS)a4Strided 2-D convolution with 'SAME' padding. When stride > 1, then we do explicit zero-padding, followed by conv2d with 'VALID' padding. Note that net = conv2d_same(inputs, num_outputs, 3, stride=stride) is equivalent to net = slim.conv2d(inputs, num_outputs, 3, stride=1, padding='SAME') net = subsample(net, factor=stride) whereas net = slim.conv2d(inputs, num_outputs, 3, stride=stride, padding='SAME') is different when the input's height or width is even, which is why we add the current function. For more details, see ResnetUtilsTest.testConv2DSameEven(). Args: inputs: A 4-D tensor of size [batch, height_in, width_in, channels]. num_outputs: An integer, the number of output filters. kernel_size: An int with the kernel_size of the filters. stride: An integer, the output stride. rate: An integer, rate for atrous convolution. scope: Scope. Returns: output: A 4-D tensor of size [batch, height_out, width_out, channels] with the convolution output. r SAME)rratepaddingr rVALID)rconv2dtfpad) r num_outputs kernel_sizerrr kernel_size_effective pad_totalpad_begpad_endrrr conv2d_sameJs4 r!c Cs*d}d}|D]}t|jd|gmt|jD]_\}}|dur'||kr'tdtjd|d|gd;} |\} } } |durP||krP|j|| | d|d}|| 9}n|j|| | | dd}|| 9}tj || j |}Wdn1sqwYqWdn1swYq|dur||krtd|S)a=Stacks ResNet `Blocks` and controls output feature density. First, this function creates scopes for the ResNet in the form of 'block_name/unit_1', 'block_name/unit_2', etc. Second, this function allows the user to explicitly control the ResNet output_stride, which is the ratio of the input to output spatial resolution. This is useful for dense prediction tasks such as semantic segmentation or object detection. Most ResNets consist of 4 ResNet blocks and subsample the activations by a factor of 2 when transitioning between consecutive ResNet blocks. This results to a nominal ResNet output_stride equal to 8. If we set the output_stride to half the nominal network stride (e.g., output_stride=4), then we compute responses twice. Control of the output feature density is implemented by atrous convolution. Args: net: A `Tensor` of size [batch, height, width, channels]. blocks: A list of length equal to the number of ResNet `Blocks`. Each element is a ResNet `Block` object describing the units in the `Block`. output_stride: If `None`, then the output will be computed at the nominal network stride. If output_stride is not `None`, it specifies the requested ratio of input to output spatial resolution, which needs to be equal to the product of unit strides from the start up to some level of the ResNet. For example, if the ResNet employs units with strides 1, 2, 1, 3, 4, 1, then valid values for the output_stride are 1, 2, 6, 24 or None (which is equivalent to output_stride=24). outputs_collections: Collection to add the ResNet block outputs. Returns: net: Output tensor with stride equal to the specified output_stride. Raises: ValueError: If the target output_stride is not valid. r blockNz+The target output_stride cannot be reached.zunit_%d)values)depthdepth_bottleneckrr) rvariable_scoper enumerater ValueErrorr rutilscollect_named_outputsname) netblocks output_strideoutputs_collectionscurrent_striderr"iunitsc unit_depthunit_depth_bottleneck unit_striderrr stack_blocks_dense|sT'   r7-C6?灕Cl?h㈵>Tc Cs|||tjjd}tjtjgt|ttjj tj |dUtjtj gfi|1tjtj gdd}|WdWdWdS1sOwYWdn1s^wYWddSWddS1svwYdS)axDefines the default ResNet arg scope. TODO(gpapan): The batch-normalization related default values above are appropriate for use in conjunction with the reference ResNet models released at https://github.com/KaimingHe/deep-residual-networks. When training ResNets from scratch, they might need to be tuned. Args: weight_decay: The weight decay to use for regularizing the model. batch_norm_decay: The moving average decay when estimating layer activation statistics in batch normalization. batch_norm_epsilon: Small constant to prevent division by zero when normalizing activations by their variance in batch normalization. batch_norm_scale: If True, uses an explicit `gamma` multiplier to scale the activations in the batch normalization layer. Returns: An `arg_scope` to use for the resnet models. )decayepsilonscaleupdates_collections)weights_regularizerweights_initializer activation_fn normalizer_fnnormalizer_paramsr)rN) r GraphKeys UPDATE_OPSr arg_scoperl2_regularizervariance_scaling_initializernnrelu batch_normr) weight_decaybatch_norm_decaybatch_norm_epsilonbatch_norm_scalebatch_norm_paramsarg_scrrr resnet_arg_scopes0"rR)N)r N)NN)r8r9r:T)r collections tensorflowr __version__tf_slimrtensorflow.contribcompatv1 namedtuplerrr! add_arg_scoper7rRrrrr s(     2 R