g[NddlmZddlmZmZmZddlZddlZddlm Z ddl m Z m Z ddl mZmZddlmZdd lmZdd lmZd d lmZejeZGd de ZGdde ZGddeZeGddeZGddeZdS)) dataclass)OptionalTupleUnionN)CrossEntropyLoss)InstructBlipQFormerConfigInstructBlipVisionConfig)$InstructBlipForConditionalGeneration/InstructBlipForConditionalGenerationModelOutput)PretrainedConfig)!MODEL_FOR_CAUSAL_LM_MAPPING_NAMES)logging)CONFIG_MAPPINGceZdZdS)InstructBlipVideoVisionConfigN__name__ __module__ __qualname__{/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/instructblipvideo/modular_instructblipvideo.pyrr)DrrceZdZdS)InstructBlipVideoQFormerConfigNrrrrrr-rrrcVeZdZdZdZ d fd Zededede fd Z xZ S) InstructBlipVideoConfiga [`InstructBlipVideoConfig`] is the configuration class to store the configuration of a [`InstructBlipVideoForConditionalGeneration`]. It is used to instantiate a Instructblipvideo model according to the specified arguments, defining the vision model, Q-Former model and language model configs. Instantiating a configuration with the defaults will yield a similar configuration to that of the Instructblipvideo [Salesforce/instruct-blip-flan-t5](https://huggingface.co/Salesforce/instruct-blip-flan-t5) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: vision_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`InstructBlipVideoVisionConfig`]. qformer_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`InstructBlipVideoQFormerConfig`]. text_config (`dict`, *optional*): Dictionary of configuration options used to initialize any [`PretrainedConfig`]. num_query_tokens (`int`, *optional*, defaults to 32): The number of query tokens passed through the Transformer. video_token_index (`int`, *optional*): Token index of special video token. kwargs (*optional*): Dictionary of keyword arguments. Example: ```python >>> from transformers import ( ... InstructBlipVideoVisionConfig, ... InstructBlipVideoQFormerConfig, ... OPTConfig, ... InstructBlipVideoConfig, ... InstructBlipVideoForConditionalGeneration, ... ) >>> # Initializing a InstructBlipVideoConfig with Salesforce/instruct-blip-flan-t5 style configuration >>> configuration = InstructBlipVideoConfig() >>> # Initializing a InstructBlipVideoForConditionalGeneration (with random weights) from the Salesforce/instruct-blip-flan-t5 style configuration >>> model = InstructBlipVideoForConditionalGeneration(configuration) >>> # Accessing the model configuration >>> configuration = model.config >>> # We can also initialize a InstructBlipVideoConfig from a InstructBlipVideoVisionConfig, InstructBlipVideoQFormerConfig and any PretrainedConfig >>> # Initializing Instructblipvideo vision, Instructblipvideo Q-Former and language model configurations >>> vision_config = InstructBlipVideoVisionConfig() >>> qformer_config = InstructBlipVideoQFormerConfig() >>> text_config = OPTConfig() >>> config = InstructBlipVideoConfig.from_text_vision_configs(vision_config, qformer_config, text_config) ```instructblipvideoN c Ttjdi||i}td|i}td|i}tdt di||_t di||_d|vr|dnd}t|di||_ |j j |_ |j j |_ ||_ ||_ |jj|j_|j jt"v|_d|_d|_dS) NzZvision_config is None. initializing the InstructBlipVideoVisionConfig with default values.z\qformer_config is None. Initializing the InstructBlipVideoQFormerConfig with default values.zTtext_config is None. Initializing the text config with default values (`OPTConfig`). model_typeoptg?g{Gz?r)super__init__loggerinfor vision_configrqformer_configr text_configtie_word_embeddingsis_encoder_decodernum_query_tokensvideo_token_index hidden_sizeencoder_hidden_sizer#ruse_decoder_only_language_modelinitializer_factorinitializer_range) selfr)r*r+r.r/kwargstext_model_type __class__s rr&z InstructBlipVideoConfig.__init__ksD ""6"""  M KKt u u u  !N KKv w w w  K KKn o o o:KK]KK<NN~NN7C{7R7R+l33X])/:II[II#'#3#G "&"2"E 0!2262D2P//3/?/JNo/o,"%!%rr)r*r+c |d|||d|S)a  Instantiate a [`InstructBlipVideoConfig`] (or a derived class) from a InstructBlipVideo vision model, Q-Former and language model configurations. Returns: [`InstructBlipVideoConfig`]: An instance of a configuration object )r)r*r+r)to_dict)clsr)r*r+r6s r from_vision_qformer_text_configsz8InstructBlipVideoConfig.from_vision_qformer_text_configssY s '//11)1133#++--      r)NNNr!N) rrr__doc__r#r& classmethodrrr r< __classcell__)r8s@rrr1s5 5 n%J $&$&$&$&$&$&L 4 7 &    [     rrceZdZdS)4InstructBlipVideoForConditionalGenerationModelOutputNrrrrrArAsDrrAceZdZ ddejdejdeejdeejdeejdeejd eejd eed eed eejd eededee e ffdZ ej ddejdeejdeejdeejdeejdedejfdZ dS))InstructBlipVideoForConditionalGenerationNF pixel_valuesqformer_input_idsqformer_attention_mask input_idsattention_maskdecoder_input_idsdecoder_attention_maskoutput_attentionsoutput_hidden_stateslabels return_dictinterpolate_pos_encodingreturnc | | | n |jj} |j\} }}}}|| |z|||}|||| | | }|d}t j|ddt j|j }|j |jddd}t j|ddt j|j }|t j |}| |d}| |d}t j||gd}|||||||| | }|dddd|dddf}||}|| |jj|zd}t j|ddt j|j }|j|}|t j |}t)|jd dN||jjkd|}|||<nzt2d t j|||j gd}t j|||j gd}|jjr||||| | }| r|jn|d}d}| | |j } |dd| d dddf}|d ddddf} | d ddf|j }!t?d }"|"| d|jj!j"|! d}n?||||||| | | }| r|j#n|d}| r|jn|d}| s||||f}#||f|#zn|#StI|||||S)a0 ```python >>> from transformers import InstructBlipVideoProcessor, InstructBlipVideoForConditionalGeneration >>> import torch >>> from huggingface_hub import hf_hub_download >>> import av >>> import numpy as np >>> def read_video_pyav(container, indices): ... ''' ... Decode the video with PyAV decoder. ... Args: ... container (`av.container.input.InputContainer`): PyAV container. ... indices (`List[int]`): List of frame indices to decode. ... Returns: ... result (np.ndarray): np array of decoded frames of shape (num_frames, height, width, 3). ... ''' ... frames = [] ... container.seek(0) ... start_index = indices[0] ... end_index = indices[-1] ... for i, frame in enumerate(container.decode(video=0)): ... if i > end_index: ... break ... if i >= start_index and i in indices: ... frames.append(frame) ... return np.stack([x.to_ndarray(format="rgb24") for x in frames]) >>> model = InstructBlipVideoForConditionalGeneration.from_pretrained("Salesforce/instructblip-vicuna-7b", device_map="auto") >>> processor = InstructBlipVideoProcessor.from_pretrained("Salesforce/instructblip-vicuna-7b") >>> file_path = hf_hub_download( ... repo_id="nielsr/video-demo", filename="eating_spaghetti.mp4", repo_type="dataset" ... ) >>> container = av.open(file_path) >>> # sample uniformly 4 frames from the videWhy is this video funny?o >>> total_frames = container.streams.video[0].frames >>> indices = np.arange(0, total_frames, total_frames / 4).astype(int) >>> clip = read_video_pyav(container, indices) >>> prompt = "What is happening in the video?" >>> inputs = processor(text=prompt, images=clip, return_tensors="pt").to(model.device) >>> outputs = model.generate( ... **inputs, ... do_sample=False, ... num_beams=5, ... max_length=256, ... repetition_penalty=1.5, ... length_penalty=1.0, ... ) >>> generated_text = processor.batch_decode(outputs, skip_special_tokens=True)[0].strip() >>> print(generated_text) "A person is eating a bowl of pasta, and they are using a fork to eat it. The person is sitting at a table, and the plate of pasta is on the table in front" ```N)rDrKrLrNrOrdtypedevicedim)rGrH query_embedsencoder_hidden_statesencoder_attention_maskrKrLrNr/KExpanding inputs for video tokens in InstructBLIPVideo should be done in processing. Please follow instruction here (https://gist.github.com/zucchini-nlp/65f22892b054dc0d68228af56fbeaac2) to update your InstructBLIPVideo model. Using processors without these attributes in the config is deprecated and will throw an error in v4.47.) inputs_embedsrHrKrLrN.mean) reduction)r]rHrIrJrKrLrNrM)losslogitsvision_outputsqformer_outputslanguage_model_outputs)%configuse_return_dictshapereshape vision_modeltorchonessizelongrU query_tokensexpand ones_likerepeat_interleavecatqformerlanguage_projectionr.language_modelget_input_embeddingsgetattrr/ unsqueeze expand_asflattenr' warning_oncetor2ra contiguousrviewr+ vocab_sizer`rA)$r5rDrErFrGrHrIrJrKrLrMrNrO batch_sizeframeschannelheightwidthrb image_embedsimage_attention_maskrnquery_attention_mask query_outputs query_outputlanguage_model_inputslanguage_model_attention_maskr]special_image_maskoutputsrar` shift_logits shift_labelsloss_fctoutputs$ rforwardz1InstructBlipVideoForConditionalGeneration.forwardsFN&1%->q-A-A+A111(DE !% 8 8 F F!6 = =j$+JfioJoqs t t(- ! & & ( (" -UZH]Hd) ) ) %C+@@BB9MM  !"_Y77N 4; 3T : : F"+t{/L"L!W!WXZ![![!e!efs!t!t 0E0M0M0O0OM, - -   z    "I'N>NOdOk>l>l&mstuuuM"Y.0A0AB_Bf0g0ghnoN ; 6" C))+-"3%9' *G(3BW^^ FD!6=11FKKNN?#4#4aaa 78%c3B3k2==?? %c122g99;;>>v}MM ,f===x 1 1"dk6M6X Y Y[g[l[lmo[p[pqq))+-"3'="3%9'*  G$/>7< d t j|||j gd }t j|||j gd }|j!jj"sQ|#d d|jd zd z |d <|#dd|jd z|d<|j!j$d||d|}|j!jj"s|jjj%ddkrdn|jjj}t j|gg|d | j }tM|t j's#t j||j(gd|_(nt j||gd}|S)a Overrides `generate` function to be able to use the model as a conditional generator. Args: pixel_values (`torch.FloatTensor` of shape (batch_size, num_channels, height, width) or (batch_size, num_frames, num_channels, height, width)): Input images or videos to be processed. qformer_input_ids (`torch.LongTensor` of shape (batch_size, sequence_length), *optional*): The sequence used as a prompt to be fed to the Q-Former module. qformer_attention_mask (`torch.LongTensor` of shape (batch_size, sequence_length), *optional*): Mask to avoid performing attention on padding token indices. input_ids (`torch.LongTensor` of shape (batch_size, sequence_length), *optional*): The sequence used as a prompt for the generation. attention_mask (`torch.LongTensor` of shape (batch_size, sequence_length), *optional*): Mask to avoid performing attention on padding token indices. interpolate_pos_encoding (`bool`, *optional*, defaults to `False`): Whether to interpolate the positional encoding of the image embeddings. Returns: captions (list): A list of strings of length batch_size * num_captions. hf_device_mapT)rNrONrRrSrrVrX)rGrHrYrZr[rNr/r\ max_length min_length)r]rHLLaMAForCausalLMrr))hasattr_preprocess_acceleratergrhrilast_hidden_staterjrkrlrmrUrnrorprqrrrsrtrer. LongTensorr+ bos_token_idrepeatr|rvrwr/rxryrzr'r{rur-getgenerate architectures isinstanceTensor sequences)r5rDrErFrGrHrOgenerate_kwargsrrrrrrrrnrrrrlanguage_attention_maskr]rrr bos_tokenss rrz2InstructBlipVideoForConditionalGeneration.generatels> 4 ) ) *  ' ' ) ) )6B5G2 FGVU#++J,?&RWXX (( %=)     %z,*;*;*=*=crc*B%*]i]pqqq(// 0B10Er2NN $z,*;*;*=*=crc*B%*]i]pqqq ! )%*_5F%G%G "-??A?NN!7!I!I&VW!I!X!X!&,@BX+Y_`!a!a!a '1%".#7 %  %6qqq:PL>  4; 3T : : F"+t{/L"L!W!WXZ![![!e!efs!t!t 0E0M0M0O0OM, - -   z    "I'N>NOdOk>l>l&mstuuuM"Y(.*;*;*:;;BB:qQQTTUaUhiiJgu|44 C$)Iz7;L.MSU$V$V$V!!)Z$9rBBBr) NNNNNNNNNF)NNNNF)rrrrj FloatTensorrrboolrrrArno_gradrrrrrCrCs >B15598<=A,0/3-1&*).{ { '{ !,{ !))9 : { E-. { !!12 { $E$45{ !))9 :{ $D>{ 'tn{ )*{ d^{ #'{  uJJ K{ { { { zU]__9==A0459).AA'A$E$45A!))9 : A E,- A !!12 A#'A  AAA_AAArrC) dataclassesrtypingrrrrjtorch.utils.checkpointtorch.nnr;transformers.models.instructblip.configuration_instructbliprr 6transformers.models.instructblip.modeling_instructblipr r configuration_utilsr models.auto.modeling_autorutilsrautor get_loggerrr'rrrrArCrrrrs  "!!!!!)))))))))) %%%%%% 433333JJJJJJ!!!!!!  H % %     $<        %>   u u u u u .u u u p      ;j    @@@@@0T@@@@@r